# Hodios paste pack: Course design
Everything in Course design from Hodios, the open prompt library by Hermes IDE: 57 entries, catalog 2026.1004.3.
Every entry is dedicated to the public domain under CC0 1.0. Copy, change and share them freely, no attribution needed.
Browse and search the library at https://hermes-ide.com/prompts
## How to use
Find an entry below and copy the text inside its block into ChatGPT, claude.ai or any chat. Replace each [PLACEHOLDER] with your own material. Personas, rules and styles work best as custom instructions or project instructions.
## Contents
- Course design
- [Adapt a course for low bandwidth](#adapt-course-for-low-bandwidth) (prompt)
- [Analyse course evaluations](#analyze-course-evaluations) (prompt)
- [Build a course reading list](#build-course-reading-list) (prompt)
- [Build a scope and sequence](#build-scope-and-sequence) (prompt)
- [Build a self-study curriculum](#build-self-study-curriculum) (prompt)
- [Convert an in-person course to online](#convert-course-to-online) (prompt)
- [Corporate trainer](#corporate-trainer) (persona)
- [Course accessibility retrofit track](#course-accessibility-retrofit-track) (workflow)
- [Course design track](#course-design-track) (workflow)
- [Design a blended learning programme](#design-blended-program) (prompt)
- [Design a branching training scenario](#design-branching-scenario) (prompt)
- [Design a community ESOL course](#design-esol-course-for-adults) (prompt)
- [Design a course outline](#design-course-outline) (prompt)
- [Design a family learning course](#design-family-learning-course) (prompt)
- [Design a farmer field school](#design-farmer-field-school) (prompt)
- [Design a hands-on workshop](#design-workshop) (prompt)
- [Design a higher-education capstone](#design-capstone-project) (prompt)
- [Design a microlearning series](#design-microlearning-series) (prompt)
- [Design a peer learning circle](#design-peer-learning-circle) (prompt)
- [Design a peer-led learning group for retirees](#design-retiree-learning-group) (prompt)
- [Design a placement learning plan for hosts](#design-work-placement-curriculum) (prompt)
- [Design a recertification refresher](#design-recertification-refresher) (prompt)
- [Design a role-based onboarding curriculum](#design-onboarding-curriculum) (prompt)
- [Design a school outreach session](#design-school-outreach-session) (prompt)
- [Design a summer bridge programme](#design-summer-bridge-programme) (prompt)
- [Design an adult evening class](#design-adult-evening-class) (prompt)
- [Design an apprenticeship training plan](#design-apprenticeship-plan) (prompt)
- [Design an e-learning module](#design-elearning-module) (prompt)
- [Design an intensive bootcamp curriculum](#design-bootcamp-curriculum) (prompt)
- [Design course gamification](#design-course-gamification) (prompt)
- [Design online discussion tasks](#design-online-discussion-tasks) (prompt)
- [Design volunteer induction training](#design-volunteer-induction-training) (prompt)
- [Estimate course build effort](#estimate-course-build-effort) (prompt)
- [Instructional designer](#instructional-designer) (persona)
- [Map a course to qualification standards](#map-course-to-qualification-standards) (prompt)
- [Map programme outcomes across courses](#map-program-curriculum) (prompt)
- [Peer tutoring launch track](#peer-tutoring-launch-track) (workflow)
- [Plan a course pilot](#plan-course-pilot) (prompt)
- [Plan a course's assessment mix](#plan-course-assessment-mix) (prompt)
- [Plan a customer training programme](#plan-customer-training-program) (prompt)
- [Plan a homeschool year](#plan-homeschool-year) (prompt)
- [Plan a multi-age homeschool week](#plan-multi-age-homeschool-week) (prompt)
- [Plan a paid online course](#plan-paid-online-course) (prompt)
- [Plan a staff training day session](#plan-staff-inset-session) (prompt)
- [Plan a term of an after-school club](#plan-after-school-club) (prompt)
- [Plan a themed day camp week](#plan-day-camp-program) (prompt)
- [Plan a training evaluation](#evaluate-training-effectiveness) (prompt)
- [Review a course for Universal Design for Learning](#review-course-for-udl) (prompt)
- [Run a digital skills drop-in](#run-digital-skills-drop-in) (prompt)
- [Run a training needs analysis](#run-training-needs-analysis) (prompt)
- [School curriculum lead](#school-curriculum-lead) (persona)
- [Teacher CPD programme track](#teacher-cpd-programme-track) (workflow)
- [Write a course syllabus](#write-course-syllabus) (prompt)
- [Write a course welcome message](#write-course-welcome-message) (prompt)
- [Write a facilitator guide](#write-instructor-guide) (prompt)
- [Write a module descriptor](#write-module-descriptor) (prompt)
- [Write measurable learning objectives](#write-learning-objectives) (prompt)
---
## Adapt a course for low bandwidth
`adapt-course-for-low-bandwidth` · prompt · Course design · https://hermes-ide.com/prompts/adapt-course-for-low-bandwidth
Redesigns a course for learners with poor connectivity or only a phone, using text and audio over video, offline packs, messaging-app or SMS delivery, small files and asynchronous assessment.
````markdown
For many learners in rural areas, refugee settings, or on prepaid data, a typical online course is unusable: a 20-minute HD video can cost a day's wages in data, live sessions drop, platforms do not load on older phones, and shared devices mean a learner has the phone only in the evening. Redesigns fail when they just compress the video. They succeed when they start from what learners actually have (device, data cost, power, time of access, shared or own phone, literacy), choose the lightest format that does the job, deliver in small chunks through a channel learners already use, and make assessment and feedback work asynchronously.
Main channel: mixed.
[COURSE_OUTLINE]
1. **Learner access profile:** summarise devices, connectivity, data cost, power, time of access and literacy from the outline; list what to check with a short access survey (sent by SMS or asked by phone) if unknown.
2. **Format conversions:** for each material, the lightest format that keeps the learning: video to a short audio clip (voice notes under 3 minutes, low bitrate) plus key images or a text summary; slides to a one-page text or image; long PDFs to short chunks readable on a small screen; live sessions to recorded audio plus an asynchronous Q&A window, with an optional live call at a fixed low-cost time.
3. **Weekly delivery plan:** how each week reaches learners through mixed: message sequence (what is sent, when, size), group versus one-to-one messages, and reminders. For SMS: messages under 160 characters, numbered, with a reply code for answers.
4. **Offline pack:** what goes in a downloadable or printed pack (memory card, USB, printed booklet), how often it is refreshed, and how learners collect it.
5. **Assessment and feedback:** asynchronous tasks that work on a basic phone (photo of written work, voice note answer, short text reply, multiple-choice by reply code), how teachers give feedback (voice notes, batch replies), and fair deadlines.
6. **Data budget:** an estimated data size per week, using rough file sizes stated as assumptions, against a target (for example under 50 MB per week), and what to cut if over.
7. **Support and testing:** a test on the lowest common device and network before launch, a help line or contact window, peer study pairs, and how to reach learners who go quiet.
- Every course outcome must still be reachable; if something cannot be done without bandwidth (for example a live lab), propose an alternative or flag it.
- Protect privacy on shared phones and messaging groups: do not expose learners' numbers to the whole group where avoidable, get consent for groups, and avoid sending sensitive content.
- Do not invent data prices or network coverage; give file sizes as approximate ranges and say what to check locally.
- Name channels generically (a messaging app, SMS) unless the outline already names a specific one.
- If the outline gives no modules or materials, ask for them and stop.
## Learner access profile
Bullets, plus survey questions if needed.
## Format conversions
Table: Current material | New format | Approx size | Notes.
## Weekly delivery plan
Table: Day | What is sent | Format | Size. Then a sample message sequence.
## Offline pack
Bullets.
## Assessment and feedback
Bullets.
## Data budget
Table: Week | Estimated MB | Within target?
## Support and testing
Checklist.
````
---
## Analyse course evaluations
`analyze-course-evaluations` · prompt · Course design · https://hermes-ide.com/prompts/analyze-course-evaluations
Analyses end-of-course student evaluation comments and scores into themes by frequency and severity, separating fixable design issues from one-offs, and names three priority changes.
````markdown
Teachers read evaluations badly in two predictable ways: the one cruel comment dominates, or the average score is taken as the story. A useful read counts how often each issue appears, judges how much it hurts learning, separates what the course design can fix (unclear assessment briefs, pacing, feedback timing) from what it cannot or should not (room temperature, "less work please"), keeps the things students value, and ends in a small number of changes students will be told about.
[EVALUATION_COMMENTS]
1. Count the comments and, if scores are given, the response rate. Under about 30% response or under 10 responses, warn that results may not represent the cohort.
2. Code every comment into themes (for example assessment clarity, feedback, workload and pacing, organisation, teaching sessions, materials, online platform, support, relevance, inclusion). A comment can carry more than one theme. Record positive and negative mentions separately.
3. Rate each negative theme for severity: high (blocks learning, affects fairness or wellbeing, or signals a policy issue), medium (makes learning harder), low (preference or comfort).
4. Classify each issue: fixable in course design, fixable by the teacher's practice, outside the course (timetabling, rooms, systems) to pass on, or not a change to make (with a short reason, for example the workload is required by the outcomes; then the fix is explaining why).
5. Check scores against themes: where a low item matches a theme, say so; where scores and comments disagree, say that too.
6. Flag any comment suggesting harassment, discrimination, safety or wellbeing concerns, or personal attacks, for handling through the proper channel, separately from the course analysis.
7. Choose three priority changes by frequency x severity x effort, each with a concrete action and how to know next year if it worked.
- Quote at most a few words per comment as evidence, and never quote anything that could identify a student.
- Report counts ("9 of 41 comments") rather than vague words like "many".
- Do not treat a single comment as a theme; list it under one-offs unless it is high severity.
- Abusive or personal remarks about staff are noted as such and excluded from themes, without repeating them.
- Do not invent comments, scores or comparisons with previous years.
- If no comments are supplied, ask for them and stop.
## Snapshot
Responses, response rate, overall tone in two sentences, data limits.
## Themes
Table: Theme | Negative mentions | Positive mentions | Severity | Example words.
## Fixable design issues
Table: Issue | Evidence | Type of fix | Effort (low, medium, high).
## Keep doing
Bullets: praised elements with counts.
## One-offs and outliers
Bullets, plus any concerns to route elsewhere.
## Priority changes
Numbered, three: change, action, success measure.
## Response to students
A short "You said, we did" paragraph for next cohort.
````
---
## Build a course reading list
`build-course-reading-list` · prompt · Course design · https://hermes-ide.com/prompts/build-course-reading-list
Builds a balanced course reading list with core and optional readings per week, range of perspectives, accessibility notes and a realistic reading load, flagging every item to verify.
````markdown
A reading list shapes what students think a field is. Good lists have a small number of well-chosen core readings per week that students actually read, optional readings for depth, a mix of foundational and recent work, a range of perspectives, regions and authors, and a weekly load matched to the level. Unrealistic lists (200 pages a week for first-years) teach students to skim or skip. The single biggest risk when an assistant drafts a list is invented or garbled references, so every item must be checked against a library catalogue or database before it reaches students.
Build a reading list for **[COURSE]**, [WEEKS] weeks, for **[LEVEL]**.
1. If weekly topics were not given, propose a topic per week and mark them "proposed". If the field is one you cannot recommend readings for with confidence, say so and give search strategies and reading types instead of titles.
2. For each week choose 1 to 3 core readings and 2 to 4 optional readings. For each reading give author(s), title, year, type (book chapter, journal article, report, primary source, media), approximate length in pages, why it is on the list in one line, and your confidence that the reference is accurate (high, medium, low).
3. Include only works you are confident exist. Prefer well-known works whose details you can state accurately. Never invent DOIs, page ranges, editions or URLs; leave them out if unsure. Mark lower-confidence items clearly.
4. Balance the list: foundational and recent work, theory and empirical or applied work, and authors from different regions, traditions and backgrounds where the field allows. Include at least one item per week that is accessible to a struggling reader (a shorter, clearer text or a non-text source like a lecture or documentary).
5. **Reading load:** estimate core pages and hours per week at a realistic speed for the level (for academic text, first-years read roughly 10 to 15 pages an hour for close reading). Flag weeks above the target and swap or trim. If no target is given, aim for about 3 to 5 hours of core reading a week for undergraduates.
6. **Perspectives audit:** summarise who is represented (era, region, approach, author diversity as far as is publicly known and relevant) and what gaps remain, without guessing individuals' identities.
7. **Accessibility notes:** open-access or library-available options, items that need a digitised chapter, alternative formats, and reading guidance (questions to read with) for the hardest texts.
- Accuracy over coverage: a shorter list of real readings is better than a long list with errors. Say "I don't know a reliable reading for this week" if that is the case and suggest how to find one.
- Do not claim a reading is open access, in print or in a specific library unless you are sure; tell the instructor to check.
- Do not infer authors' race, gender or other identities; audit perspectives through stated approach, region and publicly self-described identity only.
- Respect existing required readings even if you would choose differently; you may note concerns.
## Approach
3 to 5 sentences on the shape of the list and the assumptions made.
## Reading list by week
A `###` per week with its topic, then a table: Core / optional | Reference | Type | Pages | Why | Confidence.
## Reading load
Table: Week | Core pages | Estimated hours | Flag.
## Perspectives audit
Bullets: represented, gaps, suggestions.
## Accessibility notes
Bullets.
## Verify before publishing
A checklist of every medium or low confidence item plus a reminder to check all references against the library catalogue.
````
---
## Build a scope and sequence
`build-scope-and-sequence` · prompt · Course design · https://hermes-ide.com/prompts/build-scope-and-sequence
Builds a multi-year scope and sequence for a school subject, with big ideas, unit order across years, prerequisite links, planned revisits and where key knowledge is assessed.
````markdown
A scope and sequence is the backbone a department teaches from for years. Weak ones are lists of topics in the order the textbook happened to use, with each unit taught once and forgotten, prerequisites taught after the units that need them, and assessment that checks the unit just finished rather than whether knowledge stuck. Strong ones are built around a small number of big ideas and threads (for history: chronology, causation, evidence; for science: particles, energy, cells), order units so earlier ones make later ones easier, plan where each key concept returns in a more complex form, and assess cumulatively.
Subject: [SUBJECT]. Years: [YEAR_RANGE].
1. **Big ideas:** four to seven big ideas or threads for [SUBJECT] that the sequence builds over [YEAR_RANGE], each with what a pupil understands at the start and at the end.
2. **Sequence overview:** units per year and term, with approximate weeks, fitting the stated teaching time (state your assumption if not given).
3. **Unit details:** for each unit, the core knowledge (three to five items that must be remembered: facts, concepts, procedures), the disciplinary skills, the big ideas it develops, and key vocabulary. Keep it to one table row per unit. If the range spans more than three years or about 20 units, give full rows for the first year and for exam-critical units, list the rest by title, and offer to detail them next.
4. **Prerequisite chains:** which units depend on which; check that nothing is taught before what it needs, and show the chains for the two or three most important concepts.
5. **Revisits:** where each big idea and key concept is deliberately revisited in a later year in a more complex context, not just repeated.
6. **Assessment points:** where key knowledge is assessed, including cumulative checks that test earlier units, and what a pupil should be able to show at the end of each year.
7. **Coverage check:** if a required curriculum is given, map each statement to a unit and flag anything missing or squeezed. If not, say what the sequence assumes.
8. **Decisions for the department:** trade-offs you made (depth versus breadth, what you dropped, choice of contexts, diversity of examples and voices) for the team to confirm.
- Order by what makes later learning easier, not by textbook order or tradition; explain non-obvious choices.
- Be realistic about time: if the required content cannot fit, say what has to be cut or reduced instead of squeezing.
- Use only the curriculum statements given; never invent statutory requirements or exam content. If the user names a framework or exam board without pasting its content, plan from the subject's widely taught content, say so, and mark every coverage claim [check against the specification].
- Represent a range of perspectives, people and places in contexts where the subject allows.
- If [SUBJECT] or [YEAR_RANGE] is missing, ask and stop.
## Big ideas
Table: Big idea | Start of range | End of range.
## Sequence overview
Table: Year | Term | Unit | Weeks.
## Unit details
Table: Unit | Core knowledge | Disciplinary skills | Big ideas | Key vocabulary. Short phrases, one row per unit.
## Prerequisite chains
Text chains such as Unit A -> Unit C -> Unit F, with a sentence each.
## Revisits
Table: Concept | First taught | Revisited in | How it deepens.
## Assessment points
Table: When | What is assessed | Cumulative content.
## Coverage check
Table: Requirement | Unit | Status.
## Decisions for the department
Bullets.
````
---
## Build a self-study curriculum
`build-self-study-curriculum` · prompt · Course design · https://hermes-ide.com/prompts/build-self-study-curriculum
Builds a self-directed curriculum for learning a new field, with milestones, resource types, projects and checkpoints sized to the hours available. Use when teaching yourself a field.
````markdown
Self-taught learners usually stall for the same reasons: they consume tutorials without producing anything, they jump to advanced topics before the foundations hold, they never test themselves, and they have no way of knowing whether they are making progress. A good self-study curriculum is a sequence of milestones defined by what the learner can do, each ending in a small project and a checkpoint, paced to the time they actually have.
Build a self-study curriculum for **[FIELD]**, with 5 hours per week.
1. Define the destination: what the learner will be able to do at the end, in two or three concrete sentences. If no goal was given, assume a solid working foundation for personal or entry-level professional use, and say so.
2. Map the field: the 5 to 8 core areas, which ones are foundations, and their prerequisite order. Name what is deliberately left out for later.
3. Plan 4 to 8 milestones. For each:
- What the learner can do at the end (an observable capability).
- Key concepts and skills.
- Resource types to use (an introductory textbook chapter, a structured course, documentation, worked-example collections, practice problem sets, communities for feedback), with what to look for in a good one.
- A small project that produces something real and uses the milestone's skills.
- A checkpoint: a self-test the learner can run without help ("explain X without notes", "solve these 3 problem types", "build Y from scratch in under 2 hours"), with a pass criterion.
- Estimated hours and the resulting number of weeks at 5 hours per week.
4. Design the weekly rhythm: how to split the hours between learning, practice, project work and review, with spaced review of earlier milestones.
5. List the common pitfalls in this field and how to avoid them.
- Do not invent resource titles, authors or URLs. Name a specific resource only when it is long-established and widely known in the field, and tell the learner to check for the current edition. Otherwise describe the resource type.
- Be honest about time: if reaching the destination needs more than about a year at 5 hours per week, say so and suggest a nearer first destination.
- If the field is ambiguous ("design", "AI"), pick the most likely meaning given the starting point, say which one in the first line, and name the alternatives.
- If the field involves physical risk or professional licensing (electrical work, medicine, aviation), say what can be self-taught safely and what requires formal training or supervision.
## Destination
2 to 3 sentences, plus total estimated hours and weeks.
## Map of the field
An indented list in prerequisite order, with "later" items marked.
## Milestones
For each milestone a heading "Milestone n: capability (weeks a to b)", then bullets for concepts, resources, project, checkpoint and hours.
## Weekly rhythm
A small table: Activity | Hours per week | Notes.
## Pitfalls
3 to 5 bullets.
````
---
## Convert an in-person course to online
`convert-course-to-online` · prompt · Course design · https://hermes-ide.com/prompts/convert-course-to-online
Redesigns an in-person course for online or hybrid delivery, deciding what becomes live or self-paced and how activities, assessment and community change. Use before moving a course online.
````markdown
Moving a course online by streaming the same lectures on a video call ("emergency remote teaching") produces exhausted students and low engagement. A real conversion asks of each activity what it is for, then picks the mode that does that job best online: self-paced (asynchronous) for explanation, reading and reflection people can do at their own pace; live (synchronous) time for discussion, practice with feedback and connection. Online courses need more explicit structure than in-person ones: a predictable weekly rhythm, clear instructions, visible instructor presence and deliberate community building. Assessment usually needs redesign because invigilated exams do not transfer cleanly.
Redesign this course for **fully-online** delivery.
[COURSE_OUTLINE]
1. If the outline gives no activities or no assessments (for example only a course title), ask for the topics, weekly session types and lengths, assessments and class size in one short list and stop. If only class size or session lengths are missing, assume typical values, state them under Assumptions and continue.
2. **Conversion principles:** 4 to 6 rules you applied, specific to this course.
3. **Activity conversion:** for every current activity, the new mode (live, self-paced, or dropped/merged), the online format (for example a 3 x 8-minute video set with a check question after each; a breakout case discussion; a collaborative document; a virtual or take-home lab) and why.
4. **Weekly rhythm:** a repeating week template with what opens when, live session times and length (no more than about 90 minutes live without a break), and deadlines that do not all fall on the same day. For hybrid, say how in-room and online students take part equally (roles, a room microphone, a co-host who watches the chat).
5. **Assessment changes:** for each assessment, keep, adapt or replace, focusing on what it must evidence. Prefer authentic and open-book tasks, staged submissions and short oral checks over remote proctoring; note the integrity and equity trade-offs.
6. **Community and presence:** week-1 onboarding activities, discussion structures that need real responses (not "post once, reply twice"), small stable groups, and how the instructor shows up each week (announcements, short videos, feedback).
7. **Accessibility and technology:** captions and transcripts, accessible documents, low-bandwidth options, time-zone fairness for live sessions (recordings plus an alternative participation task), and a minimum tech requirements statement.
8. **Instructor workload:** a realistic estimate of build time and weekly running time, and where to save effort (reuse, a teaching assistant, peer feedback).
9. **Pilot checklist:** what to test before launch.
- Do not simply move every lecture into a live video session; justify each live minute.
- Keep student workload equivalent to the in-person course; list the weekly hours.
- If a platform is named, describe features in general terms and say to check what the institution's version supports; do not invent menu paths.
- Labs, placements or practical skills that cannot be done remotely must be flagged with options (on-campus intensive, kits, simulations) rather than quietly dropped.
## Conversion principles
Numbered.
## Activity conversion
Table: Current activity | Purpose | New mode | Online format | Reason.
## Weekly rhythm
A day-by-day template table, then hybrid notes if relevant.
## Assessment changes
Table: Assessment | Keep / adapt / replace | New design | Integrity and equity notes.
## Community and presence
Bullets.
## Accessibility and technology
Bullets.
## Instructor workload
Build hours and weekly hours with savings.
## Pilot checklist
Checkbox list.
## Assumptions
Bullets: every value you assumed and what the instructor should confirm.
````
---
## Corporate trainer
`corporate-trainer` · persona · Course design · https://hermes-ide.com/prompts/corporate-trainer
Acts as a corporate trainer who builds adult learning around real job tasks, keeps sessions practical and interactive, and measures what changes at work. Use for workplace training conversations.
````markdown
From now on, work as this persona: Corporate trainer.
You are a corporate trainer with years of experience designing and delivering workplace learning: onboarding cohorts, management development, sales and customer-service skills, software roll-outs, compliance that people actually remember, and train-the-trainer programmes. You have run sessions in boardrooms, warehouses, call centres and on video calls, for audiences who did not choose to be there. You know a session has worked when people do something differently on Monday, not when the feedback forms say they enjoyed lunch.
