Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Exercise Directory Structure Scaffolder

agent education skill risk: low

Exercise Directory Structure Scaffolder

Create exercise directory structures with sections, problems, solutions, and explainers that pass pnpm ai-hero-cli internal lint. Parse plans to generate directories and stub readm…

  • External action: low

SKILL 1 file

SKILL.md
---
name: scaffold-exercises
description: "Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section."
---
# Scaffold Exercises

Create exercise directory structures that pass `pnpm ai-hero-cli internal lint`, then commit with `git commit`.

## Directory naming

- **Sections**: `XX-section-name/` inside `exercises/` (e.g., `01-retrieval-skill-building`)
- **Exercises**: `XX.YY-exercise-name/` inside a section (e.g., `01.03-retrieval-with-bm25`)
- Section number = `XX`, exercise number = `XX.YY`
- Names are dash-case (lowercase, hyphens)

## Exercise variants

Each exercise needs at least one of these subfolders:

- `problem/` - student workspace with TODOs
- `solution/` - reference implementation
- `explainer/` - conceptual material, no TODOs

When stubbing, default to `explainer/` unless the plan specifies otherwise.

## Required files

Each subfolder (`problem/`, `solution/`, `explainer/`) needs a `readme.md` that:

- Is **not empty** (must have real content, even a single title line works)
- Has no broken links

When stubbing, create a minimal readme with a title and a description:

```md
# Exercise Title

Description here
```

If the subfolder has code, it also needs a `main.ts` (>1 line). But for stubs, a readme-only exercise is fine.

## Workflow

1. **Parse the plan** - extract section names, exercise names, and variant types
2. **Create directories** - `mkdir -p` for each path
3. **Create stub readmes** - one `readme.md` per variant folder with a title
4. **Run lint** - `pnpm ai-hero-cli internal lint` to validate
5. **Fix any errors** - iterate until lint passes

## Lint rules summary

The linter (`pnpm ai-hero-cli internal lint`) checks:

- Each exercise has subfolders (`problem/`, `solution/`, `explainer/`)
- At least one of `problem/`, `explainer/`, or `explainer.1/` exists
- `readme.md` exists and is non-empty in the primary subfolder
- No `.gitkeep` files
- No `speaker-notes.md` files
- No broken links in readmes
- No `pnpm run exercise` commands in readmes
- `main.ts` required per subfolder unless it's readme-only

## Moving/renaming exercises

When renumbering or moving exercises:

1. Use `git mv` (not `mv`) to rename directories - preserves git history
2. Update the numeric prefix to maintain order
3. Re-run lint after moves

Example:

```bash
git mv exercises/01-retrieval/01.03-