How you work:
- You start from the job. Before designing anything you ask what people need to do, in which situations, what goes wrong today, and how the business will notice the difference. If the real problem is a broken process, unclear expectations, missing tools or a manager issue, you say so; training cannot fix those.
- You treat participants as adults with experience. You find out what they already know, build on it, and make the relevance obvious in the first ten minutes: their tasks, their customers, their systems, their numbers.
- You design for practice. Most session time goes to doing the task with feedback: role-plays with real scenarios, case work, simulations, hands-on system exercises, peer coaching. Input comes in short bursts, ideally no more than 10 to 15 minutes before people do something.
- You plan for transfer. You involve managers before and after, give job aids people will actually use, set an on-the-job assignment, and follow up at 30 and 90 days. You know most of the value is lost if nothing happens after the session.
- You facilitate with care. You read the room, handle the sceptic and the dominator without embarrassing them, make it safe to try and get it wrong, and adjust pace on the fly. On video calls you use shorter blocks, cameras-optional activities, polls, chat and breakouts with clear instructions.
- You measure honestly. You separate reaction, learning, behaviour and results, choose a small number of measures the business already tracks, and you are candid about what a training programme can and cannot claim credit for.
- You keep it lean. You would rather run a tight 90-minute session with real practice than a full day of slides, and you offer a lean option and a fuller one when budget or time is tight.
What you flag:
- "Can you make a training on X?" requests with no clear performance problem or success measure.
- Slide decks with more than a few lines per slide, agendas with no practice, and sessions that end with "any questions?" as the only check.
- Role-plays with unrealistic scripts, and activities that feel childish to adult professionals.
- Compliance or safety content that relies on memorising rules instead of practising decisions, and content that could expose the organisation if inaccurate; you mark it for an expert to verify.
- Evaluation limited to happy sheets, and claims of return on investment that the data cannot support.
- Exclusion: inaccessible materials, activities that disadvantage remote or disabled participants, examples that stereotype.
Your boundaries:
- You do not invent company policies, legal requirements, product details or statistics; you leave clear placeholders for subject-matter experts to fill.
- You do not promise behaviour change or business results; you design for them and say how to check.
- You respect that the sponsor owns the decision, and you are honest when you think the request will not work.
Your habits:
- You ask one or two sharp questions at a time, then produce something usable: an agenda, an activity, a facilitator note, a scenario, an evaluation plan.
- You give timings, materials and instructions precise enough that someone else could run the session.
- You end with the next concrete step and who should take it.
````
---
## Course accessibility retrofit track
`course-accessibility-retrofit-track` · workflow · Course design · https://hermes-ide.com/prompts/course-accessibility-retrofit-track
Retrofits an existing course for accessibility in gated stages, from an audit of materials to prioritised fixes, reworked documents, media and assessments, and a check with learners.
````markdown
Retrofits an existing course so disabled learners, and everyone else, can use it without having to ask for adjustments first. It works the way an experienced learning technologist would: audit what exists, fix the barriers that block the most learners first, rework documents and media, then activities and assessment, and finally check with real learners. Each step writes one artifact and stops for approval.
[COURSE_MATERIALS]
Rules for every step:
- Work from the materials given. Where you cannot see a file, say what to check and how (for example run the authoring tool's accessibility checker, test with keyboard only, check with a screen reader) rather than guessing the result.
- Use the Web Content Accessibility Guidelines (WCAG) 2.2 level AA as the default reference unless the institution names another standard; cite success criteria by number only when sure, otherwise describe the requirement.
- Keep learning outcomes and academic standards the same; change the access, not the bar.
- Never ask for or record individual learners' diagnoses; talk about barriers and needs.
- Do not state legal duties as fact; say to check the institution's policy and local law with the disability or accessibility service.
- Mark anything missing as [X] and end each artifact with open questions.
---
# Step 1: Audit the course
1. Ask in one message for anything essential that is missing: platform, file formats, whether videos have captions, how assessments run, and the standard to meet.
2. List every material type and check it against the main barrier groups: documents (real headings, reading order, tables with header rows, link text, colour contrast, scanned images of text, PDF tagging), slides (titles, layout order, text size, alt text), images and diagrams (meaningful alt text or long descriptions, colour-only meaning), video and audio (captions, transcripts, audio description of essential visuals), platform pages (keyboard use, consistent navigation, timed elements), live sessions (captions, recordings, chat alternatives), activities and assessments (time limits, formats, tools that need a mouse or fine motor control).
3. Note barriers for different learners: blind and low vision, d/Deaf and hard of hearing, physical and motor, cognitive and learning differences such as dyslexia, mental health, and learners using phones or assistive tech.
4. Mark each finding as seen in the samples or to be checked, with the quick test to run.
Output: Audit summary, Findings table (Material | Barrier | Who it affects | Seen or to check | Test), Open questions.
Stop and wait for approval.
---
# Step 2: Prioritise the fixes
1. Score each approved finding: impact (blocks access, makes it hard, minor), reach (how many learners and materials), and effort (quick, medium, large).
2. Group into: fix now (blocks access, high reach, often quick: captions on core videos, untagged scanned readings, colour-only charts, inaccessible quiz settings); fix this term; fix at next redesign.
3. For each group, name the owner role, the skill or tool needed and a rough time estimate as a range.
4. Set standards for new materials so the problem does not return: a short authoring checklist and templates.
5. Plan interim adjustments for any learner who needs access before fixes land.
Output: Priority table (Finding | Impact | Reach | Effort | Group | Owner), Authoring checklist, Interim adjustments, Open questions.
Stop and wait for approval.
---
# Step 3: Rework documents and media
1. For each fix-now document: the specific changes (heading structure, reading order, table headers, descriptive links, plain-language summary at the top for long readings, accessible format alongside PDFs).
2. Write alt text for the images and diagrams provided: short alt text for simple images, a long description for complex diagrams and charts, and empty alt for decorative ones. Flag any whose meaning you cannot tell.
3. For video and audio: caption and transcript plan (correct auto-captions rather than trusting them), audio description or text alternatives where visuals carry meaning, and chaptering long recordings.
4. For slides and platform pages: layout and contrast fixes, text size, and consistent navigation.
5. A quality check per item: the test that confirms the fix worked.
Output: Document fixes, Alt text and descriptions, Media plan, Slide and platform fixes, Check list, Open questions.
Stop and wait for approval.
---
# Step 4: Rework activities and assessment
1. Review each activity and assessment for barriers in format, timing, tools and environment, keeping the outcome it assesses fixed.
2. Build flexibility in by default where it does not change what is assessed: choice of submission format (written, audio, video), extended time windows instead of short timed tests where speed is not the skill, keyboard-accessible quiz tools, and clear, plain-language briefs with exemplars.
3. For live and group work: captions, recordings, roles that do not depend on one ability, and alternatives to speaking live.
4. Note where an individual adjustment will still be needed and how learners request it without repeating disclosures.
5. Check each change against the outcome: say if a change would alter the standard and propose an alternative that does not.
Output: Activity and assessment changes (Item | Barrier | Change | Outcome still assessed?), Individual adjustment route, Open questions.
Stop and wait for approval.
---
# Step 5: Check with learners
1. Plan a check with learners who use assistive technology or have access needs, recruited through the accessibility service or an open invitation, paid or thanked for their time and never identified in reports.
2. Write tasks for them to try (find this week's reading, watch a video and answer a question, submit an assignment, join a discussion) and short questions afterwards.
3. Add an automated and manual check pass on the reworked materials, and a feedback route for all learners to report barriers at any time.
4. Summarise what to fix next and how to keep the course accessible: review dates, the authoring checklist, and who owns it.
Output: Learner check plan, Tasks and questions, Ongoing feedback route, Next fixes and maintenance, Open questions.
````
---
## Course design track
`course-design-track` · workflow · Course design · https://hermes-ide.com/prompts/course-design-track
Takes a course from audience and outcomes to an outline, assessments, lesson materials and a review pass, pausing for approval between steps. Use when building a whole course.
````markdown
Designs the course "[COURSE_NAME]" by backward design, one approved step at a time: who it is for and what they will be able to do, then the module outline, then the assessments that prove the outcomes, then the materials for each session, then an alignment and quality review. Each step produces one document and stops for the designer's approval or edits; later steps build on the approved versions instead of re-asking. The designer stays in charge of every decision about scope, content and standards; the assistant drafts, checks alignment and flags gaps.
## Steps
Work through these steps in order. Do not skip a gate.
1. audience-outcomes (discover)
2. outline (design)
3. assessments (design)
4. materials (build)
5. review (review)
### Step 1: Audience and outcomes
Establish who "[COURSE_NAME]" is for and what they will be able to do at the end.
1. Ask the designer, in one message, for anything not already given: the learners (background, prior knowledge, motivation), the setting (school, university, workplace, online), the length and session pattern, any required standards or syllabus, constraints (class size, technology, budget), and how the course will be judged a success.
2. When you have the answers, write:
- **Learner profile:** 4 to 6 bullets, including likely misconceptions and barriers.
- **Course outcomes:** 4 to 6 outcomes, each one sentence with one observable verb (no "understand" or "know"), at levels that fit the audience and the time, most at apply or above.
- **Out of scope:** what the course deliberately does not cover.
- **Assumptions:** anything you assumed rather than were told.
3. Flag any outcome that is unrealistic for the time available.
Stop and wait for approval or edits. Do not start the outline.
**Gate:** stop here and wait for the user's approval before step 2 (outline).
### Step 2: Outline
Using the approved outcomes for "[COURSE_NAME]", build the module outline.
1. List the concepts and skills each outcome depends on, and order them by prerequisite.
2. Group them into modules or weeks that fit the approved length and session pattern. Front-load foundations, revisit key ideas later in new contexts, and leave a consolidation point about two-thirds through plus time for the final assessment.
3. Produce a table: Module | Title | Outcomes served | Key concepts | Session time | Independent time.
4. Check that every outcome is served by at least one module and that every module serves at least one outcome. Remove or merge modules that serve none.
5. State the weekly learner workload and flag any week that is heavier than the rest.
Stop and wait for approval or edits. Do not design assessments yet.
**Gate:** stop here and wait for the user's approval before step 3 (assessments).
### Step 3: Assessments
Design the evidence that learners in "[COURSE_NAME]" have met the approved outcomes.
1. **Summative:** one or two assessments in which learners perform the outcomes, preferably an authentic task (a project, case analysis, portfolio, performance or practical). For each: the brief as learners will read it, the outcomes it assesses, its weight, and when it is due in the outline.
2. **Rubric:** an analytic rubric for each summative task, with 3 to 6 non-overlapping criteria and 4 levels whose descriptors name observable features of the work, not adjectives.
3. **Formative:** one low-stakes check per module (a quiz, an exit ticket, a draft with peer feedback, a short practical), with what the teacher does with the results.
4. **Alignment matrix:** outcomes as rows, assessments as columns. Every outcome is assessed summatively at least once; flag any that are not.
Stop and wait for approval or edits. Do not write session materials yet.
**Gate:** stop here and wait for the user's approval before step 4 (materials).
### Step 4: Materials
Write the materials for "[COURSE_NAME]" one module at a time. Ask which module to start with if the designer has not said; default to module 1.
For each module:
1. **Session plan:** objectives for the session, a timed sequence (opener, explicit teaching with a worked example, guided practice, independent or group practice, check for understanding, close) with timings that add up to the session length.
2. **Content notes:** the explanations, examples and key questions the teacher needs, written out, not summarised.
3. **Learner materials:** worksheets, readings described by type and level, task cards or slides outlines, as text the designer can paste.
4. **The formative check** from Step 3, written in full with answers.
5. **Differentiation:** support and stretch options for this module.
Do not invent specific book titles, authors or URLs; describe the resource needed instead.
After each module, stop and wait for approval before writing the next. When the designer says the materials are done, move on to the review.
**Gate:** stop here and wait for the user's approval before step 5 (review).
### Step 5: Review
Review the whole of "[COURSE_NAME]" as an independent course reviewer would, using the approved outcomes, outline, assessments and materials.
Check and report:
1. **Alignment:** every outcome is taught, practised and assessed; every activity and assessment serves an outcome. List any break in the chain.
2. **Load and pacing:** weekly workload is realistic and even; no module crams new ideas without practice.
3. **Assessment quality:** briefs are clear, rubrics are observable and non-overlapping, and summative tasks actually require the outcome's verb.
4. **Accessibility and inclusion:** materials are readable, alternatives exist for any inaccessible format, examples are varied and free of stereotypes.
5. **Accuracy:** statements that should be checked by a subject expert, listed rather than asserted.
Output a table: Area | Finding | Severity (must fix / should fix / consider) | Suggested fix. Rank must-fix items first, then end with the three changes that would most improve the course. Make no edits yourself; the designer decides what to change.
````
---
## Design a blended learning programme
`design-blended-program` · prompt · Course design · https://hermes-ide.com/prompts/design-blended-program
Designs a blended programme mixing live sessions, self-paced work and on-the-job practice, with sequencing, weekly time load and support. Use for multi-week training that must change practice at work.
````markdown
Blended learning is not "some e-learning plus a workshop". Each modality has a job: self-paced work is best for knowledge people can absorb at their own speed and revisit; live sessions are for practice with feedback, discussion of hard cases and accountability; on-the-job assignments are where transfer happens. A good blend runs a repeating weekly rhythm (prepare, practise together, apply at work, reflect), keeps the weekly time load honest, and involves the participant's manager, because what happens after training predicts whether behaviour changes more than the training itself does.
Design a 6-week blended programme.
[OUTCOMES]
Audience: **[AUDIENCE]**
1. If the outcomes are topics rather than behaviours ("communication", "Excel"), rewrite them as 3 to 6 observable outcomes and mark them "rewritten, please confirm". If the time participants can give is unknown, assume about 3 hours a week and say so.
2. **Modality map:** for each outcome decide what goes self-paced, what goes live and what is practised on the job, with a one-line reason tied to what each modality does best.
3. **Weekly rhythm:** define the repeating cycle (for example: self-paced prep early in the week, a live practice session mid-week, an on-the-job assignment, a short reflection or peer check-in at the end).
4. **Week-by-week plan:** for each week the focus, the self-paced items (with minutes), the live session (length, format, main activity), the on-the-job assignment and the reflection prompt. Sequence from foundations to integrated, realistic application, with the last week focused on a capstone application and a plan for continuing.
5. **On-the-job practice:** for each assignment, what the participant does at work, what they bring back, and what the manager does (brief, observe, give feedback).
6. **Support:** facilitator presence, peer groups or learning pairs, how stragglers are noticed and helped (missed live session plan, nudges), and accessibility for self-paced items (captions, transcripts, mobile-friendly).
7. **Time load:** a table of weekly hours per participant, per manager and per facilitator. Flag any week above the stated budget and adjust.
8. **Evaluation:** how you will know behaviour changed at work (observations, work samples, manager ratings, a business measure), not only completion and satisfaction.
- Every self-paced item has a purpose and a check (a quick retrieval quiz, a submitted reflection, a question to bring to the live session); no "watch this video" with no follow-up.
- Live sessions spend at least half their time on practice or discussion, not presentation.
- Do not exceed the participants' time budget; if the outcomes cannot fit, say what to cut or how many weeks would be needed.
- Do not name specific vendor platforms unless the user did; describe functions (a discussion forum, a video tool).
## Design summary
3 to 5 sentences: the blend, the rhythm and why.
## Modality map
Table: Outcome | Self-paced | Live | On the job | Reason.
## Week-by-week plan
Table: Week | Focus | Self-paced (min) | Live session | On-the-job assignment | Reflection.
## On-the-job practice
Per assignment: task, bring back, manager role.
## Support
Bullets.
## Time load
Table: Week | Participant hours | Manager hours | Facilitator hours.
## Evaluation
Bullets with measures and timing.
## Assumptions
Bullets.
````
---
## Design a branching training scenario
`design-branching-scenario` · prompt · Course design · https://hermes-ide.com/prompts/design-branching-scenario
Designs a branching decision scenario with a realistic situation, choices, consequences, feedback and a debrief. Use to train judgement in e-learning or a live facilitated session.
````markdown
A branching scenario trains judgement by letting people make the decisions they face at work and see what happens. It works when the situation is specific and believable, every option is something a real person might choose, and consequences unfold in the story before any instructional feedback appears. Weak scenarios have one obviously correct option, "wrong" choices nobody would make, and an instant "Incorrect!" that teaches nothing. Full branching explodes in size, so practical designs fold paths back together and let a poor choice make later decisions harder rather than spawning a whole new tree.
Design a branching scenario with 4 decision points on the main path.
[SKILL]
Audience: **[AUDIENCE]**
1. If the skill is too general to stage as one situation (for example "leadership" or "communication"), ask which specific situation to stage and stop. If real mistakes people make are not given, base distractors on common, plausible errors and mark them for a subject-matter expert to confirm.
2. **Scenario brief:** the learning goal as an observable behaviour, the setting, the learner's role, the other characters (with what they want), and what is at stake. Keep it to one situation the audience actually meets.
3. **Branch map:** a Mermaid flowchart of scenes, choices and endings, using a foldback structure: poor choices lead to a recovery scene with a harder state, then rejoin the main line, so the total stays manageable (about 2 to 3 times the number of decision points in scenes).
4. **Scenes:** for each decision point write:
- the situation in 60 to 120 words, with realistic dialogue;
- three options: the strongest choice, a plausible but flawed choice, and a common mistake. All three should be tempting to someone in the audience; none is silly or rude for no reason;
- for each option, the consequence shown in the story (what the other character says or does next), then a short feedback note that explains the principle in plain terms.
5. **Endings:** a strong, a mixed and a poor ending, each showing realistic outcomes, with a path back ("try again from scene 2").
6. **Debrief:** 5 or 6 questions that move from what happened to why it worked and how it applies at work, plus the 2 or 3 principles the scenario teaches.
7. **Build notes:** how to run it as e-learning (variables to track, such as trust or time, and where they change) and as a live session (the facilitator reads scenes, groups vote, discuss, then reveal).
- Keep the options similar in length and tone so the best one is not given away by being longest or kindest-sounding.
- Show consequences before feedback. Feedback explains; it never scolds.
- Do not invent organisation-specific policy, legal rules or safety procedures; use placeholders such as [refund limit] where they matter.
- Characters are diverse and realistic without stereotypes; no character is a caricature villain.
- Write for [AUDIENCE]: vocabulary, setting and stakes they recognise.
## Scenario brief
Short paragraphs and a character list.
## Branch map
A Mermaid `flowchart TD` code block with node ids that match the scene headings.
## Scenes
One `###` heading per scene: situation, then options A/B/C each with Consequence and Feedback.
## Endings
Strong, mixed, poor.
## Debrief
Numbered questions, then key principles.
## Build notes
E-learning bullets, then live-session bullets.
````
---
## Design a community ESOL course
`design-esol-course-for-adults` · prompt · Course design · https://hermes-ide.com/prompts/design-esol-course-for-adults
Designs a term-long community ESOL course for adult newcomers at one level, built on real-life topics, mixed literacy routes, rolling enrolment, patchy attendance and simple progress checks.
````markdown
Community ESOL learners are adults rebuilding a life in a new language: booking a GP appointment, talking to a child's teacher, reading a tenancy letter, getting and keeping work. A class at one level still mixes people with a university degree and people who never went to school, and fluent speakers who cannot read beside readers who cannot speak. Learners miss weeks for shifts, appointments, childcare and moves, and new people join mid-term.
Courses fail when they follow a grammar book instead of learners' lives, when literacy is treated as a speaking problem, when every lesson assumes last week's, and when progress is only shown by an exam at the end. Level: entry-1. Term: 12 weeks.
[LEARNER_PROFILE]
1. **Needs snapshot:** from the profile, name the two or three literacy routes the class needs (for example: emergent readers new to print, readers new to the Latin script, confident readers who need speaking) and the real situations learners face most. List what you would ask learners in week one to confirm this (a picture-based needs survey, not a form).
2. **Topic units:** group the 12 weeks into 3-4 week units on real-life topics chosen from the profile (health and the GP, children's school, work and job search, housing and bills, transport, shopping, local services, emergencies). Each unit ends in a real-world task (a role-played GP call, filling in a school absence note, a short job interview).
3. **Can-do outcomes:** three to five can-do statements per unit pitched at entry-1, covering speaking and listening, reading and writing. Separate the literacy route outcomes when they differ.
4. **Lesson shape:** a repeatable weekly structure with a short recap that lets newcomers start, input with real or realistic materials (letters, forms, signs, recorded dialogues), controlled then freer practice, a literacy block split by route, and a close where learners say one thing they can now do.
5. **Rolling enrolment and attendance:** make every week self-contained within the unit theme; a welcome routine and buddy for new joiners; a one-page take-home summary per week with pictures; how to place a mid-term joiner (a quick oral and reading check).
6. **Progress checks:** light checks that respect adults (can-do self-assessment with pictures, a teacher checklist from observed tasks, a writing sample at the start and end of each unit), recorded as RARPA-style individual targets where the provider uses them. Note where an accredited exam would replace or add to this, without naming specific exam rules unless the user gave them.
7. **Wellbeing and signposting:** a short list of the local services to map with learners (advice, health, housing, employment support), marked [check locally], and how to respond if a learner raises trauma, immigration or housing crises (listen, do not counsel, refer to the named contact).
- Pitch everything at entry-1; if the profile clearly shows learners at another level, say so and suggest splitting or differentiating.
- Never assume first-language literacy. Plan explicit literacy teaching for anyone who needs it (letter formation, sound-letter links, sight words for forms) rather than giving them the same worksheet.
- Use learners' languages as a resource (peer explanation, bilingual glossaries) rather than banning them.
- Topics must be adult and practical; no childish materials. Avoid tasks that make learners disclose immigration status, trauma or family circumstances in front of the group.
- Level names follow the UK adult ESOL framework. If the setting is outside the UK, use the CEFR equivalent and say to check the local framework.
- Do not invent funding rules, exam specifications or local services; mark them [check locally].
- If the profile is too thin to choose literacy routes or topics, ask for the missing items (literacy in any script, main life situations, hours per week) and stop.
## Needs snapshot
Literacy routes and priority situations, then the week-one needs check.
## Term plan
Table: Weeks | Unit topic | Real-world task | Can-do outcomes | Literacy route focus.
## Weekly lesson shape
Table: Minutes | Segment | What happens | Route differences.
## Rolling enrolment and attendance
Bullets.
## Progress checks
Bullets, with a sample can-do self-assessment line.
## Signposting and wellbeing
Bullets.
## Questions to confirm
Bullets.
````
---
## Design a course outline
`design-course-outline` · prompt · Course design · https://hermes-ide.com/prompts/design-course-outline
Designs a course with backward design, moving from outcomes to assessments to a sequenced, paced module plan with an alignment matrix. Use when building a new course or workshop series.
````markdown
Courses designed topic-first end up as a list of things to cover, with assessments bolted on at the end that test whatever was easiest to test. Backward design reverses the order: decide what learners must be able to do at the end, decide what evidence would show it, and only then plan the learning that leads there. Every module should exist because an outcome needs it, and every outcome should be assessed.
Design a course on **[SUBJECT]** for **[AUDIENCE]**, lasting **8 weeks**.
1. Outcomes: write 4 to 6 course-level outcomes. Each starts with an observable verb, describes what the learner can do after the course, and is achievable in 8 weeks for this audience. Include at least one outcome at the apply level or above and, where it fits, one about transfer to the learner's own context.
2. Evidence: plan the assessments.
- One or two summative assessments that require performing the outcomes, preferably an authentic task (a project, a case, a portfolio, a performance), not only a test.
- Formative checks in every module, low-stakes, with feedback.
- Weightings that reflect the importance of each outcome.
3. Learning plan: break the course into modules or weeks that fit 8 weeks.
- Order them by prerequisites: what must be understood before what. Front-load the foundations, and revisit key ideas later (spiral).
- For each module: a title, the outcomes it serves, key concepts, learning activities, the formative check, and the estimated learner hours (in session and independent).
- Leave slack: a catch-up or consolidation point about two-thirds through, and time to work on the summative task.
4. Alignment: build a matrix of outcomes × modules × assessments and fix any outcome that is not taught or not assessed.
- Keep the workload realistic for the audience. State the assumed weekly hours; if 8 weeks does not give the session pattern, assume one and say so.
- Do not recommend specific textbooks, courses or URLs unless you are confident they exist; describe the resource type instead ("an introductory open textbook chapter on…").
- If the subject is too broad for 8 weeks ("all of physics in 4 weeks"), narrow the scope, say what you cut, and why.
- Make no claims about accreditation or institutional requirements; flag them as things to check.
## Course summary
Three or four sentences: who, what, how long, assumed weekly hours, and the summative task.
## Outcomes
Numbered O1, O2…
## Assessment plan
A table: Assessment | Type (summative / formative) | Outcomes | Weight | When.
## Module plan
A table: Week or module | Title | Outcomes | Key concepts | Activities | Formative check | Hours.
## Alignment matrix
A table with outcomes as rows and modules and assessments as columns, marked with ✓.
## Assumptions and open questions
Bullets.
````
---
## Design a family learning course
`design-family-learning-course` · prompt · Course design · https://hermes-ide.com/prompts/design-family-learning-course
Designs a short family learning course where parents or carers and children learn together, with joint and separate parts each session, a weekly take-home activity and an informal celebration.
````markdown
Family learning courses help parents and carers support their children's learning and often restart the adult's own learning too. Many adults who come had a poor experience of school, may not be confident with the subject, and may speak another language at home. Courses lose them when the adult session feels like being back in a classroom, when parents are shown how they are "doing it wrong", when take-home tasks need materials or money, or when the joint time is the child performing for the adult. They work when adults have their own time to learn and ask questions, joint time is playful and shared, the take-home activity uses everyday things, and progress is celebrated.
Subject: [SUBJECT].
Children's age or school year: [CHILD_AGE].
Number of sessions: 6.
1. **Course aims:** for adults (what they will understand about how children learn [SUBJECT] now, what they will feel confident to do at home, any own-skill gain), and for children.
2. **Session structure:** a repeatable session with an adults-only part (with childcare or a parallel children's activity), a joint part where adult and child do a task together, and a short close where families choose this week's take-home activity. Default to 90-120 minutes unless the setting says otherwise.
3. **Session-by-session plan:** for each of the 6 sessions: theme, the adult session content (including how the school or setting teaches this, explained without jargon), the joint activity, and what children practise.
4. **Take-home activities:** one per week, using free or household items, short (10-15 minutes), adaptable for different languages and literacy levels, with a simple way to share how it went (a photo, a sticker card, a chat at the next session).
5. **Recruiting and keeping families:** personal invitations, timing around work and school runs, food, welcoming dads, grandparents and other carers, interpreters or bilingual helpers, and what to do when a family misses a week.
6. **Celebration and next steps:** an informal final celebration (children show what they made, certificates for adults), signposting adults to further learning, and a short feedback activity for adults and children.
- Strengths-based tone: never imply parents are failing; build on what families already do at home and in their own languages.
- Pitch children's activities at [CHILD_AGE] and adults' activities at an adult level.
- No take-home activity that needs a device, internet, printer or bought materials unless the setting confirms families have them; offer a non-digital option.
- Note safeguarding basics for the setting (adults stay responsible for their own child in joint time; staff ratios in any separate children's activity per local policy, marked [check]).
- Do not invent funding rules or qualification details.
- If [SUBJECT] or [CHILD_AGE] is missing, ask and stop.
## Course aims
Two short lists: Adults, Children.
## Session structure
Table: Minutes | Part | Adults | Children.
## Session-by-session plan
Table: Session | Theme | Adult session | Joint activity | Children practise.
## Take-home activities
Numbered, one per session.
## Recruiting and keeping families
Bullets.
## Celebration and next steps
Bullets.
````
---
## Design a farmer field school
`design-farmer-field-school` · prompt · Course design · https://hermes-ide.com/prompts/design-farmer-field-school
Designs a season-long farmer field school with participatory field observation, comparison plots, group analysis and locally chosen topics, scheduled around the crop or livestock calendar.
````markdown
A farmer field school is a group of 20-30 farmers who meet regularly through one whole season at a shared study plot, observe, experiment and decide together, with a facilitator rather than a lecturer. It works because farmers test practices in their own conditions and draw their own conclusions. It goes wrong when it turns into demonstrations of a package the facilitator already chose, when sessions do not line up with what is happening in the field that week, when meetings clash with peak labour or market days, or when women, younger farmers or non-literate members cannot take part fully.
System: [CROP_OR_LIVESTOCK]. Sessions: 12.
[LOCAL_CONTEXT]
1. **Learning priorities:** from the context, the three to five problems the group will investigate, phrased as farmers' questions (for example "Does mulching save enough water to pay for the labour?"). Plan a first-session problem ranking so the group confirms or changes them.
2. **Study plot design:** a comparison of the farmers' usual practice against one to three alternatives they choose, with plot or animal group sizes, layout, what stays the same, and what gets recorded (growth, pests and beneficial insects, disease, water, labour hours, costs, yield or milk). Keep it simple enough to run without a lab.
3. **Season calendar:** place the 12 sessions across the season so each matches a field stage (land preparation, planting, early growth, flowering, pest peaks, harvest, post-harvest or the livestock equivalents), avoiding peak labour and market days.
4. **Session routine:** the repeated half-day flow - field observation in small groups, agro-ecosystem analysis drawing (plant, pests, natural enemies, weather, soil, decisions), presentation and group decision, a special topic, and a group dynamic or energiser - with timings.
5. **Special topics:** one per session, matched to the calendar and the priorities (seed selection, soil and water, scouting, natural enemies, safe storage, record keeping, marketing).
6. **Group and facilitation:** group formation and norms, subgroups with rotating roles, inclusion (timing and childcare for women, pictorial recording for non-literate members, local language), and what the facilitator does and does not do.
7. **Evaluation and graduation:** a simple pre- and post-season ballot box test on field knowledge, records of plot results, farmers' own decisions about adoption, a field day for neighbours and a graduation event.
- Farmers choose what to test; the facilitator suggests options but does not impose a package.
- Do not give pesticide, veterinary medicine or fertiliser product names, doses or withdrawal periods. Where a topic involves them, say to use the national extension service or a qualified agronomist or vet and local label rules.
- Do not invent local yields, prices, rainfall or pest data; mark them to collect locally.
- Plans must work with low cost and local materials.
- If season dates or the main problems are missing, ask for them and stop.
## Learning priorities
Numbered farmer questions.
## Study plot design
Table: Treatment | What changes | Plot or group size | What to record.
## Season calendar
Table: Session | Approximate date or crop stage | Field focus | Special topic.
## Session routine
Table: Minutes | Activity | Who leads.
## Special topics
Bullets, one line each.
## Group and facilitation
Bullets.
## Evaluation and graduation
Bullets and three sample ballot box questions.
````
---
## Design a hands-on workshop
`design-workshop` · prompt · Course design · https://hermes-ide.com/prompts/design-workshop
Designs a half-day or full-day workshop with outcomes, a timed agenda, practice activities, materials and a facilitator guide. For trainers and team leads running hands-on sessions.
````markdown
Workshops fail as slide marathons with an exercise bolted on at the end. Adults learn a skill by doing it with feedback, so a good workshop spends most of its time on practice that mirrors the real task, keeps input short, and closes with participants committing to how they will use it. Attention drops after 10 to 20 minutes of listening and faster on video calls, which need shorter blocks and more frequent breaks.
Design a in-person workshop on [TOPIC] lasting [DURATION].
[AUDIENCE]
1. **Outcomes:** 2 to 4 things participants will be able to do by the end, each with an observable verb, realistic for [DURATION]. Fewer outcomes done well beats coverage.
2. **Agenda:** a timed agenda that adds up exactly to [DURATION]. Structure each block around connecting to what people already know, short concept input (10 to 15 minutes at most at a time), concrete practice, and a debrief or conclusion. At least half of the time is participants doing, not listening. Include breaks: in person, at least every 90 minutes; remote, a short break about every hour and no single block over 60 minutes.
3. **Activities:** for each practice activity: purpose (which outcome), setup, instructions as the facilitator will say them, grouping, timing, what good output looks like, and debrief questions. Use realistic cases from the audience's world. Vary the formats (pairs, small groups, solo, whole room).
4. **Materials:** everything to prepare: slides kept to a minimum, handouts, case materials, templates, and equipment. For remote: the collaborative tools needed by type (shared whiteboard, documents, polls), breakout room setup and links.
5. **Facilitator guide:** per block, key messages, timings with checkpoints, likely questions and pushback with responses (especially for a skeptical or mandatory audience), what to watch for in groups, and what to cut if running late (mark the cuttable segments in the agenda).
6. **Before and after:** optional pre-work (15 minutes or less), the opening that sets expectations, a closing where each participant writes a specific commitment, and follow-up (a reminder or resource within a week). Add a short evaluation: a reaction question and a check of whether they can now do the outcome.
7. **Accessibility:** materials readable and shareable in advance, captions for remote sessions, activities that do not depend on one sense or on standing, cameras optional, and quiet participants given a way to contribute in writing.
- The agenda's times must add up to the duration given. If the topic cannot be taught to the outcomes in the time, say what to cut or split into two sessions.
- Do not rely on any named commercial tool; describe the function and let the organiser pick.
- Fit the audience's level and context; if the audience description is vague (no size or prior knowledge), state the assumption.
- Keep the guide usable by someone other than the designer.
Use the section headings from the output contract. Agenda as a table: Time | Block | Activity | Format | Outcome | Cuttable?. Activities as subsections. Materials as a checklist.
````
---
## Design a higher-education capstone
`design-capstone-project` · prompt · Course design · https://hermes-ide.com/prompts/design-capstone-project
Designs a university capstone with milestones, partner involvement, supervision, rubrics and a fair way to assess individual contribution in teams. Use when planning or redesigning a capstone.
````markdown
A capstone is where a programme proves its graduates can integrate what they learned on an open, realistic problem. Capstones go wrong in predictable ways: projects scoped too large or too vague, partners who disappear or treat students as free labour, supervision that only notices problems in the final week, rubrics that grade the polish of the final presentation instead of the outcomes, and team grades that reward free-riders and punish the students who carried the project. Good designs fix scope early with a written agreement, use frequent milestones with formative feedback, and assess individual contribution with several sources of evidence.
Design a 12-week capstone for **[PROGRAM]**.
[OUTCOMES]
1. If it is unclear whether projects are team or individual, or whether external partners are involved, state the assumption you take (team projects of 4 to 5 with an external partner) and design for it, adding a short note on how the design changes for the alternative.
2. **Overview:** the purpose, the outcomes it evidences (each linked to an assessed deliverable), project types that suit the programme, and how projects are sourced and allocated (partner proposals, student proposals, preference-based matching).
3. **Milestones:** a timeline across 12 weeks with at least: scoping agreement, project plan, an early prototype or proposal review, a mid-point review, a final deliverable, and a presentation or defence. For each: what is submitted, who gives feedback and whether it is graded.
4. **Partner involvement:** a one-page partner brief (what a good project looks like, time asked of the partner, contact cadence, what students can and cannot deliver), a scoping agreement template (deliverables, data access, confidentiality, intellectual property position to confirm with the institution, communication), and what happens if a partner disengages.
5. **Supervision:** cadence and format of supervisor meetings, a meeting log template, early-warning signs (missed meetings, unequal commits or contributions, scope drift) and the escalation route.
6. **Assessment and rubrics:** the weighting across deliverables and process, and an analytic rubric for the main deliverable with 4 to 6 criteria tied to the outcomes and 4 performance levels with descriptors.
7. **Individual contribution:** a combination of at least three sources: structured peer assessment that adjusts the team mark within limits, individual reflective logs or contribution statements, artefact evidence (version history, authored sections, meeting logs) and an individual viva or questions at the presentation. Describe how the adjustment works and how disputes are handled.
8. **Risks and contingencies:** partner drop-out, team conflict, a student withdrawing, ethics approval for projects with human participants or personal data, and accessibility or reasonable adjustments.
- Do not state the institution's rules on intellectual property, ethics review or academic regulations as fact; write them as items to confirm with the relevant office.
- Rubric descriptors describe observable qualities of the work, not effort or attitude.
- The total student workload should match the credit weight; if it is not given, assume a typical load and say so.
- Keep partner demands realistic: about 1 hour a week or less, with defined touchpoints.
## Capstone overview
Short paragraphs plus an outcome-to-deliverable table.
## Milestones
Table: Week | Milestone | Submission | Feedback from | Graded (weight).
## Partner involvement
Partner brief, scoping agreement template and disengagement plan.
## Supervision
Cadence, meeting log template, early-warning signs, escalation.
## Assessment and rubrics
Weighting table, then the rubric table: Criterion | Excellent | Proficient | Developing | Not yet.
## Individual contribution
Evidence sources, the adjustment method with an example, dispute process.
## Risks and contingencies
Table: Risk | Prevention | If it happens.
## Assumptions
Bullets.
````
---
## Design a microlearning series
`design-microlearning-series` · prompt · Course design · https://hermes-ide.com/prompts/design-microlearning-series
Designs a series of five-minute lessons delivered over days, each with one objective, a hook, a practice item with feedback and spaced recall of earlier lessons.
````markdown
Microlearning works when each piece is small because it is focused, not because a long course was chopped into slices. A good five-minute lesson has one objective, starts with a hook that makes the learner care (a scenario, a surprising fact, a mistake they recognise), teaches one idea with one concrete example, and asks the learner to do something with it straight away. Across a series, the strongest lever is retrieval spaced over time: each lesson asks a quick question about an earlier one, at growing intervals, so knowledge is pulled back before it fades. The channel shapes the format: an email can carry a short read, a chat message must be shorter still, a video lesson needs a script.
Design a 10-lesson microlearning series on **[TOPIC]** for **[AUDIENCE]**, delivered by **email**.
1. **Series overview:** the overall performance goal (what learners will do differently at work or in life), why microlearning suits it, the cadence (for example every working day), and the total time per lesson.
2. **Objectives map:** split the goal into 10 single objectives, one per lesson, each with an observable verb, sequenced so each builds on the last. Group them into 2 to 4 themes.
3. **Schedule:** the delivery day for each lesson and which earlier lessons each one recalls, using expanding gaps (for example recall lesson 1 in lessons 2, 4 and 8).
4. **Lessons:** for each lesson write:
- title and objective;
- the hook (one or two sentences);
- the core content in the channel's format: email about 150 to 250 words; chat 3 to 5 short messages; app a few screens of text with a prompt; video a 60 to 120 second script with on-screen text cues;
- one practice item (scenario question, choose the better response, spot the mistake, or a do-it-today task) with feedback for each answer, explaining why;
- one spaced recall question on an earlier lesson, with the answer (from lesson 2 onwards);
- a one-line "try this today" action.
5. **Final check:** a 5 to 8 item scenario-based check covering the whole series, with answers, and one reflection question about applying it.
- One idea per lesson; if the topic needs more than 10 lessons to do properly, say what you would cut or add.
- Keep each lesson to about five minutes of the learner's time, including the practice.
- Practice items test application in realistic situations, not recall of the lesson's wording. Distractors reflect real mistakes.
- Plain, friendly language for the audience; no jargon without a definition.
- Use only accurate content. For regulated topics (safety, food hygiene, compliance) state that content must be checked against the organisation's policies and local regulations, and do not invent specific legal requirements or figures.
- If the topic is too broad for a series (for example "management"), narrow it, say how, and design for the narrower topic.
## Series overview
Bullets.
## Objectives map
Table: Lesson | Theme | Objective.
## Schedule
Table: Lesson | Day | Recalls lessons.
## Lessons
One subsection per lesson with the parts in step 4, labelled.
## Final check
Numbered items with answers, then the reflection question.
````
---
## Design a peer learning circle
`design-peer-learning-circle` · prompt · Course design · https://hermes-ide.com/prompts/design-peer-learning-circle
Designs a facilitated peer learning circle around a free online course, with a weekly meeting format, facilitator script, goal-setting, check-ins and a plan to keep going without an expert.
````markdown
Most people who start a free online course never finish it alone. A learning circle is a small group (about 4-12 people) that meets weekly to work through the same online material together, with a facilitator who is not an expert in the topic: their job is to host, keep time, ask good questions and help people get unstuck. Circles work when meetings have a steady rhythm, learners set their own goals, the group solves problems together instead of waiting for an answer, and people feel missed if they do not come. They fail when the facilitator tries to teach, when the course is too hard or too long for the time, or when the group stops after the material ends with no next step.
Topic: [TOPIC]. 6 weekly meetings.
1. **Circle overview:** a short invitation for a flyer or post, who it suits, the material and the time learners need between meetings. If no material is named, describe what to look for in a free course (clear weekly units, no paywall for the core content, works on the devices available) and mark the choice [to select].
2. **Meeting format:** a repeatable 90-minute meeting (or the given length): check-in round, recap of the week's material, working time on the course with peers, a group problem-solving or discussion activity, reflection, and planning for next week.
3. **Week-by-week plan:** for each of the 6 meetings, the course section, a discussion or activity idea, and what learners do before the next meeting. Include a first meeting for goals and tech set-up, and a final meeting for sharing and next steps.
4. **Facilitator script:** short, sayable wording for opening the first meeting, running check-ins, answering "I don't know" honestly ("Let's find out together"), helping someone stuck without solving it for them, drawing in quiet members, and closing.
5. **Goals and check-ins:** a simple personal goal card, a weekly one-line progress check, and how to respond when someone falls behind.
6. **Keeping it going:** handing facilitation to members, what happens after the last week (a new course, a project, a meet-up), and a short end feedback round.
- The facilitator is a host, not a teacher. Do not write lectures for them.
- Keep the between-meeting load realistic (state hours per week) and the course pitch right for beginners unless the setting says otherwise.
- Do not invent specific course titles, providers or links; describe criteria or mark [to select] unless the user named one.
- Include accessibility and digital inclusion: device lending or pairing, captions, offline notes, and help with log-ins without sharing passwords.
- If the topic is missing, ask and stop.
## Circle overview
Invitation text and practical details.
## Meeting format
Table: Minutes | Segment | What happens.
## Week-by-week plan
Table: Week | Course section | Activity | Before next meeting.
## Facilitator script
Short headed blocks of wording.
## Goals and check-ins
Goal card and weekly check.
## Keeping it going
Bullets.
````
---
## Design a peer-led learning group for retirees
`design-retiree-learning-group` · prompt · Course design · https://hermes-ide.com/prompts/design-retiree-learning-group
Designs a peer-led interest group for older adults on a topic such as history, languages, science or art, with a session format, rotating presenters, discussion, outings and accessibility.
````markdown
Peer-led learning groups for older adults, in the spirit of the University of the Third Age movement, have no teachers or exams: members share what they know, learn together for the pleasure of it, and the convenor organises rather than lectures. Groups thrive on a predictable format, real discussion, variety of voices and a social side. They struggle when the convenor or one expert does all the talking, when sessions are too long or hard to hear, when new members feel the group is a closed circle, or when nobody else will take a turn presenting because it feels like an exam.
Topic: [TOPIC]. Programme: 10 meetings.
1. **Group purpose:** a two-sentence description for a newsletter or noticeboard, who it suits (beginners welcome?) and what members can expect to get out of it.
2. **Session format:** a repeatable 90-120 minute meeting (or the length given): welcome and news, a 20-30 minute member talk or shared activity, discussion with three or four prepared questions, a tea break, a second activity (reading aloud, object handling, listening, practice in pairs), and planning next time.
3. **Programme:** themes for each of the 10 meetings that build a sense of journey, with a suggested format for each (member talk, shared reading, guest speaker, film or recording, hands-on, outing), and who might lead.
4. **Presenter guide:** a one-page guide that makes taking a turn easy: choose a small slice, 20 minutes, two or three objects or pictures, a handout of no more than one page in large print, end with questions for the group. Include pairing nervous presenters and the option of leading a discussion instead of giving a talk.
5. **Outings and extras:** visits, walks or events linked to the topic, with access and cost notes to check, and low-cost reading or listening between meetings.
6. **Accessibility:** hearing (seating, microphone, one person speaks at a time), sight (large print, contrast, slides readable from the back), mobility (venue access, seating with arms, breaks), and memory-friendly recaps.
7. **Running the group:** convenor tasks, sharing the jobs (tea, room, records), welcoming newcomers, handling a dominant talker kindly, keeping costs low, and a short feedback round at the end of the programme.
- No teacher-pupil hierarchy: language and format treat members as equals with life experience to share.
- Do not invent venue, outing or speaker details, prices or access facts; mark them [check].
- Keep tasks optional; no homework, tests or pressure to present.
- If the topic is very broad ("culture"), suggest three narrower options and ask which to plan, or plan the most likely one and say so.
## Group purpose
Short paragraph.
## Session format
Table: Minutes | Part | Who leads.
## Programme
Table: Meeting | Theme | Format | Possible lead.
## Presenter guide
Bullets, ready to print.
## Outings and extras
Bullets.
## Accessibility
Bullets.
## Running the group
Bullets.
````
---
## Design a placement learning plan for hosts
`design-work-placement-curriculum` · prompt · Course design · https://hermes-ide.com/prompts/design-work-placement-curriculum
Designs a host's learning plan for a student placement or internship, with weekly learning goals, supervised tasks, observation and feedback points, an assessment sign-off and a final review.
````markdown
Placement hosts often have goodwill but no plan: the student spends week one reading policies, then does whatever is lying around, gets feedback only at the end, and the university form is filled in from memory on the last day. Good placements give a clear progression from observing to doing with support to doing independently, real work with a purpose, regular short feedback, evidence collected as it happens, and a named supervisor with protected time. The host's plan has to fit the course's requirements without turning the placement into paperwork.
Field: [PLACEMENT_FIELD]. Length: 8 weeks.
1. **Placement goals:** four to six learning goals for [PLACEMENT_FIELD], mapped to the course requirements where given, each with what the student will be able to do by the end.
2. **Week-by-week plan:** for each of the 8 weeks, the focus, real tasks (moving from observe, to assist, to lead with supervision, to independent where safe), who they work with, and the evidence the week produces. Include a meaningful small project with a real audience in the second half.
3. **Supervision and feedback:** named supervisor and day-to-day contacts, a 15-minute weekly check-in agenda (what went well, one thing to improve, next week's goals), points where the supervisor observes a task with a short observation form, and how the student can raise a concern.
4. **Assessment and sign-off:** how evidence is collected during the placement (observation notes, work samples, reflective logs), a mid-point review, and what the supervisor signs, using the course's forms where given. Separate observed facts from judgement.
5. **Induction and safety:** a first-day and first-week plan covering people, tools and access, health and safety, confidentiality, and for under-18s or vulnerable settings the safeguarding and supervision rules to confirm [check with the course and local law].
6. **Final review:** an end-of-placement conversation guide, a short reference or feedback statement template, and what the host learns for next time.
- Real, useful work: no placements made of filing and shadowing only; but no unsupervised tasks beyond the student's competence or legal limits.
- Do not invent the course's forms, required hours, pay or employment law; mark them [check with the university or college] or [check local law].
- Respect any adjustments the student has agreed, and do not ask for disability or health details beyond what the student chooses to share.
- Feedback language is specific and behavioural, never about personality.
- If the field is unclear, ask and stop. If the student's level or year is not given, assume the most likely one from the field, state it at the top of Placement goals and list it under questions to confirm, then continue.
- If the request is really for unsupervised cover or free labour, say plainly that a placement needs a named supervisor and learning goals, note that pay and employment rules must be checked locally, and plan useful supervised work instead.
## Placement goals
Table: Goal | By the end the student can | Course requirement.
## Week-by-week plan
Table: Week | Focus | Tasks | Level of independence | Evidence.
## Supervision and feedback
Bullets, weekly check-in agenda and observation form.
## Assessment and sign-off
Bullets.
## Induction and safety
First-day and first-week checklist.
## Final review
Conversation guide, statement template, and any assumptions or questions to confirm with the course.
````
---
## Design a recertification refresher
`design-recertification-refresher` · prompt · Course design · https://hermes-ide.com/prompts/design-recertification-refresher
Designs annual refresher training for a compliance-heavy role with a pre-test that lets staff skip what they know, what changed since last year, realistic scenarios and a short sign-off.
````markdown
Annual refreshers usually repeat the same slides, so experienced staff click through and learn nothing, while the few things that actually changed or went wrong this year get the same weight as everything else. A better refresher starts with a short pre-test so people who show they know a section can skip it, spends the time on changes since last year, local incidents and near misses, and the decisions people get wrong under pressure, practises them in realistic scenarios, and ends in a sign-off that records competence rather than attendance. Practical skills (manual handling, first aid, fire equipment) still need hands-on practice and observation.
Topic: [TOPIC]. Time per person: up to 60 minutes.
1. **Must-know content:** the critical requirements for [TOPIC] grouped into four to six sections, marking which are knowledge, which are decisions, and which are practical skills. Add a "what changed" section from the input; if nothing is given, list what to check (law, regulator guidance, internal policy, incident and audit data) rather than inventing changes.
2. **Pre-test:** two or three questions per section, scenario-based rather than recall where possible, with a pass rule per section (for example all correct to skip it). Changes since last year and practical skills are never skippable.
3. **Refresher pathway:** for each section, the short content for those who did not pass (5-10 minutes), the format (micro-module, toolbox talk, huddle, hands-on practice) and timings, so the longest path fits 60 minutes.
4. **Scenarios:** four to six realistic scenarios from this role, including at least one from a recent incident or near miss if given, each with the decision, the right action, the common wrong action and why.
5. **Sign-off:** a short final check, a practical observation checklist for hands-on skills, a declaration that the person has read updated policy, and what happens if someone does not pass.
6. **Records and review:** what to record for audit (date, version, result, assessor), how to spot topics many people fail, and when to update the refresher.
- Technical and legal content must be checked by a competent person (for example the organisation's health and safety lead, safeguarding lead or a qualified trainer) against current law and guidance; mark all such points [verify].
- Never invent legal requirements, regulator rules, refresher frequencies or incident details.
- Practical skills are not signed off by a quiz alone.
- Keep it respectful of experienced staff; no trick questions.
- If the topic or role is unclear, ask and stop.
## Must-know content
Table: Section | Type (knowledge, decision, practical) | Skippable? | Key points.
## Pre-test
Numbered questions with answers and the pass rule per section.
## Refresher pathway
Table: Section | Content | Format | Minutes. Then shortest and longest path totals.
## Scenarios
Table: Scenario | Right action | Common mistake | Why it matters.
## Sign-off
Final check, observation checklist, declaration.
## Records and review
Bullets.
````
---
## Design a role-based onboarding curriculum
`design-onboarding-curriculum` · prompt · Course design · https://hermes-ide.com/prompts/design-onboarding-curriculum
Designs a cohort onboarding curriculum for one role with week-by-week modules, practice tasks, sign-offs and a readiness check. Use when several new hires start together and must reach proficiency.
````markdown
Most onboarding fails the same way: the first week is a firehose of slides, policies and system tours, and new hires are then left to "learn on the job" with no clear picture of what good looks like. Strong onboarding works back from the tasks a proficient person does, sequences them from frequent and low-risk to rare and high-stakes, and moves each task through a progression: see it done, do it with support, do it alone, then do it under normal workload. A cohort adds peer practice and shared debriefs, which cut the load on managers and speed up learning. Readiness is shown by observed performance on real or realistic work, not by attendance or a quiz.
Design a 4-week cohort onboarding curriculum for the role **[ROLE]**.
[TOOLS_AND_PROCESSES]
1. **Check the input first.** If the tools and processes are only a list of names with no indication of what a new hire does with them, or the role's core outputs are unclear, ask up to 4 short questions (core tasks, volume, what errors cost, who supports the cohort) and stop. Otherwise proceed and record any assumption.
2. **Task analysis.** List the 8 to 15 tasks a proficient person in this role performs. Rate each for frequency (daily, weekly, rare), risk if done wrong (low, medium, high) and difficulty (low, medium, high), then give each a treatment: train and sign off, train only, or job aid. Use this to decide order: frequent, low-risk tasks first; high-risk tasks only after supervised practice; rare tasks go to a job aid rather than heavy training. Every later module, practice task and sign-off must trace back to a task in this table.
3. **Readiness definition.** Write 4 to 6 observable statements of what a new hire can do, unaided, at the end of week 4, including any quality or speed standard (e.g. "resolves a standard billing ticket within the SLA with no QA errors"). Mark which standards you assumed.
4. **Week-by-week plan.** For every week give the focus, the modules, the share of time spent on live cohort sessions, self-paced work and supervised real work, and the shift in responsibility (shadow → assisted → independent with review → independent). Week 1 must include real hands-on practice by day 2 or 3, not only orientation. Spread policy and compliance content across the weeks next to the tasks they govern.
5. **Practice tasks.** For each module, one practice task that mirrors the real job, with the setup (sandbox, sample data, shadowed live work), what "done well" looks like and who gives feedback.
6. **Sign-offs.** For each task rated medium or high risk, a sign-off: the evidence (observed, work sample, review of N real cases), the standard, who signs and what happens if the standard is not met (re-practice, extra shadowing, extended supervision) without shaming.
7. **Readiness check.** A final check at the end of week 4: a realistic scenario or observed live work with a short checklist, plus the 30/60/90-day measures that show the onboarding worked (quality, volume, time to first independent task, early attrition).
8. **Support and roles.** Who does what: cohort facilitator, buddy, manager, subject-matter experts. Include a weekly cohort debrief, buddy check-ins and manager one-to-ones, with time each role must budget.
- Do not invent the organisation's policies, SLAs, legal requirements or system features. Where they matter, write a clearly marked placeholder such as [SLA: confirm with team lead].
- Keep the total weekly load realistic for a full-time new hire (no more than about 60% structured training by week 3; the rest is supervised real work).
- Prefer job aids and checklists over memorisation for rare or reference-heavy tasks, and say which job aids to build.
- Any safety-critical or regulated task must not be done unsupervised before its sign-off; say so in the plan.
- Avoid filler such as company history lectures beyond a short welcome; justify every module by a task in the analysis.
## Overview
Role, cohort, length, and a 3-sentence summary of the approach.
## Task analysis
Table: # | Task | Frequency | Risk | Difficulty | Treatment (train and sign off / train / job aid) | Week first practised. Then the list of job aids to build.
## Readiness definition
Numbered, observable statements.
## Week-by-week plan
Table: Week | Focus | Modules | Live / self-paced / real work (%) | Responsibility level. A short note per week below the table.
## Practice tasks
Table: Module | Practice task | Setup | Done well looks like | Feedback from.
## Sign-offs
Table: Task | Evidence | Standard | Signed by | If not yet met.
## Readiness check
The final scenario or observation, the checklist, and the 30/60/90-day measures.
## Support and roles
Bullets per role with time commitment.
## Assumptions and questions
What you assumed and what the team should confirm.
````
---
## Design a school outreach session
`design-school-outreach-session` · prompt · Course design · https://hermes-ide.com/prompts/design-school-outreach-session
Designs a one-off school outreach session run by a university, museum or employer, with a hands-on activity, a role model element, curriculum links, timing and follow-up resources for teachers.
````markdown
Outreach sessions are often a researcher talking over 40 slides of their own work to pupils who were told to attend. Pupils remember sessions where they did something with their hands, solved a puzzle a real researcher faces, met someone they could picture themselves becoming, and got a clear link to what they study in class. Teachers value sessions that connect to the curriculum and come with something to use afterwards. Short sessions need ruthless focus: one big idea, one activity, one memorable person.
Topic: [TOPIC].
Pupils' age or school year: [PUPIL_AGE].
Length: 60 minutes.
1. **Session goal:** the one big idea pupils should leave with and the one feeling (for example "people like me can do this"), stated in pupil-friendly words for [PUPIL_AGE].
2. **Run of show:** a timed plan for 60 minutes: a hook in the first three minutes (a mystery object, a surprising question, a live demo), a short framing, the hands-on activity as the largest block, the role model moment, and a close with a question to take away.
3. **Hands-on activity:** a task that mirrors real work in the field, with materials, set-up, pupil instructions, roles in small groups, questions to ask while circulating, an easier and a harder version, and what to do if it does not work.
4. **Role model moment:** how the presenter or a student ambassador briefly shares their route into the field (including setbacks and non-standard routes), and a short Q&A with prompts to get pupils asking.
5. **Curriculum links:** the subjects and topics this connects to at this age; mark specific curriculum references [check with the teacher] unless given.
6. **Practicalities and safety:** room and kit, risk assessment points for the activity, safeguarding basics for visiting adults (a teacher present at all times, no one-to-one contact, no collecting pupils' personal contact details, photo consent via the school), and accessibility.
7. **Follow-up for teachers:** a one-page teacher sheet with a 20-minute follow-up lesson idea, links to free resources described generically, and how pupils can find out more about routes into the field.
8. **Evaluation:** two or three quick measures (a before-and-after hands-up or card sort, one-word exit tickets, a teacher comment) and what not to claim from a single session.
- Pitch language, activity and examples at [PUPIL_AGE]; no jargon without a plain explanation.
- Talk-only time is under a third of the session.
- Use inclusive examples and role models, and avoid suggesting the field is only for "the clever ones".
- Do not invent curriculum references, statistics about the field, or named resources; describe them and mark [check].
- If the topic or age is missing, ask and stop.
## Session goal
Two lines.
## Run of show
Table: Minutes | Segment | Presenter does | Pupils do.
## Hands-on activity
Materials, set-up, instructions, circulating questions, variations.
## Role model moment
Bullets and Q&A prompts.
## Curriculum links
Bullets.
## Practicalities and safety
Checklist.
## Follow-up for teachers
Teacher sheet text.
## Evaluation
Bullets.
````
---
## Design a summer bridge programme
`design-summer-bridge-programme` · prompt · Course design · https://hermes-ide.com/prompts/design-summer-bridge-programme
Designs a summer bridge programme for students entering college or university that closes skill gaps and builds belonging, with a diagnostic, academic skills, refreshers and mentoring.
````markdown
Bridge programmes work when they do two jobs at once: build the specific academic habits and knowledge the next stage assumes (independent study, academic reading and writing, maths for the subject, using feedback), and make students feel they belong, know people, and know where to go for help. They fail when they feel remedial or labelled ("the catch-up group"), when content repeats school instead of previewing the new way of learning, when students who need it most cannot attend because of jobs, caring or cost, and when the support ends on the last day with no handover.
This entry is for students moving into further or higher education (age 16 and over). For younger pupils moving between schools, say that a school transition plan suits them better and adapt only if the user confirms.
Length: 3 weeks.
[TARGET_STUDENTS]
1. **Goals and measures:** three to five goals (for example confidence with academic writing, a peer network of at least three people, knowing how to use the support services), each with a measure taken at the start and end and at first-term follow-up.
2. **Diagnostic:** a short, low-stakes diagnostic in the first days (subject skills such as maths or reading, study habits, confidence) that sorts students into routes without labelling them, and how results are shared with each student.
3. **Programme schedule:** a week-by-week table for 3 weeks, and a typical day, balancing academic sessions, social and campus activities, and free time.
4. **Academic strand:** sessions that preview the real next stage: a taste lecture or class with a real tutor, note-making, academic reading, a short assignment with feedback and a resubmission, subject refreshers by diagnostic route, and study skills (time planning, using feedback, asking for help).
5. **Belonging strand:** small consistent groups, current-student mentors, campus or site navigation, meeting staff, how to use the library, wellbeing, careers and money services, and an activity where students bring their own experience as an asset.
6. **Mentoring and handover:** mentor recruitment and training, a contact plan into the first term, and what information passes to tutors (with the student's consent).
7. **Access and logistics:** removing barriers - stipend or lost-earnings support, travel, food, childcare or caring, accessibility, timing for working students, and an online option - each marked with the cost to check against the budget.
8. **Evaluation:** the measures above plus attendance, first-term continuation and early assessment results compared with a sensible comparison group, with limits stated.
- Frame the programme as a head start, not remediation; avoid deficit language in student-facing wording.
- Never make participation or diagnostic results a hidden condition of entry unless the user says it is, and then state it openly to students.
- Share data about students with tutors only with consent and the institution's data rules.
- Do not invent costs, bursary amounts, entry rules or outcome statistics; mark them [X] or [check].
- If the target students or the gaps they face are not described, ask and stop.
- If the target group is under 16 (for example primary-to-secondary movers), say this design assumes older students, suggest a school transition plan instead, and ask whether to continue.
- Signpost wellbeing and support services and say that any student in crisis is referred to the institution's support team or local emergency services.
## Goals and measures
Table: Goal | Measure | When measured.
## Diagnostic
Bullets.
## Programme schedule
Table: Week | Academic focus | Belonging focus | Key event. Then a typical day.
## Academic strand
Bullets.
## Belonging strand
Bullets.
## Mentoring and handover
Bullets.
## Access and logistics
Table: Barrier | Support | Cost to check.
## Evaluation
Bullets.
````
---
## Design an adult evening class
`design-adult-evening-class` · prompt · Course design · https://hermes-ide.com/prompts/design-adult-evening-class
Designs a community or adult-education evening course with sessions that respect adults' time, plenty of hands-on practice, mixed abilities, missed weeks and a final project.
````markdown
Adults choose evening classes after work, often tired, paying their own fees, and with very different starting points and reasons. They stay when every session is worth the journey: something made, practised or solved, built on what they already know, with time to ask questions and a sense of progress. They drop out when sessions are lectures, when one missed week means they are lost, or when the pace suits nobody. The tutor is usually an expert in the subject, not necessarily in teaching adults, and needs a plan that works in a community room with a mixed group.
Subject: [SUBJECT]. Sessions: 8 of 120 minutes.
1. **Course overview:** a title that says what learners will be able to do, a two- or three-sentence description for the prospectus, who it is for, and what prior knowledge or equipment is needed.
2. **Learners and assumptions:** the likely mix of starting points, motivations and constraints (time, cost, confidence, access needs), and the assumptions this plan makes. If learners are not described, state reasonable assumptions for this subject.
3. **Outcomes:** four to six outcomes stated as things learners can do by the end.
4. **Session-by-session plan:** for each of the 8 sessions: focus, what learners make, practise or solve, key teaching points, and a small between-session practice task that fits a busy week (optional, never required to keep up).
5. **Session template:** a repeatable structure for 120 minutes: arrival and a quick warm-up or recap, a short demonstration or input, extended hands-on practice with the tutor circulating, a break, more practice or application, sharing or show-and-tell, and a close with next week's preview. Most of the time is practice.
6. **Mixed abilities:** how each session offers a core task, an easier route and a stretch, how experienced learners can contribute without dominating, and how to catch up anyone who missed a session (a one-page recap per session, a quick catch-up task at the start).
7. **Final project:** a project or showcase that pulls the course together, scoped to fit the last two or three sessions, with options for different levels and a celebration in the final session. If some learners want accreditation, note what evidence to keep.
8. **Materials and costs:** a materials list with a starter-kit option, low-cost alternatives, and anything the venue must provide.
9. **First session:** a detailed plan for session one: welcomes and introductions that are not awkward, finding out what learners want, a quick early win in the subject, setting expectations and safety if relevant.
10. **Feedback and evaluation:** a mid-course check-in, an end-of-course feedback form of five or six questions, and how to record learners' progress against outcomes.
- Respect adult learners: draw on their experience, explain why things are done, and let them choose where possible. No childish activities or marking schemes.
- Practice dominates every session; talk-only input stays short.
- No session depends on having attended every previous one.
- Plan for real access needs: seating, lighting, print size, hearing, and breaks for a session of 120 minutes.
- Where the subject carries physical risk (tools, electrics, cooking, movement), include the relevant safety briefing and note that the provider's policies and any legal requirements apply.
- Do not invent prices or supplier names; give typical items and let the tutor price them.
- If the subject is too vague to plan (for example "art"), ask for the specific focus and level, offering options.
- Before finishing, check that the sessions add up to the outcomes, that the timings fit 120 minutes, and that the final project is achievable in the time given.
## Course overview
## Learners and assumptions
## Outcomes
Numbered.
## Session-by-session plan
Table: Session | Focus | Learners make or practise | Key teaching points | Optional practice.
## Session template
Table: Minutes | Segment | What happens.
## Mixed abilities
Bullets, and the catch-up approach.
## Final project
Brief with level options.
## Materials and costs
List.
## First session
Timed plan.
## Feedback and evaluation
Bullets and the feedback questions.
````
---
## Design an apprenticeship training plan
`design-apprenticeship-plan` · prompt · Course design · https://hermes-ide.com/prompts/design-apprenticeship-plan
Designs an on-the-job training plan for an apprentice or trainee with a competency matrix, rotations, sign-offs, mentoring and review points. For trades, workshops and small businesses.
````markdown
An apprenticeship succeeds when the apprentice moves steadily from watching to doing under supervision to working independently, with every step recorded and checked by someone competent. In small businesses the risk is the opposite of a classroom: apprentices get stuck on the same low-level jobs because they are useful, or are left alone on tasks before they are safe. A plan fixes this with a competency matrix, a sequence of rotations or job types, clear sign-off evidence, regular mentoring, and formal reviews. Many countries have official apprenticeship standards, off-the-job training requirements, college components and end-point or trade assessments; those rules vary and must be checked rather than assumed.
Design a 12-month training plan for an apprentice in the role **[ROLE]**.
[COMPETENCIES]
1. If the competencies are a short list of headings with no detail, break each into observable tasks a competent worker performs, and mark this breakdown "drafted, confirm with your standard or assessor". If you do not know whether an official standard or licence applies, ask the user which country or framework applies, or say clearly that they must check.
2. **Plan overview:** what the apprentice will be able to do at the end, the progression stages (for example: induction and safety, supervised core tasks, wider range with less supervision, independent work with checks), and how off-the-job learning (college days, courses, study time) fits around the work.
3. **Competency matrix:** each competency broken into tasks, with a four-level scale: 1 = has seen it done and can explain it; 2 = does it under direct supervision; 3 = does it independently with work checked; 4 = competent and could show someone else. Give the target level and target month for each task.
4. **Rotations and timeline:** month by month, the kinds of jobs, areas or sites the apprentice works on, which competencies each builds, and who supervises. Make sure no competency is starved because the apprentice is always kept on the most useful job.
5. **Sign-offs:** for each safety-critical or high-risk task, the evidence needed (observed several times, a work sample, a question-and-answer check), who is competent to sign, and the rule that the apprentice must not do it unsupervised before sign-off.
6. **Mentoring:** who mentors, weekly check-in format (15 minutes is enough: what went well, what was hard, what to try next week, logbook review), and how the mentor's time is protected.
7. **Review points:** formal reviews (for example at 1, 3, 6, 9 and 12 months) with the apprentice, mentor and any college or assessor, what is reviewed, and what happens if progress is behind (extra practice, changed rotation, support for learning needs).
8. **Logbook template:** a simple record the apprentice fills in after each job and the mentor countersigns.
- Safety first: anything involving electricity, gas, heights, machinery, chemicals, food safety, vehicles or vulnerable people is gated behind supervision and sign-off, and you do not invent the legal requirements for it; tell the user to confirm them with the relevant regulator, awarding body or insurer.
- Do not state funding rules, wage rates, off-the-job hour requirements or legal obligations as fact; list them under "Assumptions and checks".
- Keep paperwork light enough for a small business: one matrix, one logbook, short reviews.
- Write the plan so it is fair and supportive: progress gaps are treated as a training problem first, not a disciplinary one.
## Plan overview
Short paragraphs and the progression stages.
## Competency matrix
Table: Competency | Task | Target level (1-4) | Target month | Current level (blank to fill).
## Rotations and timeline
Table: Months | Work focus | Competencies built | Supervisor.
## Sign-offs
Table: Task | Evidence | Signed by | Unsupervised only after.
## Mentoring
Bullets plus the weekly check-in agenda.
## Review points
Table: Month | Who | What is reviewed | If behind.
## Logbook template
Fields to fill in.
## Assumptions and checks
Bullets: what to confirm with the standard, college, regulator or insurer.
````
---
## Design an e-learning module
`design-elearning-module` · prompt · Course design · https://hermes-ide.com/prompts/design-elearning-module
Designs a self-paced e-learning module with objectives, a screen-by-screen storyboard, interactions, knowledge checks and accessibility notes. For instructional designers and L&D teams.
````markdown
Most self-paced e-learning is "click next" reading with a quiz at the end: it informs, but it rarely changes what people do. Modules that work are built backwards from the behaviour on the job, use realistic decisions and scenarios rather than click-to-reveal, follow the evidence on multimedia learning (cut what is not needed, signal what matters, do not read on-screen text aloud word for word, break content into learner-paced segments), and are accessible from the start, not retrofitted.
Design a self-paced module of about 20 minutes on this topic.
[TOPIC]
1. **Design summary:** the performance goal (what learners will do differently on the job), who the learners are, and whether e-learning is the right fix. If the problem is really a process, tool or motivation issue, say so briefly.
2. **Objectives:** 2 to 5 objectives with observable verbs, each tied to the performance goal.
3. **Module structure:** sections with estimated minutes that add up to about 20. Allow roughly one minute per content screen and more for scenarios. Open with relevance (a realistic situation or a problem), not a list of objectives.
4. **Storyboard:** every screen in order. For each: on-screen text (short), narration if any (complementing, not duplicating, the on-screen text), visuals, the interaction and its purpose, branching and feedback, and notes for the developer. Prefer interactions that make learners decide (scenarios with consequences, sorting, spotting the error) over click-to-reveal and drag-and-drop for its own sake.
5. **Knowledge checks:** at least one per objective, at application level, written as realistic situations. Give each option tailored feedback that explains why, and state the completion and passing criteria.
6. **Accessibility:** to WCAG 2.2 AA: captions and transcripts for audio and video, alt text for meaningful images, keyboard operability for every interaction (with an accessible alternative to drag-and-drop), colour contrast and no meaning carried by colour alone, no time limits, readable plain language and reading order. Note any interaction that needs an alternative.
7. **Developer notes:** tracking (completion and score as SCORM or xAPI, according to the LMS), assets to source or create, variables and branching logic, and points to check with a subject-matter expert.
- Base content on the source material given; mark anything you added from general knowledge so a subject-matter expert can verify it, and never invent policy details, figures or legal requirements.
- Keep interactions feasible for the stated tool; if you are not sure the tool supports something, say "check that your tool supports this" rather than asserting it.
- If the topic is too large for 20 minutes, propose a series of shorter modules and design the first.
- Write for the audience's reading level and language background.
Use the section headings from the output contract. Module structure as a table: Section | Objective | Minutes. Storyboard as a table: Screen | On-screen text | Narration | Visual | Interaction and feedback | Dev notes. Knowledge checks as numbered items with options and per-option feedback.
````
---
## Design an intensive bootcamp curriculum
`design-bootcamp-curriculum` · prompt · Course design · https://hermes-ide.com/prompts/design-bootcamp-curriculum
Designs an intensive multi-week bootcamp curriculum (coding, data, design or trades) with a daily rhythm, a project spine, assessments, pacing for fatigue and an honest graduate profile.
````markdown
Bootcamps compress months of learning into weeks. They fail learners in familiar ways: a syllabus copied from a framework's documentation rather than from job ads, too many tools covered shallowly, lectures in the morning that nobody retains by afternoon, burnout in weeks 4-6, weaker learners silently falling behind until the final project, and marketing that promises job titles the curriculum cannot deliver. Strong bootcamps work back from what a junior in the target role does in their first month, keep a project spine running the whole way, practise daily with fast feedback, assess at checkpoints with a plan for those who miss the bar, and are honest about what graduates can and cannot do.
Field: [FIELD]. Length: 12 weeks.
[TARGET_ROLES]
1. **Graduate profile:** from the target roles, list 6-10 tasks a junior does in their first months, and turn them into outcomes. Separate must-have from nice-to-have; drop tools that appear rarely in the ads.
2. **Entry requirements:** the prerequisite skills, a pre-work module (hours and content) and an admissions task that predicts success better than an interview alone.
3. **Week-by-week plan:** group the 12 weeks into phases (foundations, core skills, integration, capstone and job readiness). For each week: focus, skills, the project increment, and the checkpoint.
4. **Project spine:** small daily exercises, weekly mini-projects, a team project that mirrors real workflows (version control, reviews, briefs, site practice), and an individual capstone for the portfolio.
5. **Daily rhythm:** a typical day for full-time or part-time delivery: short input (under 45 minutes at a time), guided practice, independent or pair work, review or stand-up, and a reflection. Include breaks and a lighter day each week.
6. **Assessment and checkpoints:** a checkpoint every two to three weeks with a practical task and rubric, what happens if a learner does not pass (catch-up plan, repeat a phase, deferral), and the final assessment against the graduate profile.
7. **Pacing and support:** where fatigue peaks and what changes then, mentoring and help queues, wellbeing check-ins, support for learners with access needs, and early-warning signs instructors watch.
8. **Honest limits:** what graduates will be able to do, what they will still need on the job, and wording for marketing that does not over-promise.
- Every topic must trace to a task in the graduate profile; list what you cut and why.
- Do not quote job-placement rates, salaries or market demand; say what to research and how.
- Never write guaranteed-job, guaranteed-salary or "job-ready in X weeks" claims; if asked for them, decline briefly and give honest marketing wording instead.
- For trades or regulated fields, note where licensing, supervised hours or awarding-body rules apply and mark them [check local regulations]; a bootcamp cannot replace them.
- Keep the plan realistic for the hours available; if 12 weeks cannot reach the target roles from the stated entry profile, say so and propose a narrower role or longer programme.
- If target roles or the entry profile are missing, ask for them and stop.
## Graduate profile
Table: Junior task | Outcome | Must or nice to have.
## Entry requirements
Bullets: prerequisites, pre-work, admissions task.
## Week-by-week plan
Table: Week | Phase | Focus | Skills | Project increment | Checkpoint.
## Project spine
Bullets.
## Daily rhythm
Table: Time | Block | What happens.
## Assessment and checkpoints
Bullets and a sample checkpoint rubric.
## Pacing and support
Bullets.
## Honest limits
Bullets and suggested marketing wording.
````
---
## Design course gamification
`design-course-gamification` · prompt · Course design · https://hermes-ide.com/prompts/design-course-gamification
Designs course game mechanics (quests, progress, badges, choice, team challenges) tied to learning outcomes, flags points that reward the wrong behaviour and plans for disengaged learners.
````markdown
Gamification helps when the game rewards the learning itself: attempting harder problems, practising, revising work after feedback, helping peers. It backfires when points reward the easy and visible (logins, clicks, speed, volume of posts), when public leaderboards tell the bottom half they are losers, when extrinsic rewards replace interest people already had, and when the novelty fades after three weeks. Durable designs support autonomy (meaningful choices), competence (visible progress toward real mastery) and relatedness (team goals, contribution).
Learners: teens.
[COURSE_OUTLINE]
1. **Engagement problem:** name the specific behaviour to change (for example students skip practice quizzes, few submit drafts, online learners drop off in week 3). If none is given, infer the likeliest from the outline and say so.
2. **Core loop:** the repeating cycle learners go through each week (choose a quest, practise, get feedback, level up), in one or two sentences, and how it maps to the course's learning cycle.
3. **Mechanics map:** for each unit or module, the mechanics used and the learning behaviour each rewards. Choose from: quests with choice of route, mastery levels or skill trees tied to outcomes, retries without penalty, narrative or theme, team challenges with shared goals, badges for specific demonstrated skills, unlocks, and personal-best progress. Use only a few, consistently.
4. **Progress and rewards:** how progress is shown (progress toward outcomes, not raw points), what badges mean (each with a criterion a teacher could verify), and how this relates to grades. Keep game points separate from final grades, or say exactly how they feed in.
5. **Perverse incentive check:** for every mechanic, what a learner could do to game it without learning, and the fix.
6. **Disengaged learners:** a fallback for learners who do not care for games or fall behind: private progress only, catch-up quests, choice to opt out of competitive elements, and a human check-in.
7. **Running it:** set-up effort, what a teacher does weekly, low-tech options (paper tracker, wall chart) as well as digital, and how to tell after four weeks if it is working.
- Every mechanic must reward a behaviour that serves an outcome; cut any that only rewards attendance, clicks or speed.
- No public ranking of individuals for children or teens; for adults, only opt-in leaderboards, ideally team-based or personal-best.
- No loss-based pressure (streak-breaking penalties, losing earned levels) and no purchasable advantages.
- Collect no more learner data than the course already does; respect the platform's privacy settings and school policies.
- Do not name specific apps or platforms unless the outline already uses them.
- If the outline has no outcomes or structure, ask for them and stop.
## Engagement problem
Two or three sentences.
## Core loop
One or two sentences and a simple text diagram.
## Mechanics map
Table: Unit or module | Mechanic | Learning behaviour rewarded | Outcome served.
## Progress and rewards
Bullets, with a badge list: Badge | Criterion | Evidence.
## Perverse incentive check
Table: Mechanic | How it could be gamed | Fix.
## Disengaged learners
Bullets.
## Running it
Bullets: set-up, weekly routine, four-week check.
````
---
## Design online discussion tasks
`design-online-discussion-tasks` · prompt · Course design · https://hermes-ide.com/prompts/design-online-discussion-tasks
Designs async online discussion tasks that produce real exchange, with decision or problem prompts, roles, staggered deadlines, a reply rubric and instructor moves, not "post once, reply twice".
````markdown
"Post 250 words on the reading and reply to two classmates" produces parallel monologues: everyone posts the night before the deadline, replies say "Great point, I agree", and the instructor reads 300 posts nobody else reads. Discussion works online when the prompt forces a position or a decision that reasonable people disagree on, when learners need each other's input to finish (different cases, roles or data), when deadlines are staggered so replies have something to reply to, when groups are small (5-8), and when the rubric rewards building on, challenging and synthesising rather than word count.
Weeks: 6.
[MODULE_TOPICS]
1. For each of the 6 weeks, choose a discussion format that fits the topic, varying them across the course: decide-and-defend (pick from options and justify), case analysis with different groups taking different cases, debate with assigned sides, problem-solving with partial information shared across members, critique of a worked example or draft, applying a concept to learners' own context, and a synthesis week.
2. Write each prompt in learner-facing words: the scenario or question, what to post first (and its length), what replies must do, and how it connects to an outcome or assessment.
3. Define rotating roles for small groups (starter, challenger, connector to the reading, summariser) and how they rotate.
4. Set staggered deadlines (for example initial post by day 3, replies by day 6, summariser post by day 7) and recommended group size and grouping method.
5. Write a short reply rubric with three or four criteria (uses evidence, builds on or challenges a specific point, moves the discussion forward, clarity) and three levels, plus examples of a weak and a strong reply.
6. List instructor moves: a weekly launch note, targeted questions to a thread that stalls, drawing quiet learners in privately, a weekly wrap-up that names good contributions (with permission) and corrects misconceptions, and a time budget per week.
- Prompts must have no single obvious answer and must require the reading or concept to answer well.
- Avoid prompts that make learners disclose personal, health or sensitive information; offer a hypothetical option when using their own context.
- Keep marking manageable: grade a sample or the summariser post, or use the rubric holistically per week; state the instructor time per week.
- Include accessibility: plain-language prompts, an audio or video posting option where possible, and a deadline window that works across time zones if learners are distributed.
- If topics are missing, ask for them and stop.
## Design principles used
Three to five bullets tied to this course.
## Weekly tasks
For each week: format, learner-facing prompt, what to post, what replies do, outcome link.
## Roles
Table: Role | What it does | Rotation.
## Deadlines and group set-up
Bullets.
## Reply rubric
Table: Criterion | Developing | Secure | Excellent. Then a weak and a strong example reply.
## Instructor moves
Bullets with minutes per week.
````
---
## Design volunteer induction training
`design-volunteer-induction-training` · prompt · Course design · https://hermes-ide.com/prompts/design-volunteer-induction-training
Designs induction training for nonprofit or community volunteers in one role, covering day-one essentials, safeguarding and boundaries, shadowing, short modules and a sign-off sized to unpaid time.
````markdown
Volunteers give unpaid time and leave quickly when induction is a long slideshow of policies, or when they are thrown in with no idea what to do. They also put people at risk when nobody explains boundaries, confidentiality and what to do with a worry. Good induction separates what a volunteer must know before their first shift from what they can learn on the job, teaches it through real situations from the role, uses shadowing, and checks readiness before anyone works unsupervised.
Role: [ROLE]. Induction budget: about 3 hours.
[ORGANISATION_CONTEXT]
1. **Day-one essentials:** list what the volunteer must know and be able to do before their first shift for [ROLE]: purpose and values, who to report to, health and safety for this role, safeguarding and how to raise a concern, confidentiality and data, boundaries, emergencies, and the two or three core tasks. Everything else goes to "learn on the job".
2. **Induction plan:** fit the essentials into 3 hours, split into short modules (15-40 minutes) that can run as a group session, one-to-one or self-paced online. Each module: purpose, method (scenario discussion, demonstration, practice), and a quick check. If the essentials cannot fit, say what to cut or move into a second session.
3. **Safeguarding and boundaries:** realistic scenarios from this role (for example a client offers a gift, asks for a phone number, discloses abuse, a volunteer is asked to do something outside their role), with the right response for each. Use the organisation's policies; where none are given, write [insert your policy] and name the role of the safeguarding lead.
4. **Shadowing and sign-off:** how many shadow shifts, what the volunteer observes and then does under supervision, and a readiness checklist the supervisor signs. Include pre-start checks to confirm (references, background checks where the role needs them, marked [check local law and policy]).
5. **Materials:** a one-page role card, a "who to call" card, and a short welcome message.
6. **Keeping volunteers:** first-month check-ins, refresher for policy changes, recognition, and an easy way to give feedback or step back.
- Respect unpaid time: no module longer than 40 minutes, no content that is not needed for the role.
- Plain, warm language; no jargon or legal wording in volunteer-facing materials.
- Never invent the organisation's policies, legal requirements or background-check rules; mark them [check] and say who to ask.
- Volunteers never investigate or counsel; they listen, record and pass concerns to the named lead the same day (immediately if someone is in danger, contacting local emergency services).
- Include accessibility: varied formats, timing that suits working volunteers, adjustments on request.
- If the organisation context does not say who volunteers will meet or who supervises them, ask for that and stop.
## Day-one essentials
Two lists: Before first shift, Learn on the job.
## Induction plan
Table: Module | Minutes | Format | Method | Quick check. Total row.
## Safeguarding and boundaries
Table: Scenario | What to do | Who to tell.
## Shadowing and sign-off
Bullets and the readiness checklist.
## Materials
Role card, who-to-call card and welcome message drafts.
## Keeping volunteers
Bullets.
````
---
## Estimate course build effort
`estimate-course-build-effort` · prompt · Course design · https://hermes-ide.com/prompts/estimate-course-build-effort
Estimates the effort to build a course by format (instructor-led, e-learning by interactivity level, video) using hours-per-finished-hour ranges, roles, review cycles and risks, given as a range.
````markdown
Course build estimates go wrong in the same ways: one number is given instead of a range, "1 hour of e-learning" is treated the same whether it is page-turning or a branching simulation, subject-matter expert time and review rounds are left out, scattered source material is assumed ready, and translation, accessibility, LMS testing and pilot fixes appear only at the end. A defensible estimate breaks the work into components, applies hours-per-finished-hour ranges by format and interactivity, adds the roles and review cycles explicitly, and states assumptions so the client or manager can see what moves the number.
[COURSE_SCOPE]
1. Restate the scope as components with finished learning time each: instructor-led sessions (with facilitator guide, slides, activities, handouts), e-learning by interactivity (basic: text, images, simple questions; moderate: scenarios, interactions, audio; advanced: branching simulations, custom media), video (talking head, screen capture, animation), job aids and assessments.
2. Apply rough hours-per-finished-hour ranges as starting points, labelled as commonly quoted industry rules of thumb that vary widely: for example instructor-led about 25-80 hours per hour, basic e-learning about 50-125, moderate about 125-275, advanced 200-700 or more; short video by minute of finished footage depending on style. Adjust up or down for the source material state, the team's experience, reuse of templates and stakeholder count, and say why.
3. Split effort by role: instructional design, development or authoring, media, subject-matter expert time (often underestimated: interviews, reviews, checking accuracy), project management (10-15% is common), quality assurance and accessibility, LMS set-up and testing, translation or localisation if needed.
4. Add review cycles explicitly (for example design document, storyboard or script, alpha, beta, final), with the time each takes and who reviews.
5. Build a schedule from the team's hours per week, showing the critical path and whether the deadline holds.
6. Give the total as low, likely and high, and a contingency for the top risks.
7. Suggest ways to reduce effort without hurting learning: fewer interactivity levels, job aids instead of modules, templates, cutting nice-to-know content, piloting a slice first.
- Always a range; show the arithmetic behind each component. If the user insists on one number, give the likely figure as the number to quote, with the range and the two or three assumptions that move it in one short line underneath.
- If team hours per week are not given, assume them, state the assumption, and show how the schedule changes if they differ.
- Label every ratio as an assumption to calibrate against the team's own past projects.
- Do not quote day rates or prices unless the user gives them; if they do, convert hours to cost with the arithmetic shown.
- If finished learning time or format is unknown, ask for it, or estimate two clearly different scenarios and say which questions would decide between them.
## Scope as understood
Table: Component | Format and level | Finished time.
## Estimate by component
Table: Component | Hours per finished hour (range) | Low | Likely | High. Totals row.
## Effort by role
Table: Role | Low | Likely | High.
## Schedule
Bullets or table by phase and week, with review cycles and critical path.
## Assumptions
Bullets.
## Risks and contingency
Table: Risk | Effect on effort | Mitigation.
## Ways to reduce effort
Bullets with the hours each saves.
````
---
## Instructional designer
`instructional-designer` · persona · Course design · https://hermes-ide.com/prompts/instructional-designer
Acts as an instructional designer who starts from performance goals, uses backward design and evidence-based learning principles, and cuts content that does not change behaviour.
````markdown
From now on, work as this persona: Instructional designer.
You are an instructional designer with a long track record in corporate learning, higher education and online courses. You have built onboarding programmes, compliance training people actually remember, university modules, and self-paced courses, and you have seen far more training fail from too much content than from too little. People bring you a topic, a slide deck to "turn into a course", a request from a stakeholder, or a programme that is not working.
How you work:
- You start with performance, not content. Your first questions are: what should people be able to do, in what situation, that they cannot do now? How will we know? Is this actually a skill gap, or a process, tool, clarity or incentive problem that training will not fix? You say so when training is not the answer.
- You design backwards: outcomes with observable verbs, then the evidence that would show each outcome (assessments and on-the-job measures), then the practice that builds toward that evidence, and only then the content needed to support the practice.
- You cut ruthlessly. Content earns its place only if learners need it to perform. "Nice to know" goes into a reference or job aid, not the course.
- You apply evidence-based learning principles plainly: manage cognitive load (one idea at a time, worked examples before independent practice, remove decoration); retrieval practice and spacing over re-reading; realistic practice with feedback, getting harder over time; varied examples so learning transfers; and support for transfer back on the job (manager involvement, job aids, follow-up).
- You prefer realistic scenarios and decisions over information dumps, and short practice-heavy formats over long presentations.
- You adapt to constraints: budget, time, tools, audience size and the stakeholder's real deadline, and you offer a lean option and a fuller option when trade-offs matter.
- You ask one or two questions at a time, and when you have enough, you produce something concrete: an outcome list, an outline, a storyboard, an assessment, a critique.
What you flag:
- Objectives with "understand", "know" or "be aware of" that cannot be observed.
- Assessments that test recall when the job needs judgement or performance.
- Courses with no practice, or practice that does not resemble the real task.
- Slide-heavy modules, clicking "next" presented as interactivity, and narration that reads the screen aloud.
- Evaluation limited to satisfaction surveys.
- Accessibility gaps: missing captions or alternatives, low contrast, colour-only cues, interactions that need a mouse, and content that excludes or stereotypes.
- Learning-styles matching and other popular claims the evidence does not support; you say so briefly and offer what does work.
Your boundaries:
- You are honest with stakeholders, including when the request is the wrong solution, but you respect that they own the decision.
- You do not invent subject-matter facts. You mark what a subject-matter expert must provide or check, especially for regulated, safety, medical, legal or financial content.
- You do not claim results a design cannot show; you say what each kind of evaluation can and cannot prove.
Your habits:
- Every recommendation ties back to a performance outcome.
- You show trade-offs in a sentence or a small table, not in essays.
- You end with the next decision the person needs to make.
````
---
## Map a course to qualification standards
`map-course-to-qualification-standards` · prompt · Course design · https://hermes-ide.com/prompts/map-course-to-qualification-standards
Maps a vocational or professional course to an awarding body's units or occupational standards in a coverage matrix, showing which criteria are taught, assessed and evidenced, and which are missing.
````markdown
Training providers map courses to qualification units or occupational standards for approval, audits and quality reviews. The typical failures: criteria ticked because the topic is "covered" in a session when nothing assesses it; criteria that need performance in the workplace evidenced only by a quiz; one portfolio item claimed against fifteen criteria; behaviours (such as professionalism or teamwork) never explicitly taught or evidenced; and the command verb of a criterion (describe, explain, evaluate, demonstrate) ignored. A useful map is criterion by criterion, distinguishes taught from assessed from evidenced, and checks that the evidence type matches what the criterion asks.
[COURSE_OUTLINE]
[STANDARDS]
1. List every criterion or knowledge, skill and behaviour statement with its code exactly as given. Do not paraphrase codes or merge criteria.
2. For each, find where the course teaches it, where learners practise it, and where it is assessed; record the session or module reference.
3. Judge the evidence fit: does the assessment method match the criterion's command verb and context? (A "demonstrate in the workplace" criterion needs observation, witness testimony or a work product; an "evaluate" criterion needs written or oral judgement, not a list.)
4. Rate each criterion: fully covered (taught and assessed with fitting evidence), partly covered (taught but not assessed, or assessed with weak evidence), or missing.
5. Flag over-claims: a single activity mapped to many criteria, generic evidence, criteria claimed but only mentioned in passing.
6. Propose an evidence plan for every partial or missing criterion: the smallest change (add a question, a task, an observation point, a reflective account, a professional discussion) and where in the course it fits.
7. Summarise coverage counts and the top risks for approval or audit.
- Use only the standards text supplied; never invent criteria, codes, assessment rules or awarding-body requirements. If the user's text is incomplete or ambiguous, say which parts.
- Mark interpretations of what a criterion requires as your reading, to confirm against the awarding body's guidance or the end-point assessment plan.
- Be strict: "mentioned in a session" is not "assessed".
- If either the course outline or the standards are missing, ask for the missing one and stop.
## Summary
Counts: fully, partly, missing; top three risks.
## Coverage matrix
Table: Code | Criterion (short) | Taught where | Assessed where | Evidence type | Fit | Rating.
## Gaps
Bullets, by code.
## Over-claims and weak evidence
Bullets, by code.
## Evidence plan
Table: Code | Proposed change | Where in course | Evidence produced.
## Questions for the awarding body
Bullets.
````
---
## Map programme outcomes across courses
`map-program-curriculum` · prompt · Course design · https://hermes-ide.com/prompts/map-program-curriculum
Maps programme-level outcomes across courses showing where each is introduced, reinforced and mastered, and flags gaps, overloads and sequencing problems. Use for programme review or accreditation.
````markdown
A curriculum map shows whether a programme actually delivers what it promises. Each programme outcome should be introduced (I), reinforced (R) and finally mastered (M) in a sensible order, and mastery should be shown in an assessment, not just "covered" in a lecture. Common problems are outcomes that are never assessed at mastery, outcomes that only appear in electives (so some graduates never meet them), courses claiming nearly every outcome, and mastery placed before introduction. A map is only as good as its evidence, so it must separate what course documents state from what the mapper infers.
Build a curriculum map from the material below.
[PROGRAM_OUTCOMES]
[COURSES]
1. If the courses have no outcomes or assessments at all (only titles), say the map would be guesswork, list exactly what to collect from each course lead, and produce only a provisional map clearly labelled "inferred from titles".
2. For each course and programme outcome, assign I, R or M where there is a real link, using these definitions: I = the outcome is first taught and practised at a basic level; R = it is practised with more complexity or independence; M = students demonstrate it at the programme's exit standard in an assessed task. Leave the cell empty where there is no meaningful link.
3. Mark every cell as stated (the course's own outcomes or assessments show it) or inferred (you judged it from content). Put an asterisk on inferred cells.
4. **Gaps:** outcomes with no M, no assessed evidence, only elective coverage, or a missing I before R or M.
5. **Overloads:** courses mapped to more than about half the programme outcomes, or with M on several outcomes but a single assessment; outcomes concentrated in one year.
6. **Sequencing issues:** M or R appearing in a term before the first I, prerequisites that do not match the map, and long gaps where an outcome is not practised.
7. **Assessment evidence:** for each outcome, which assessment(s) provide mastery evidence, and whether the assessment type fits the outcome's verb (an exam cannot show "collaborate in a team").
8. **Recommendations:** the 5 to 8 changes with the biggest effect, each naming the course(s) and what to adjust (add an assessment, move an outcome, drop a claim), smallest effective change first.
- Do not inflate the map to make it look complete. An honest gap is more useful than a claimed link.
- Use only the course information supplied; do not assume content a course "probably" covers without marking it inferred.
- Be neutral about individual courses and staff; describe the curriculum, not the people.
- If accreditation standards are mentioned, do not quote their wording from memory; refer to them by name and ask the user to check the exact criteria.
## Summary
3 to 5 sentences on overall coverage and the biggest issues.
## Curriculum map
Table: rows are courses in programme order (with year/term and required/elective), columns are outcomes PO1, PO2, …; cells I, R, M or blank, inferred cells with *. Then a totals row counting I/R/M per outcome.
## Gaps
Bullets by outcome.
## Overloads
Bullets.
## Sequencing issues
Bullets.
## Assessment evidence
Table: Outcome | Mastery assessment(s) | Fit to the outcome's verb | Note.
## Recommendations
Numbered, each with course, change and the gap it closes.
## Questions for course leads
Bullets.
````
---
## Peer tutoring launch track
`peer-tutoring-launch-track` · workflow · Course design · https://hermes-ide.com/prompts/peer-tutoring-launch-track
Launches a school or university peer tutoring programme in gated steps, from goals and safeguarding to tutor training, matching, first sessions and an impact review after a term.
````markdown
Launches a peer tutoring programme in a `secondary` setting, one approved step at a time: clear goals and a simple model, safeguarding and approvals, recruiting and training about 10 tutors, matching tutors to tutees, running and supporting the first sessions, and reviewing impact after a term. Subjects and need:
[SUBJECTS]
Peer tutoring works when it is structured: trained tutors, a set session routine, regular sessions over weeks, the right materials and staff monitoring. It does not work as unsupervised "homework buddies".
Each step produces one document and stops for the lead's approval; later steps build on approved decisions. Never invent policies, legal requirements or data; use placeholders such as [check with your safeguarding lead]. Refer to learners by role or code, never by name.
## Steps
Work through these steps in order. Do not skip a gate.
1. goals-and-design (plan)
2. safeguarding-and-approvals (plan)
3. recruit-and-train (build)
4. matching (build)
5. first-sessions (operate)
6. impact-review (review)
### Step 1: Goals and design
1. Ask in one message for anything missing: who the tutees are and how they are chosen, evidence of need, available time and space, and staff time for coordination.
2. Turn the subjects into two or three measurable first-term goals for tutees and tutors (for example fluency, quiz scores, confidence, attendance).
3. Recommend a model for a `secondary` setting with reasons: cross-age or same-age, one-to-one or small group, when sessions happen, and frequency (as a starting point, two or three 20-30 minute sessions a week for eight to ten weeks).
4. Draft the routine tutors follow every session, suited to the subject, and the materials needed.
5. Name the roles: coordinator, safeguarding contact, weekly tutor support.
Output: goals table (Goal | Measure | Baseline source | Target), model, routine, roles.
Stop for approval.
**Gate:** stop here and wait for the user's approval before step 2 (safeguarding-and-approvals).
### Step 2: Safeguarding and approvals
1. List the safeguarding measures for a `secondary` setting: sessions in visible, supervised spaces; no private contact or personal messaging outside sessions; a disclosure procedure (listen, never promise secrecy, tell the named staff contact the same day); how either side can ask to change partner or stop; background checks for adults working with under-18s [check with your safeguarding lead and local law]; data protection for progress data.
2. List approvals and communications: leadership, safeguarding lead, timetabling, family information or consent, staff briefing, each marked [check local policy].
3. Draft a one-page tutor code of conduct and a plain-language note for tutees and families.
4. Write a risk register (Risk | Likelihood | Impact | Control | Owner) covering safeguarding, tutor workload, tutee stigma, missed sessions and inaccurate teaching.
Output: safeguarding measures, approvals checklist, code of conduct, family note, risk register.
Stop for approval. No recruiting yet.
**Gate:** stop here and wait for the user's approval before step 3 (recruit-and-train).
### Step 3: Recruit and train
1. Draft a recruitment message for about 10 tutors: the role, time commitment, what they gain, how to apply. Select for reliability, patience and secure knowledge, not only top grades.
2. Plan short training sessions: the routine, explaining without giving answers (wait, prompt, hint, model), specific praise, the materials, session logs, the code of conduct and disclosure steps, and what to do when they do not know the answer (say so, check together, flag it in the log), and role-plays (a silent tutee, one who wants answers, one who is upset).
3. Add a readiness check: an observed practice session with a checklist.
4. Plan ongoing support: regular tutor huddles, help between sessions, end-of-term recognition.
Output: recruitment message, training plan with timings, readiness checklist, support plan.
Stop for approval.
**Gate:** stop here and wait for the user's approval before step 4 (matching).
### Step 4: Matching
1. Ask for anonymised tutor and tutee details (codes, strengths and needs, availability, relevant considerations) if not given.
2. Propose matching rules: tutor secure in what the tutee needs, a suitable age or attainment gap, shared availability, no known conflicts. Staff judgement overrides the rules.
3. Draft a matching table (Tutor code | Tutee code | Reason | Watch?).
4. Set the baseline: the Step 1 measures taken before the first session, and a comparison group if feasible, with its limits stated.
5. Draft a session log: date, what was covered, how it went, any concern.
Stop for approval.
**Gate:** stop here and wait for the user's approval before step 5 (first-sessions).
### Step 5: First sessions
1. Plan each pair's first session: introductions, the tutee's goal in their own words, an easy early win using the routine.
2. Set monitoring: coordinator drop-ins in the first fortnight with an observation checklist (routine followed, tutee doing the thinking, tone, materials pitched right) and weekly log reading.
3. Prepare responses to common problems: missed sessions, a tutor giving answers, a disengaged tutee, a poor match, wrong-level materials, and any safeguarding concern (Step 2 procedure, same day).
4. In week two, check privately with tutors and tutees how it is going and whether supervision works in practice.
5. Provide a two-week check-in template: attendance, observations, issues, actions.
Output: first-session plan, observation checklist, problem responses, check-in template.
Ask the lead to share how the first weeks went, adjust, and stop until the term is complete.
**Gate:** stop here and wait for the user's approval before step 6 (impact-review).
### Step 6: Impact review
1. Ask for end-of-term data: the baseline measures again, attendance, a summary of session logs, and feedback from tutors, tutees, families and staff.
2. For each goal give baseline, end point and change, and how many tutees improved, stayed level or fell back. Compare with any comparison group and state plainly what the data cannot show (small numbers, no random assignment, other support).
3. Review implementation: frequency achieved, routine fidelity, which pairs worked and why. Include benefits for tutors and whether the load on them was fair, especially near their own exams.
4. Recommend what to keep, change or stop, and whether to scale.
5. Draft a one-page leadership summary and a short celebration note for tutors and families, with no learner identifiable.
Output: results table (Goal | Baseline | End | Change | Notes), findings, recommendations, both drafts.
````
---
## Plan a course pilot
`plan-course-pilot` · prompt · Course design · https://hermes-ide.com/prompts/plan-course-pilot
Plans a pilot run of a new course or module with a small learner group, what to measure, the feedback instruments and decision rules agreed in advance for launch, revise or drop.
````markdown
Pilots often prove nothing: friendly volunteers rate it 4.6 out of 5, nobody measured whether they learned anything, and the launch decision was already made. A useful pilot tests the riskiest assumptions with learners who resemble the real audience, measures learning and time as well as satisfaction, finds the exact points where people get stuck, and agrees before it starts what results mean launch, revise or drop.
Pilot size: about 15 learners.
[COURSE_SUMMARY]
1. **Pilot questions:** turn the course's riskiest assumptions into three to five questions the pilot must answer (for example: can novices finish module 3 without help? does the course fit in the advertised hours? do learners reach outcome 2?).
2. **Pilot design:** who to recruit (real target learners, not colleagues or fans; include some likely to struggle), how many, incentives, whether to pilot the whole course or the riskiest modules, and live observation versus self-paced with analytics.
3. **Measures:** for each question, the measure and threshold: completion and drop-off point; learning gain (short pre and post check on the outcomes, or a performance task scored with a rubric); actual time per module against the plan; confusion points (where learners ask for help, rewind, fail an item or stall); usefulness and confidence ratings; accessibility issues.
4. **Instruments:** draft the pre and post check blueprint (items per outcome), a five- to eight-item feedback survey with at least two open questions, a think-aloud or observation protocol for three to five learners, a facilitator log, and a short exit interview guide.
5. **Decision rules:** written thresholds agreed in advance, for example launch if at least 80% complete and the median learner meets the outcome bar with time within 20% of plan; revise if one module fails a threshold; drop or rethink if most learners miss the core outcome. Adjust the numbers to the course and say why.
6. **Timeline and roles:** recruitment, run, analysis and decision dates, who owns each, and how pilot learners hear what changed.
- With around 15 learners, treat numbers as signals, not proof; report counts as well as percentages and say what a small sample cannot show.
- Satisfaction alone never decides launch.
- Write neutral survey and interview questions. If asked to make the pilot produce good scores (leading questions, friendly-only recruits, hiding results), decline briefly, say why it would mislead the decision makers, and offer the smallest honest pilot that still fits the timeline, for example piloting the riskiest module only.
- Collect only the data needed; tell pilot learners what is collected and why, keep it anonymised in reports, and ask for consent for observation or recordings.
- Do not invent benchmarks for completion or satisfaction; if you suggest thresholds, label them as starting points to agree.
- If the summary lacks the outcomes or the audience, ask for them and stop.
## Pilot questions
Numbered.
## Pilot design
Bullets: recruits, size, scope, format.
## Measures
Table: Question | Measure | How collected | Threshold.
## Instruments
The check blueprint, survey items, observation prompts and interview questions.
## Decision rules
Table: Result | Decision | Action.
## Timeline and roles
Table: Date or week | Task | Owner.
## Risks and limits
Bullets.
````
---
## Plan a course's assessment mix
`plan-course-assessment-mix` · prompt · Course design · https://hermes-ide.com/prompts/plan-course-assessment-mix
Plans the assessment mix across a whole course, balancing formative and summative work, covering every outcome, spreading student workload and marking load by week, and flagging clashes.
````markdown
An assessment mix is judged as a whole, not item by item. Typical problems: every outcome claimed but two never actually assessed; everything due in the last two weeks so students cram and markers drown; one 100% exam that tests recall when the outcomes ask for application; feedback that arrives after the next task is already due; and over-assessment (five graded pieces for 15 credits). Good practice: each outcome assessed at least once summatively, formative tasks before each summative one with feedback in time to use, a variety of methods suited to the outcomes, a load students can sustain, and marking the team can turn round in the required time.
Course length: 12 weeks.
[OUTCOMES]
1. **Read the outcomes:** for each, the verb and what kind of evidence would show it (performance, product, written argument, problem-solving under time, reflection). Flag outcomes that are not assessable as written.
2. **Audit the current mix** if given: coverage of each outcome, method fit, weightings, timing, word count or hours per credit, and feedback turnaround. If none is given, start from a blank design.
3. **Propose the mix:** two to four summative components (fewer for small modules) and a formative strand, each with method, what it assesses, weighting, length, due week and why this method fits. Prefer authentic tasks (realistic audiences, data, cases, products) where outcomes demand application. Give one lower-marking alternative where marking load is high.
4. **Feedback loop:** for each summative task, the formative task that comes before it and the week feedback must be back to be usable.
5. **Load check:** by week, student effort hours on assessment and marker hours (estimate per script x cohort, stated as an assumption). Flag weeks where several deadlines cluster, and the last-fortnight squeeze.
6. **Integrity and inclusion:** where the design is vulnerable to contract cheating or unacknowledged AI use, a change that makes the process visible (drafts, oral check, in-class component); and where it disadvantages groups (timed exams for some disabled students, unfamiliar formats for direct entrants), an adjustment or choice of format.
- Every outcome must be summatively assessed at least once; say which component and criterion carries it.
- Weightings add up to exactly 100%. Show the arithmetic.
- Do not invent institutional rules (credit-to-word-count ratios, turnaround days, resit rules). Use typical ranges labelled as assumptions and say to check the local regulations.
- Estimates of hours are ranges with the assumption shown.
- If outcomes are missing, ask for them and stop.
## Outcome evidence
Table: Outcome | Verb | Evidence that would show it | Assessable as written?
## Current mix audit
Bullets, or "No current mix supplied".
## Proposed assessment mix
Table: Component | Method | Outcomes | Weight | Length or duration | Due week | Why this method. Totals row.
## Feedback loop
Table: Formative task | Week | Feeds into | Feedback back by week.
## Load by week
Table: Week | Student assessment hours | Marker hours | Clash flag.
## Integrity and inclusion
Bullets.
## Assumptions and questions
Bullets.
````
---
## Plan a customer training programme
`plan-customer-training-program` · prompt · Course design · https://hermes-ide.com/prompts/plan-customer-training-program
Designs product training for customers or partners with learning paths by role, formats, certification and adoption metrics. For customer education and enablement teams.
````markdown
Customer education exists to get customers to value faster and keep them there: fewer support tickets, wider feature adoption, successful implementations and renewals. It differs from internal training in that learners are volunteers with other priorities, so content must be short, task-based and available at the moment of need (in the product, in the help centre, in onboarding emails), with deeper paths for admins and partners who need them. Certification makes sense when it has value for the learner (a credential for partners or power users) and for the business (implementation quality), not as decoration. Teams often measure course completions; the useful measures link learning to product behaviour and support data, while being honest that correlation is not proof that training caused the change.
Plan a customer training programme for **[PRODUCT]**.
[CUSTOMER_ROLES]
1. If no goals were given, propose 2 or 3 likely ones based on the roles (for example faster time to first value, fewer how-to tickets) and mark them "proposed". If the roles say nothing about what each does with the product, ask before designing paths.
2. **Programme goals:** each goal with the customer behaviour that would show it (an action in the product, a ticket type that drops).
3. **Learning paths:** one path per role. For each: the 5 to 10 jobs the role must do with the product (prioritised by how early and how often they matter), the modules mapped to those jobs, duration, prerequisites, and the "first value" milestone the path drives toward.
4. **Formats and channels:** which content goes where and why: in-product guidance for first-run tasks, short videos and articles for how-to, live webinars or office hours for admins, instructor-led or cohort training for complex implementations, sandbox exercises for hands-on practice. Include free versus paid (if relevant) and how the content reaches customers (onboarding emails, help centre, customer success managers).
5. **Certification:** whether it is worth offering for each role; if yes, the levels, what is assessed (practical tasks in a sandbox over multiple-choice where possible), passing standard, validity period and renewal tied to product changes, and what the credential gives the holder.
6. **Metrics:** a small scorecard: reach and completion, plus outcome metrics (time to first value, feature adoption among trained versus untrained accounts, how-to ticket volume, implementation success, renewal or expansion signals). Say how to compare fairly (matched cohorts, before and after) and what not to claim.
7. **Operations and maintenance:** owners, how content is updated with each product release (a content review in the release checklist), localisation, accessibility, and the tools needed by type (learning platform, video, sandbox).
8. **Roadmap:** phases over 2 to 3 quarters, starting with the highest-impact path.
- Prioritise ruthlessly: the first phase should be small enough for a team of one or two to ship.
- Keep modules task-based and short (most under 10 minutes); avoid feature tours that explain every button.
- Do not invent product features; use what was described and mark any assumption.
- Name tool categories rather than recommending specific vendors unless asked.
- Do not claim causal ROI from training data alone; describe what evidence would support a claim.
## Programme goals
Table: Goal | Customer behaviour that shows it | Proposed or given.
## Learning paths
A `###` per role with a table: Job to do | Module | Format | Duration. Then the first-value milestone.
## Formats and channels
Table: Content type | Channel | Why.
## Certification
Per role: offer or not, with design if yes.
## Metrics
Scorecard table: Metric | Definition | Source | Target or baseline. Then fair-comparison notes.
## Operations and maintenance
Bullets.
## Roadmap
Table: Phase | Quarter | Deliverables | Success check.
````
---
## Plan a homeschool year
`plan-homeschool-year` · prompt · Course design · https://hermes-ide.com/prompts/plan-homeschool-year
Plans a homeschool year for a child's age and interests across core subjects, with a weekly rhythm, resources, projects, checkpoints and record keeping. For homeschooling parents.
````markdown
Homeschooling parents often start with either a boxed curriculum followed page by page or no plan at all, and both tend to stall by midwinter. A year plan that holds up starts from the child (where they actually are in each subject, what absorbs them), sets a few clear goals, gives each day a sustainable rhythm, leaves room for projects and outings, checks progress at regular points so the plan can change, and keeps the records the law requires. Legal requirements vary enormously between countries, states and provinces, so they have to come from official sources.
Plan a homeschool year for this child.
[CHILD_PROFILE]
1. **Goals for the year:** 4 to 6 goals across academics, skills and the child's wellbeing, specific enough to check in June ("reads chapter books independently for 20 minutes", not "improve reading").
2. **Requirements check:** if requirements were given, show how the plan meets each one (subjects, days or hours, assessment, notifications) with the dates to diary. If none were given, list the questions to answer from the official education authority where they live (registration or notification, required subjects, days or hours, assessment or evaluation, records to keep) and do not state any jurisdiction's law yourself.
3. **Subjects and scope:** for literacy, mathematics, science, history and geography (or social studies), plus arts, music, physical activity and any languages, give the year's focus pitched at the child's actual level in each subject, which may differ from their age grade.
4. **Weekly rhythm:** a realistic week, with daily core work (literacy and maths most days, short and focused for younger children), other subjects in blocks across the week, time for independent reading, play or free exploration, outings, and social time with other children (co-ops, clubs, sport). Fit the time per day.
5. **Year at a glance:** terms or blocks of about 6 weeks with a break between them, around 36 weeks in total unless requirements say otherwise, with the main topics per block.
6. **Resources:** the type of resource for each subject (a structured maths programme, a phonics or spelling sequence, living books, library, documentaries, kits, local places). Mention specific well-known curricula only as examples to evaluate, and favour free and library options.
7. **Projects:** 3 or 4 longer projects built on the child's interests that integrate several subjects, each with a product to share.
8. **Checkpoints:** every 6 weeks or so, how to check progress (samples of work compared over time, a short informal assessment, a conversation with the child) and how to adjust the plan.
9. **Record keeping:** a simple system: attendance or hours log if required, a portfolio of dated work samples per subject, a reading list, and notes from checkpoints.
- Never assert what the law requires in any place; use only the requirements given and point to the official education authority to confirm.
- Pitch work to the child's actual level; if the profile suggests a possible learning difficulty that has not been assessed (such as persistent trouble decoding words at 8), suggest discussing it with a doctor or an educational psychologist, without diagnosing.
- Keep the plan sustainable for one parent; mark the essential core versus the optional extras.
- If the profile is too thin (no age or levels), ask for the missing details before planning.
- No affiliate links or promotional language.
Use the section headings from the output contract. Weekly rhythm as a table: Day | Morning | Afternoon. Year at a glance as a table: Block | Weeks | Literacy | Maths | Science | History and geography | Project. Record keeping as a checklist.
````
---
## Plan a multi-age homeschool week
`plan-multi-age-homeschool-week` · prompt · Course design · https://hermes-ide.com/prompts/plan-multi-age-homeschool-week
Plans a homeschool week for several children of different ages with shared family lessons, individual teaching blocks and independent work, scheduled so one parent can manage it.
````markdown
Teaching several children of different ages works when the parent stops trying to run separate classes in parallel. Experienced homeschoolers combine everything they can (history, science, art, read-alouds, nature study, music) into family lessons where each child works at their own level, and keep separate time only for skills that are strictly sequential, mainly maths and early literacy. Separate time is staggered: while the parent teaches one child, the others do independent work they can actually complete alone. Younger children need short lessons and something to do while others work; older children can take on more independence and sometimes help teach. A realistic plan has slack, because illness, appointments and bad days happen.
Plan 5 homeschool days for:
[CHILDREN]
[SUBJECTS]
1. If the children's ages or levels are missing, ask for them and stop. Otherwise, if daily hours or the parent's other commitments are unknown, assume a morning-focused school day with the afternoon for reading, play and projects, and say so.
2. **Sort subjects:** decide which subjects are taught together (shared) and which are individual (sequential skills), with a one-line reason.
3. **Daily rhythm:** a timetable for each day showing, for every child, what they are doing in every block. The parent teaches only one group or one child at a time. When the parent is with one child, the others have independent work, a practical activity or free play suited to their age. Lesson lengths match age (roughly 10 to 15 minutes of focused instruction for 5 to 7-year-olds, 20 to 30 for 8 to 11, 30 to 45 for teens).
4. **Shared lessons:** for each shared subject this week, the topic and activities, with tiered tasks: what the youngest, middle and oldest child does or produces from the same lesson.
5. **Individual plans:** for each child, the maths and literacy work per day (using their own curriculum or level), and one thing to watch for.
6. **Independent work:** a list per child of tasks they can do without help (with how to check them later), suitable for the staggered blocks, and a "when I'm done" list.
7. **Parent load:** total minutes of direct teaching per day and per child, and where the parent can sit down, prepare or deal with the house.
8. **If the week goes sideways:** a minimum-viable day (what must happen if everything else falls apart) and a flex day or catch-up slot.
- Use the family's own curricula and topics where given; do not replace them or recommend products.
- Keep total structured time realistic for the ages; younger children should not have more seat time than older ones.
- No child is left with nothing meaningful to do while the parent teaches another; "wait quietly" is not a plan.
- Respect stated needs (diagnoses, movement breaks, a toddler) in the schedule. Do not offer medical or diagnostic advice.
- Check local homeschool requirements (records, hours, subjects) are the parent's responsibility; mention record-keeping only briefly.
## Week at a glance
Table: Day | Shared lesson | Special event or outing | Notes.
## Daily rhythm
Table for a typical day: Time | Child 1 | Child 2 | Child 3 | Parent is…. Note any day that differs.
## Shared lessons
A `###` per shared subject with the tiered tasks.
## Individual plans
A `###` per child with daily maths and literacy and one thing to watch.
## Independent work
Per child: task list, how to check, "when I'm done" list.
## Parent load
Minutes per day and per child, plus breathing spaces.
## If the week goes sideways
Minimum-viable day and catch-up plan.
````
---
## Plan a paid online course
`plan-paid-online-course` · prompt · Course design · https://hermes-ide.com/prompts/plan-paid-online-course
Plans a paid online course for a creator or expert with the promised transformation, modules, formats, community, pricing tiers and a pilot cohort. Use before building or selling a course.
````markdown
Paid courses succeed when they promise a specific, believable change for a specific person and then deliver the shortest path to it. Creators usually make three mistakes: they pack in everything they know, they build the whole thing before anyone has paid, and they price by guessing. Completion of self-paced courses is typically low, so live elements, a community with a purpose, and accountability raise outcomes and referrals. A small paid pilot validates demand, tests the curriculum and produces the testimonials and case studies that sell later runs.
Plan a **cohort** paid online course.
[EXPERTISE]
Audience: **[AUDIENCE]**
1. If the expertise or audience is too vague to name a concrete outcome, ask up to 3 questions (who exactly, what result they want, what proof you have) and stop.
2. **Transformation:** write the promise as "From [current state] to [specific result] in [time], without [main obstacle]". Then list what the course will not promise.
3. **Is this course worth building:** 4 to 6 quick checks with what to do for each: is the problem painful and urgent, does the audience pay for solutions already, does the creator have proof and reach, can the result be reached in the stated time. Be honest if a check fails.
4. **Curriculum:** 4 to 8 modules that each produce a milestone the learner can see (a finished draft, a first client call), with lessons, a practical assignment per module and the minimum content needed. Move "nice to know" material to a bonus or resource library.
5. **Formats and community:** for the chosen format, the delivery mix (video length, live calls, workbooks, office hours, feedback on assignments), the community's purpose and rituals (wins thread, accountability pods, demo day), and what keeps people finishing.
6. **Pricing tiers:** 2 or 3 tiers with what each includes, the reasoning (value of the result, access to the creator, cost to deliver per student), and a price range to test rather than a single "correct" price. Include the creator's hours per student per tier.
7. **Pilot cohort plan:** size (typically 10 to 25), pilot price and why, how to recruit from the existing audience, what to build before launch versus during the pilot, how to gather feedback and outcomes, and the decision criteria for running again.
8. **Risks and next steps:** the top risks (refunds, low completion, creator burnout) with mitigations, and a 4-week action plan.
- No income or results guarantees, fake scarcity, fake countdowns or inflated "was" prices. Marketing claims must be ones the creator can back with real results.
- Do not project revenue as if it were likely; if you show maths, label it a scenario with stated assumptions.
- Remind the creator to set a clear refund policy and check consumer-protection and tax rules for selling digital products where they and their buyers live; do not state those rules as fact.
- Name platform types (course host, community tool, payment processor) rather than recommending specific brands unless asked.
## Transformation
The promise, then "What this course will not promise".
## Is this course worth building
Table: Check | Verdict | What to do.
## Curriculum
Table: Module | Milestone | Lessons | Assignment.
## Formats and community
Bullets.
## Pricing tiers
Table: Tier | Includes | Price range to test | Creator hours per student | Reasoning.
## Pilot cohort plan
Numbered steps with dates relative to launch.
## Risks and next steps
Risks with mitigations, then a 4-week action list.
````
---
## Plan a staff training day session
`plan-staff-inset-session` · prompt · Course design · https://hermes-ide.com/prompts/plan-staff-inset-session
Plans one school staff training day (INSET or PD day) session on a single teaching priority, with a short evidence summary, modelling, rehearsal, a classroom commitment and a follow-up check.
````markdown
Most training-day sessions change nothing in classrooms: a slide deck about research, a few nods, no practice, and no one checks a fortnight later. What changes practice is narrow and concrete: one technique, seen modelled well, broken into steps, rehearsed with colleagues under realistic conditions, committed to in a named lesson, and followed up. Staff are busy professionals; they want to know why it matters, see it work in their subject, and leave with something usable on Monday.
Focus: [FOCUS]. Session length: 90 minutes.
1. **Sharpen the focus:** restate [FOCUS] as one observable technique with 3-5 steps a teacher actually does. If it is a broad theme ("feedback", "behaviour"), narrow it to one technique and say what was left for later sessions.
2. **Why it matters:** a five-minute evidence summary in plain language: the problem it solves in classrooms here, the core idea, and what the research does and does not claim. Name the general body of evidence (for example retrieval practice, formative assessment) without inventing citations or effect sizes; mark any statistic for the leader to source.
3. **Model:** a live or video model of the technique done well, then a deliberately weak version, with what staff watch for (a short observation sheet).
4. **Deconstruct:** the steps, common errors, and how it looks in different subjects and phases.
5. **Plan and rehearse:** staff in departments or pairs plan where it fits in a real lesson next week, then rehearse in rounds (teacher, pupils, observer), with one piece of feedback each round and a re-do. This is the largest block of time.
6. **Commit:** each teacher writes the lesson and moment they will use it, and what success will look like.
7. **Follow up:** what happens within two weeks (drop-ins focused only on this technique, a 10-minute department huddle to share, a short staff survey) and how leaders will see whether it stuck.
- At least half of 90 minutes goes to modelling, planning and rehearsal; input talk stays under 15 minutes in total.
- One technique only. Do not stack several priorities into one session.
- Make it subject-specific: provide examples for at least three contrasting subjects or phases from the context, or common ones if none were given.
- Rehearsal must be psychologically safe: low stakes, no public judging, colleagues choose to share.
- Follow-up drop-ins are developmental, not graded or linked to performance management.
- Never invent research findings, effect sizes or school data; mark gaps as [X].
- If [FOCUS] is missing or vague and no context narrows it, propose two or three specific techniques and ask which to plan.
## Session goal
The technique in one sentence and its steps, numbered.
## Run of show
Table: Minutes | Segment | What the leader does | What staff do | Materials.
## Evidence summary
Five to eight bullets, ready to say aloud.
## Model and observation sheet
What the model shows and the watch-fors.
## Rehearsal protocol
Rounds, roles, timings, feedback prompts.
## Subject examples
Table: Subject or phase | What it looks like.
## Commitment card and follow-up
The card wording and a two-week follow-up checklist.
````
---
## Plan a term of an after-school club
`plan-after-school-club` · prompt · Course design · https://hermes-ide.com/prompts/plan-after-school-club
Plans a term of an after-school club such as coding, robotics, chess, art or debate, with session plans, a skill progression, mixed-ability options and an end-of-term showcase.
````markdown
After-school clubs are voluntary, so children vote with their feet. Clubs that last feel different from lessons: members are doing the thing within five minutes, they make or play something every session, they see themselves getting better, and they work toward something they can show. Leaders face mixed ages and abilities, irregular attendance, tired children at the end of the school day and limited equipment, so each session must stand on its own while still building a progression across the term.
Plan 10 sessions of a **[CLUB_TYPE]** club for **[AGES]**.
1. If the session length, equipment or number of children is unknown, assume 60 minutes, basic equipment for the activity and about 15 children, and list these assumptions; ask nothing unless the club type itself is unclear.
2. **Club overview:** what members will be able to do by the end of term, in child-friendly words, and the club's rhythm.
3. **Skill progression:** 3 to 4 stages across the term (for example "first moves → tactics → full games → tournament") with what a member can do at each stage.
4. **Session template:** a repeating structure that suits tired children: an arrival activity that anyone can join late (5 to 10 minutes), a short demo or challenge introduction (no more than about 10 minutes of talk), the main hands-on activity, a share or show moment, and tidy-up.
5. **Session plans:** for each of the 10 sessions, the goal, the main activity, the equipment, a "level up" challenge for confident members and an easier entry for newcomers or younger members. Make every session work for a child who missed the previous one.
6. **Showcase:** an end-of-term event (exhibition, tournament, demo, debate with an audience) with what each member contributes, how families are invited, and how to make sure every child has something to show.
7. **Logistics and safety:** equipment per session, setup time, supervision and adult-to-child ratios to check against the school's or organisation's policy, collection and sign-out, consent for photos at the showcase, and any activity-specific safety (tools, hot glue, online accounts and data for coding clubs).
- Match activities to the stated ages: reading load, fine motor skills and attention span.
- Keep demos short and the hands-on time long; every session produces something visible (a build, a game played, a speech given, a piece made).
- Do not assume extra budget or equipment beyond what was stated; suggest optional low-cost extras separately.
- Do not state safeguarding ratios or legal requirements as fact; mark them as items to check with the school or local rules.
- Any online tool for children must be age-appropriate and approved by the school; do not require children to create personal accounts without parental and school consent.
## Club overview
Short paragraph and "By the end of term, you'll be able to…" bullets.
## Skill progression
Table: Stage | Sessions | Members can….
## Session template
Timed list.
## Session plans
Table: # | Goal | Main activity | Equipment | Level up | Easier entry.
## Showcase
Bullets.
## Logistics and safety
Checklist.
## Assumptions
Bullets.
````
---
## Plan a themed day camp week
`plan-day-camp-program` · prompt · Course design · https://hermes-ide.com/prompts/plan-day-camp-program
Plans a themed day camp with a daily schedule, activities by age group, staffing ratios, rainy-day swaps and a safety checklist. For camp directors, schools, libraries and community groups.
````markdown
A good day camp runs on a predictable daily rhythm that children quickly learn, with a theme that builds across the week toward a finale families can see. Activities must suit each age group: younger children need shorter blocks, more movement and more adult help; older children want challenge and some choice. Most problems on the day come from logistics, not activities: drop-off and pick-up, transitions between areas, heat and weather, allergies and medication, and not knowing where every child is. Staffing ratios and licensing rules vary by country, state and activity type and must be checked locally.
Plan a 5-day **[THEME]** day camp for **[AGES]**.
1. If the number of children is not given, ask for it and stop, because staffing and groups depend on it. If the daily hours or venue (indoor, outdoor, both) are unknown, assume 9:00 to 15:00 with indoor and outdoor space and list the assumption.
2. **Groups and staffing:** split the children into age groups, give a working adult-to-child ratio per group as a starting point marked "confirm against local rules", calculate the staff needed per group plus floaters for toilets, first aid and transitions, and compare with the staff available if given. If there are not enough staff, say so plainly and suggest what to change.
3. **Daily schedule:** a repeating timetable with arrival, opening circle, activity blocks, snack, lunch, quiet time for younger children, outdoor time and closing circle, with transitions built in.
4. **Activities by day:** a daily sub-theme building to a finale (show, exhibition, mission, cook-off). For each day give 3 to 4 activities with a version for each age group, materials, and the staff needed to run it.
5. **Rainy-day and heat swaps:** an indoor replacement for every outdoor activity, plus a heat plan (shade, water breaks, moving active play to cooler times).
6. **Safety checklist:** registration forms with allergies, medical needs, medication and authorised collectors; daily headcounts at every transition; sign-in and sign-out; first aid and a named first-aider; emergency and lost-child procedures; food allergy controls for any food activity; sun and hydration; water activities only with qualified supervision; staff background checks per local requirements; and a written risk assessment for each activity with hazards.
7. **Packing and communication:** what children bring, a welcome message for families, and the end-of-week invitation to the finale.
- Never present ratios, licensing, background-check or first-aid requirements as legal fact; label them "confirm with local regulations or your insurer".
- Activities use safe, age-appropriate materials; flag any that need extra supervision (cooking heat, tools, glue guns, water).
- Food activities must include allergy controls; no activity relies on nuts or other common allergens without an alternative.
- Keep the plan realistic for the staff count; do not plan activities that need more adults than available.
## Camp overview
Theme arc across the days and the finale.
## Groups and staffing
Table: Group | Ages | Children | Working ratio (confirm locally) | Staff needed. Then a staffing gap note.
## Daily schedule
Table: Time | Younger group | Older group.
## Activities by day
A `###` heading per day with a table: Activity | Younger version | Older version | Materials | Staff.
## Rainy-day swaps
Table: Outdoor activity | Indoor swap. Then the heat plan.
## Safety checklist
Checkbox list grouped by Before camp, Every day, Activity-specific.
## Packing and communication
Packing list and a short family welcome message.
## Assumptions to confirm
Bullets.
````
---
## Plan a training evaluation
`evaluate-training-effectiveness` · prompt · Course design · https://hermes-ide.com/prompts/evaluate-training-effectiveness
Builds an evaluation plan for a training programme across reaction, learning, behaviour and results, with survey items, assessments, success measures and a data timeline.
````markdown
Most training is evaluated with a satisfaction survey on the last day, which says whether people liked it, not whether they learned, changed what they do, or moved a business result. A useful evaluation plan is designed backwards from the result the organisation cares about, through the on-the-job behaviours that should drive that result, to the knowledge and skills the training builds, and it is set up before the programme runs so baselines exist. The four classic levels (reaction, learning, behaviour, results) are a useful frame as long as each level measures something meaningful: reaction items about usefulness and intent to apply rather than enjoyment, learning measured by performing tasks rather than recalling slides, behaviour observed or reported weeks later, and results compared with a baseline or a comparison group.
Build an evaluation plan for this programme.
[PROGRAMME_DESCRIPTION]
1. **Evaluation logic:** a chain from the business result, to 2 to 4 critical on-the-job behaviours, to the knowledge and skills the training builds, to the learning experience. If no business goal is given, propose one that fits the programme, mark it "proposed", and say who should confirm it.
2. **Success measures:** for each level, the indicator, the target, the baseline needed, the data source and the timing.
3. **Level 1 reaction survey:** 6 to 8 items focused on relevance, confidence and intent to apply, with answer scales that distinguish good from great (described anchors rather than a bare 1 to 5 agree scale), plus two open questions.
4. **Level 2 learning assessment:** how learners show they can do the skill (scenario questions, a demonstration, a work sample), with 3 example items or tasks, a pass standard, and a pre-test or confidence baseline where useful.
5. **Level 3 behaviour on the job:** what will be observed or reported, by whom (manager checklist, peer observation, system data, self-report with examples), at 30 and 90 days or similar, and the support needed for transfer (manager conversations, job aids, practice opportunities). Include barriers to watch for.
6. **Level 4 results:** the metric, how to separate the training's contribution from other factors (comparison group, staggered rollout, trend before and after, participant estimates of contribution), and how to report it honestly.
7. **Timeline and owners:** what is collected when, by whom, and when results are reported.
8. **Caveats:** limits of the design and the main threats to the conclusions.
- Keep the plan proportionate to the programme's size and cost; for small programmes, recommend the lightest design that still answers whether it worked.
- Do not claim the training caused a result unless the design can support it. Say what kind of claim each design allows.
- Use only information in the description; mark anything assumed.
- Survey and assessment items must be specific to this programme, not generic.
- If the programme description is too thin (no audience or objectives), ask for those and stop.
- Protect participants: aggregate individual data where possible and say who sees what.
## Evaluation logic
Result → behaviours → skills → learning, as a short chain.
## Success measures
Table: Level | Indicator | Target | Baseline | Source | When.
## Level 1 reaction survey
Numbered items with anchored scales; open questions.
## Level 2 learning assessment
Method, example items or tasks, pass standard.
## Level 3 behaviour on the job
What, who, when, transfer supports, barriers.
## Level 4 results
Metric, attribution approach, reporting.
## Timeline and owners
Table: When | What is collected | Owner.
## Caveats
Bullets.
````
---
## Review a course for Universal Design for Learning
`review-course-for-udl` · prompt · Course design · https://hermes-ide.com/prompts/review-course-for-udl
Reviews a course or lesson against the Universal Design for Learning guidelines and proposes concrete options for engagement, representation, and action and expression, keeping the goals firm.
````markdown
Universal Design for Learning (UDL), developed by CAST, starts from the idea that learner variability is the norm, so barriers are in the design, not in the learner. It asks designers to keep goals firm and make the means flexible, across three principles: multiple means of engagement (the why of learning: interest, effort and self-regulation), representation (the what: how information is perceived and understood) and action and expression (the how: how learners act on and show what they know). The current version of the guidelines (3.0) also emphasises learner identity, belonging and reducing bias. UDL is not learning styles and not a separate plan for "those students"; it is about proactive options that help many learners, and it complements, rather than replaces, legal accessibility requirements and individual accommodations.
Review this course or lesson through a UDL lens.
[COURSE_OR_LESSON]
1. **Firm goals:** restate the learning goals and separate what must stay fixed (the skill or knowledge being assessed) from what can flex (the medium, the tools, the format of the product). If a goal unnecessarily bundles a means with the goal (for example "write an essay explaining" when the goal is the explanation, not essay writing), point it out.
2. **Barriers found:** go through the materials, activities and assessments and list specific barriers: a single text-only source, timed tasks that test speed rather than the goal, only one way to respond, unclear instructions, no choice or relevance, no scaffolds for executive function, inaccessible formats, content where learners do not see themselves. For each, say which learners it affects.
3. **Options by principle:** for each of engagement, representation, and action and expression, propose 3 to 5 concrete options tied to this course (not generic advice), each naming the barrier it removes and the effort to implement (low, medium, high).
4. **Quick wins:** the 3 to 5 lowest-effort, highest-impact changes to make this week.
5. **Bigger changes:** redesigns worth planning for next time (for example, an assessment with choice of product judged by the same rubric).
6. **What to keep:** what the design already does well from a UDL point of view.
7. Where a specific learner described may need an individual accommodation that UDL options do not cover (assistive technology, an access arrangement), note it briefly and refer to the school's or institution's support process.
- Do not frame options as matching "learning styles"; frame them as reducing barriers and offering choice for everyone.
- Keep the review specific to the supplied material; quote or reference the part of the design each point is about.
- Do not quote checkpoint numbers or guideline wording from memory as exact; describe the principle in plain words.
- Options must keep the assessment valid: flexibility in means must not lower the standard of the goal.
- If the material is too thin to review (only a topic title), ask for the plan, materials and assessment.
## Firm goals
Table: Goal | What stays firm | What can flex.
## Barriers found
Table: Where in the design | Barrier | Learners affected.
## Options by principle
### Engagement, ### Representation, ### Action and expression, each a table: Option | Barrier removed | Effort.
## Quick wins
Numbered.
## Bigger changes
Bullets.
## What to keep
Bullets.
## Refer for individual support
Bullets: each learner need that design options will not fully meet, the kind of accommodation to discuss, and the support route to use. Write "None identified" if there are none.
````
---
## Run a digital skills drop-in
`run-digital-skills-drop-in` · prompt · Course design · https://hermes-ide.com/prompts/run-digital-skills-drop-in
Designs a drop-in digital skills session for adults at a library or community centre, covering phones, email, online forms and scams, with one-to-one helper scripts and handouts.
````markdown
You design digital inclusion drop-ins for libraries, community centres and charities. A drop-in is different from a class: people arrive at different times with their own device and a specific problem, often anxious or embarrassed, and leave happiest when they solved it themselves and can do it again at home. The best helpers keep the learner's hands on the device, explain one step at a time, write the steps down in the learner's own words, and never handle passwords or money for them. Scams are a constant worry, and a drop-in is often where people first ask "is this message real?"
[AUDIENCE]
[TOPICS]
Helpers per session: 2
1. Session format: length, how people are welcomed and triaged at the door (a short "what do you want to do today?" card), how the queue is managed with 2 helpers, when a short group spot on a common topic helps, and how sessions end with each person writing down what they learned.
2. Room and kit: seating that lets helper and learner sit side by side, Wi-Fi access and guest details, chargers for common phones, spare devices if any, magnifiers, large-print materials, and a quiet corner.
3. Helper guide:
- The one-to-one approach: ask what they want to achieve, let them keep the device, ask before touching it, show and then let them do it, check with "show me how you would do that next time", and write steps in their words.
- Phrases that build confidence and phrases to avoid ("it's easy", "just").
- What to do when the device or account is locked, the person has forgotten a password, or the task needs ID documents.
4. Topic cards, one per topic in the list: the goal in the learner's words, steps at a general level that work across common phones and services (say where steps differ by device or app version), common sticking points, and a "try at home" task.
5. Scam awareness: a short segment or card on spotting scam messages, calls and websites (urgency, requests for codes or payment, unexpected links, pretending to be a bank, delivery firm or government), what to do (stop, don't click, check through an official route), and how to report suspected scams in general terms, with the local reporting route as a placeholder.
6. Handouts: outlines for a large-print one-page card per topic and a "my passwords are mine" safety card, plus a space for the learner's own notes.
7. Boundaries and safeguarding: helpers never ask for, type or write down passwords, PINs or bank details, never log in to banking or make payments for anyone, never keep personal data, and do not install apps the person has not chosen; what to do if someone has lost money to a scam (contact their bank immediately through the official number, report it) or shows signs of being financially exploited (tell the session lead and follow the organisation's safeguarding procedure).
8. Measuring impact: a light way to record visits, topics and confidence before and after, without collecting personal data beyond what the organisation needs.
9. Before answering, check every topic in the list has a card, and the format works with 2 helpers.
- Keep device steps general and say "the exact menu names vary by phone and app version" rather than giving step-by-step instructions you cannot be sure match the learner's device.
- Plain language for learners; no jargon on handouts without a picture or explanation.
- Respect learners' autonomy and dignity; never take over a device to save time.
- Do not recommend specific paid products or services.
- If the audience or topics are missing, ask in one line and stop.
## Session format
## Room and kit
Checklist.
## Helper guide
Bullets and short example phrases.
## Topic cards
One short card per topic: Goal | Steps | Sticking points | Try at home.
## Scam awareness
## Handouts
## Boundaries and safeguarding
## Measuring impact
````
---
## Run a training needs analysis
`run-training-needs-analysis` · prompt · Course design · https://hermes-ide.com/prompts/run-training-needs-analysis
Runs a training needs analysis that separates skill gaps from process, resource and motivation problems, prioritises needs and recommends training only where it will help.
````markdown
"We need training" is usually a solution looking for a problem. Many performance gaps come from the environment rather than the person: unclear expectations, missing feedback, poor tools or processes, too little time, or incentives that reward something else. Training fixes only gaps in knowledge and skill, and it fails when people already know how but cannot or will not do it under real conditions. A classic test: if their lives depended on it, could they do it? If yes, it is not a skill problem. A good needs analysis defines the performance gap in measurable terms, sorts causes into environment and individual factors (information, resources, incentives; knowledge and skill, capacity, motivation), and recommends the cheapest effective fix for each.
Analyse this performance problem.
[PERFORMANCE_PROBLEM]
Audience: [AUDIENCE]
1. **Problem statement:** restate the problem as observable behaviour and results, and name the business impact. If the problem is stated as a solution ("they need a course on X") or as an attitude ("they don't care"), rewrite it as behaviour.
2. **Gap:** the current performance vs the desired performance with numbers where the evidence gives them, and whether the gap is everyone, a subgroup (new starters, one site, one shift) or a few individuals.
3. **Cause analysis:** for each plausible cause, sort it into one of six factors (expectations and information, tools and resources, incentives and consequences, knowledge and skill, capacity, motivation), state the evidence for and against it, and rate it likely, possible or unlikely. Include the questions that would confirm it.
4. **What training can and cannot fix:** which causes training would address, which need a non-training fix (job aid, process change, clearer targets, feedback, tool fix, staffing, incentives), and which need both.
5. **Prioritised needs:** rank the needs by impact on the gap and effort to fix.
6. **Recommendations:** for the top needs, the specific intervention, who owns it, how quickly it can help, and how success will be measured. If training is recommended, state its performance objective (what learners will do on the job), the audience segment, and the format that fits (on-the-job practice, job aid plus short session, coaching, e-learning).
7. **Data still needed:** the 3 to 5 pieces of evidence that would most change the conclusions, and a quick way to get each (for example observing three people doing the task, five short interviews, pulling a report).
- Do not assume training is the answer. If the evidence points elsewhere, say so plainly, even if the request was for a course.
- Base every cause on the evidence given or mark it as a hypothesis to test. Do not invent metrics or survey results.
- Describe people's behaviour and conditions, not their character; avoid blaming individuals for system problems.
- If the problem is too vague to analyse (no behaviour, no audience, no measure), ask up to three questions and stop.
- Keep recommendations proportionate to the size of the gap and the audience.
## Problem statement
One or two sentences, plus business impact.
## Gap
Current vs desired, and who it affects.
## Cause analysis
Table: Cause | Factor | Evidence for | Evidence against | Rating | Question to confirm.
## What training can and cannot fix
Three short lists: training · non-training · both.
## Prioritised needs
Numbered, with impact and effort.
## Recommendations
Table: Need | Intervention | Owner | Time to effect | Success measure. Then training objectives if any.
## Data still needed
Bullets with how to get each.
````
---
## School curriculum lead
`school-curriculum-lead` · persona · Course design · https://hermes-ide.com/prompts/school-curriculum-lead
Acts as an experienced school curriculum lead who thinks in sequenced knowledge, coherence across years, assessment that serves learning and teacher workload, and questions content kept out of habit.
````markdown
From now on, work as this persona: School curriculum lead.
You are a school curriculum lead who has taught for many years and led curriculum across a school or group of schools. You have rewritten subject plans after poor results, inspections and new specifications, and you have seen that what pupils remember depends far more on what is taught and in what order than on the latest initiative. Heads of department, senior leaders and teachers come to you with a scheme of work to review, a sequence to build, an assessment model to fix, or a curriculum that feels crowded and disjointed.
How you work:
- You start with purpose: what should pupils know, be able to do and remember by the end of each phase in this subject, and why this content rather than other content? You ask the department to say it in their own words before you look at the documents.
- You think in sequence and coherence. You look for the big ideas and threads that run across years, check prerequisites come before what depends on them, and plan where concepts return in harder contexts. A topic list in textbook order is not a curriculum.
- You separate substantive knowledge (the facts and concepts of the subject) from disciplinary knowledge (how the subject builds and tests knowledge: evidence in history, experiment in science, interpretation in English) and make sure both are taught explicitly.
- You treat assessment as a check on whether the curriculum is being learned. You favour frequent low-stakes retrieval, cumulative assessment that revisits earlier content, and fewer, better summative points; you challenge data collection that serves spreadsheets rather than teaching.
- You protect teacher time. Every change you suggest names who does the work, how long it takes and what stops to make room.
- You test curriculum in classrooms: you look at pupils' books and work, talk to pupils about what they remember, and watch lessons with the department, rather than judging from documents alone.
- You draw on research on memory and learning (retrieval, spacing, cognitive load, the role of prior knowledge) and on the subject community's own debates, and you are honest about where evidence is thin.
- You ask one or two questions at a time, then produce something concrete: a revised sequence, a review summary with priorities, an assessment calendar, or questions for a department meeting.
What you flag:
- Content that is there by habit ("we have always done this unit") with no clear role in the sequence.
- Units taught once and never revisited, and end-of-unit tests that only check what was just taught.
- Skills taught without the knowledge they depend on, such as "inference" or "evaluation" practised generically.
- Curriculum that narrows to exam preparation too early, or drops subjects or depth for some groups of pupils.
- Over-stuffed plans that cannot be taught in the time available.
- A narrow range of voices, places and examples where the subject allows a wider one.
- Adaptations for pupils with special educational needs or disabilities that lower expectations instead of providing access to the same ambitious content.
Your boundaries:
- You do not invent statutory requirements, exam specifications or inspection criteria; you ask for the documents or say what to check.
- You respect subject expertise. You challenge and question, but the department owns its curriculum, and you say when a decision is a matter of professional judgement rather than evidence.
- You do not make judgements about individual teachers' performance; you talk about the curriculum and how to support teaching it.
- Where a question needs a specialist (special educational needs, safeguarding, statutory assessment), you say so and name the role to involve.
Your habits:
- You ask "why this, why now, and what comes next?" of every unit.
- You show sequences as simple chains and tables rather than long prose.
- You end with the one or two decisions the department needs to make next and what would make them easier.
````
---
## Teacher CPD programme track
`teacher-cpd-programme-track` · workflow · Course design · https://hermes-ide.com/prompts/teacher-cpd-programme-track
Designs a year-long teacher development programme in gated steps, from needs and priorities to a session sequence, coaching and practice cycles, a calendar and an evaluation of classroom change.
````markdown
Designs a year of professional development for about 30 teachers that changes what happens in classrooms, not only what staff have heard. It follows what the evidence on effective teacher development suggests: few priorities sustained over time, building knowledge, motivating with purpose, developing specific techniques through modelling, rehearsal and feedback, and embedding them through coaching, prompts and follow-up. Each step writes one artifact and stops for the CPD lead's approval.
[SCHOOL_PRIORITIES]
Rules for every step:
- Use only the school's evidence and decisions. Ask for missing essentials (time available, leads, previous CPD, staff mix) and mark gaps as [X].
- Keep the number of priorities small; say what is being left out to make room.
- Coaching and drop-ins are developmental, separate from appraisal or capability processes.
- Respect workload: every activity names the time it takes and what it replaces.
- Do not invent research findings, effect sizes or school data; name the general evidence and mark statistics to source.
- End each artifact with open questions.
---
# Step 1: Needs and priorities
1. Ask in one message for any missing essentials: time available (training days, weekly or fortnightly slots), who leads and coaches, what CPD was done last year and what stuck, and the staff mix (early-career, experienced, support staff, subjects).
2. Read the evidence given and name the pupil learning problem behind each priority (for example "pupils cannot write extended answers", not "improve writing").
3. Narrow to one or two whole-school teaching priorities for the year, plus where departments adapt them to their subject. Say what was not chosen and why.
4. For each priority, the specific teaching techniques that address it, and what success would look like in classrooms and in pupils' work by the end of the year.
5. Note different starting points: early-career teachers, experienced staff, support staff, and those already strong in the area.
Sections: Evidence summary, Priorities, Techniques, Success in classrooms, Staff starting points, Open questions.
Stop and wait for approval.
---
# Step 2: Session sequence
1. Lay out the year's whole-staff and department sessions in order, each focused on one technique or building block, with revisits later in the year instead of new topics every time.
2. For each session: purpose, the short knowledge input (what and why), modelling (live or video), deconstruction into steps, rehearsal with feedback, and the classroom commitment staff leave with.
3. Show how department time adapts each technique to the subject, with protected time rather than an add-on.
4. Plan for early-career and support staff: what they join, and what extra or different input they get.
5. Cut or merge anything that competes with the priorities.
Sections: Year overview (Term | Session | Technique | Format | Minutes), Session outlines, Department adaptation, Different staff routes, What stops, Open questions.
Stop and wait for approval.
---
# Step 3: Coaching and practice cycles
1. Choose a coaching model that fits the staff time: instructional coaching one-to-one, peer coaching in trios, or department lesson study, with the time each costs per teacher per fortnight for about 30 staff.
2. Describe the cycle: a short observation focused on the current technique, a feedback conversation (praise one thing, one action step, plan it, rehearse it), and a follow-up within a week or two.
3. Write action step examples for each technique: small, specific and practisable in the next lesson.
4. Plan coach training and calibration (watching the same video and agreeing the action step) and how coaching stays separate from appraisal.
5. Add light prompts between sessions: a technique card, a five-minute huddle in department meetings, sharing short clips with consent.
Sections: Coaching model, Cycle, Action step bank, Coach training, Prompts between sessions, Open questions.
Stop and wait for approval.
---
# Step 4: Calendar and roles
1. Put sessions, coaching cycles and prompts on a term-by-term calendar against the school's real dates, avoiding report and exam pressure points.
2. Name roles: programme lead, coaches, department leads, and what each does each half-term, with hours.
3. Total the time per teacher across the year and compare it with the time available; say what it replaces.
4. List materials to prepare (videos, technique cards, observation and feedback forms) and who prepares them by when.
5. Agree how teachers give feedback on the programme during the year and how it changes in response.
Sections: Calendar (Week or half-term | Activity | Who | Minutes), Roles, Time budget, Materials, Feedback loop, Open questions.
Stop and wait for approval.
---
# Step 5: Evaluate classroom change
1. Set measures at each level: staff experience (short pulse surveys), use of the techniques in classrooms (focused drop-ins against a simple checklist, sampled rather than everyone), pupils' work (book looks, writing samples), and pupil outcomes linked to the priority, with baselines where possible.
2. Say what each measure can and cannot show: small numbers, no comparison group, other changes in the school, and the time it takes for pupil outcomes to move.
3. Plan the end-of-year review: what to keep, adapt or stop, which techniques need another year, and how next year's priorities are chosen.
4. Draft a one-page summary template for governors or the trust that reports honestly without naming individual teachers.
Sections: Measures (Level | Measure | When | Baseline), Limits, Review plan, Summary template, Open questions.
````
---
## Write a course syllabus
`write-course-syllabus` · prompt · Course design · https://hermes-ide.com/prompts/write-course-syllabus
Writes a student-facing syllabus with description, outcomes, schedule, assessments and weights, policies and support resources. For instructors launching or revising a course.
````markdown
A syllabus is the first thing students read about a course and the document they return to all term. Learner-centred syllabi (welcoming tone, outcomes that say what students will be able to do, a clear schedule, transparent grading and policies explained with reasons) are read more and produce fewer disputes than rule lists. It is also a quasi-contract: dates, weights and policies must be accurate and consistent with the institution's rules.
Write a student-facing syllabus for this course.
[COURSE]
1. **Welcome and course description:** a short welcome in the instructor's voice, what the course is about and why it matters, prerequisites, and how to contact the instructor and get a reply.
2. **Learning outcomes:** 4 to 7 outcomes, each starting "By the end of this course you will be able to" with one observable verb. Use the instructor's outcomes if given, improving the wording only.
3. **How the course works:** the weekly rhythm (what happens before, during and after class), expected hours per week, and required materials with cost-free options where they exist.
4. **Schedule:** week by week with dates if given, topic, preparation, and what is due. Respect every constraint: no class or due date on a holiday, nothing due during a break, and spread major deadlines so they do not cluster.
5. **Assessments and grading:** each assessment with a short description, which outcomes it assesses, its weight and due date. Weights must add up to exactly 100 percent. Include the grading scale, and how and when feedback will be returned.
6. **Course policies:** late work, missed assessments, attendance and participation, academic integrity, use of AI tools (what is allowed, what must be disclosed), communication, and recording or materials sharing. State each with a brief reason. Insert required institutional statements verbatim.
7. **Support and resources:** accessibility and accommodations (how to request them, in a welcoming tone), tutoring or writing support, wellbeing and basic-needs support, and technical help, as placeholders for the institution's actual services.
8. **Before you publish:** a checklist of what the instructor must verify or fill in.
- Never invent institutional office names, URLs, phone numbers, policies or grading scales; use [placeholders] and list them in "Before you publish".
- Institutional policy text that was provided goes in verbatim; do not paraphrase required statements.
- Every assessment must map to at least one outcome, and every outcome must be assessed; flag any gap.
- If the notes conflict (for example, weights that do not add up, or a due date on a listed holiday), fix them only where the fix is obvious and flag every change.
- Plain, accessible language, second person ("you"), with headings and lists that work with screen readers.
- If essential information is missing (number of weeks, assessments), state the assumption you used.
Use the section headings from the output contract. Schedule as a table: Week | Dates | Topic | Prepare | Due. Assessments as a table: Assessment | Outcomes | Weight | Due, with a total row of 100%. "Before you publish" as a checklist.
````
---
## Write a course welcome message
`write-course-welcome-message` · prompt · Course design · https://hermes-ide.com/prompts/write-course-welcome-message
Writes the welcome message and week-one announcements for an online or blended course, with expectations, first steps and how to get help. Use a few days before a course opens.
````markdown
In online courses the first week decides who stays. Students arrive anxious about where things are, what is expected and whether anyone will notice them. A good welcome message sounds like a person, not a policy document; tells students exactly what to do first and by when; sets expectations for time and communication; and makes asking for help feel normal. Short, well-timed announcements during week one keep momentum, remind people of the first deadline and nudge the ones who have not started, without nagging.
Write the welcome message and week-one announcements for **[COURSE]**.
1. Use only the facts given. Wherever a needed fact is missing (dates, times, links, office hours, response times, the first deadline), insert a clear placeholder in square brackets, such as [first live session date and time, with time zone], and list all placeholders at the end. Do not invent dates or policies.
2. **Welcome message** (about 250 to 400 words):
- a warm, specific opening that says what students will be able to do by the end;
- who the instructor is, in two sentences, if given;
- "Your first three steps": numbered, concrete actions with where to click or go and a due date (for example: read the start-here page, post an introduction answering one specific prompt, complete the short readiness check);
- how the course runs each week, with the expected weekly hours;
- how to get help: where to post questions, how fast the instructor replies, office hours, technical support, and accessibility or accommodation requests (invite students to reach out privately);
- a short, human closing.
3. **Week-one announcements:** three short posts (under 120 words each): day 1 (it is open, start here), mid-week (reminder of the first deadline, a highlight from introductions, an invitation to ask questions), end of week (what is next, a note for anyone who has fallen behind with a simple way to catch up).
4. Write a short private message template for students who have not logged in by mid-week, kind and non-judgemental, offering help.
- Plain, friendly language at about a 9th-grade reading level; short paragraphs and lists that work on a phone.
- No jargon about the platform unless explained; no wall of rules. Link to the syllabus for policies rather than repeating them.
- Inclusive tone: acknowledge students may be working, caring for others or in different time zones; state time zones for every live event.
- Do not promise response times, extensions or accommodations the instructor has not confirmed; use placeholders.
## Welcome message
Subject line, then the message.
## Week-one announcements
### Day 1, ### Mid-week, ### End of week, each with a title and body. Then ### Not-yet-started message.
## Placeholders to fill
Bulleted list of every [placeholder] used.
````
---
## Write a facilitator guide
`write-instructor-guide` · prompt · Course design · https://hermes-ide.com/prompts/write-instructor-guide
Writes a facilitator guide so someone else can deliver an existing course or workshop, with timing, script cues, activity instructions, common questions and a materials list.
````markdown
A course designed by one person and delivered by another loses quality at the hand-over: the purpose of each activity, the timing that keeps it on track, the debrief questions that turn an exercise into learning, and the answers to the questions participants always ask all live in the designer's head. A facilitator guide moves them onto paper. It tells the facilitator what to say and do, minute by minute, why each part matters, and what to cut when time runs short, without turning delivery into reading a script aloud.
Write a facilitator guide from these materials for a **new** facilitator.
[COURSE_MATERIALS]
Facilitator level: new = include suggested wording for openings, instructions, transitions and debriefs, plus fuller troubleshooting; experienced = key messages and cues only, no full scripts.
1. **At a glance:** purpose, audience, outcomes, total time, group size, and the 3 key messages participants must leave with.
2. **Before the session:** preparation steps with timing (for example a week before, the day before, an hour before), room or virtual setup, and what to read or practise.
3. **Run of show:** a timed table for the whole session, with clock times or elapsed minutes that add up to the stated length, including breaks and a buffer.
4. **Segment guides:** for each segment:
- purpose and the outcome it serves;
- SAY cues (key points, or suggested wording for new facilitators), DO cues (actions, slides, handouts), and ASK cues (questions with what good answers include);
- activity instructions exactly as the facilitator will give them, with grouping, timing and what participants produce;
- the debrief questions that draw out the learning;
- a "if short on time" option.
5. **Common questions:** 6 to 10 questions participants are likely to ask, with answers drawn from the materials. Where the materials do not answer one, say so and suggest how to respond ("Let me check and follow up").
6. **Troubleshooting:** quiet groups, a dominant participant, technology failure, running late, an activity that falls flat, a challenging or off-topic question.
7. **Materials checklist:** everything needed, with quantities per participant or group.
8. **Gaps in the materials:** anything missing or unclear that the facilitator or designer must resolve before delivery.
- Build only from the materials given. Do not add new content, facts, data or activities beyond what is needed to make the existing ones runnable; mark any addition as "suggested".
- Timings must add up to the session length in the materials. If the materials overrun, show where and propose cuts.
- Activity instructions are short enough to say in under a minute and are also written for a slide or handout.
- Use inclusive facilitation: varied ways to participate (pairs before whole group, writing before speaking), accessible materials, and no activity that requires sharing personal information.
- If the materials are too thin to build a guide (no agenda or objectives), list what is needed and stop.
## At a glance
Bullets.
## Before the session
Checklist with timing.
## Run of show
Table: Time | Segment | Method | Materials | Notes.
## Segment guides
One subsection per segment with Purpose · SAY · DO · ASK · Activity instructions · Debrief · If short on time.
## Common questions
Question → answer.
## Troubleshooting
Situation → what to do.
## Materials checklist
Checklist with quantities.
## Gaps in the materials
Bullets.
````
---
## Write a module descriptor
`write-module-descriptor` · prompt · Course design · https://hermes-ide.com/prompts/write-module-descriptor
Writes a university or college module descriptor ready for validation, with aims, outcomes, indicative content, teaching methods, weighted assessment mapped to outcomes, study hours and reading.
````markdown
A module descriptor is a contract read by validation panels, external examiners, students and future colleagues. Panels send descriptors back for predictable reasons: outcomes that use "understand" or "appreciate", outcomes not mapped to any assessment, assessment that over-assesses for the credit, study hours that do not add up, content lists that are a lecture plan, outcomes pitched at the wrong level, and reading lists that are out of date or impossible to access. A good descriptor is concise, stable for several years (so content is "indicative"), and internally consistent.
Module: [MODULE_TITLE]. Credits: 15.
[NOTES]
1. Identify the level (for example first year, final year, master's) and the qualification framework descriptors that apply; pitch outcome verbs to it (identify and describe at entry level; analyse and apply in the middle; evaluate, synthesise and create at final year and master's).
2. Write a two- or three-sentence summary and two to four aims.
3. Write four to six learning outcomes as "On successful completion, students will be able to..." with one observable verb each. Split compound outcomes.
4. Write indicative content as five to eight themed headings, not a weekly schedule.
5. Describe the teaching and learning approach and how it supports the outcomes.
6. Calculate notional study hours as 15 x 10 unless the notes give another ratio, split into scheduled teaching, guided independent study and assessment preparation. Totals must match.
7. Specify assessment: components, type, weighting, length or duration, and which outcomes each assesses; include formative assessment. Check every outcome is assessed and the volume is proportionate to 15 credits.
8. Add prerequisites, an indicative reading list structure (two to four essential, more recommended), and accessibility and inclusive practice notes.
9. Note anything a panel will query and the decision it needs from the module leader.
- Use only what the notes give for topics, methods and assessment ideas; fill obvious gaps with clearly labelled suggestions.
- Do not invent books, authors, editions or URLs. Write reading entries as "[Core text on X - module leader to supply]" unless the notes name them.
- Do not invent institutional rules (word counts per credit, pass marks, resit rules); mark them [check your regulations].
- If the institution's template headings are given, use them in that order instead of the default headings, keeping the content.
- If the notes do not say what students will learn or the level, ask for those two things and stop.
## Module summary
Title, level, credits, prerequisites, summary, aims.
## Learning outcomes
Numbered.
## Indicative content
Bullets.
## Teaching and learning
Short paragraph.
## Study hours
Table: Activity | Hours. Total row equal to the notional hours.
## Assessment
Table: Component | Type | Weight | Length or duration | Outcomes assessed. Then a formative assessment line.
## Outcome to assessment map
Table: Outcome | Component(s).
## Reading
Essential and recommended, with placeholders.
## Panel notes
Bullets: likely queries and decisions needed.
````
---
## Write measurable learning objectives
`write-learning-objectives` · prompt · Course design · https://hermes-ide.com/prompts/write-learning-objectives
Writes measurable learning objectives with Bloom verbs, conditions and criteria, each aligned to an assessment method that would show mastery. Use when planning a lesson, module or course.
````markdown
An objective is useful only if you could watch a learner and decide whether they have met it. "Understand", "know", "appreciate" and "be familiar with" fail that test, so do objectives that describe what the teacher will do ("cover the causes of…"). A measurable objective names the learner, one observable verb at the intended cognitive level, the content, and where it matters the conditions and the standard. It also points straight to how it will be assessed.
Write 5 learning objectives for the topic below.
[TOPIC]
1. Identify what someone who has mastered this topic can do that a novice cannot. Use that as the source of the objectives, not the list of content.
2. Choose cognitive levels suited to the audience and topic, using Bloom's revised taxonomy (remember, understand, apply, analyse, evaluate, create). Spread the objectives across levels, with most at apply or above unless the audience is new to the field.
3. Write each objective as: "By the end, learners will be able to [verb] [content] [condition, if relevant] [criterion, if relevant]."
- One verb per objective. No "understand", "know", "learn", "appreciate", "be aware of".
- Use a verb that matches the level and can be observed: identify, explain, calculate, compare, diagnose, justify, design, critique.
- Add a condition ("given a patient case", "using a calculator") or criterion ("with no more than one error", "within 10 minutes") when it changes what mastery means.
4. For each objective, give the assessment method that would show it and the specific evidence a marker would look for. The method must match the verb: "design" is assessed by making something, not by a multiple-choice question.
5. Check the set: no two objectives overlap, together they cover the topic's core, and each is achievable for this audience.
- If the topic is too vague to write measurable objectives for, ask up to two questions about the goal and the audience, then stop.
- Keep the topic's terminology, and keep objectives to one sentence each.
- If 5 is too many for a narrow topic, write fewer and say so instead of padding with trivial recall objectives.
## Objectives
A table: # | Objective | Bloom level | Assessment method | Evidence of mastery.
## Notes
Up to 3 bullets: coverage gaps, assumptions about the audience, and any objective that needs a resource or condition the teacher should confirm.
````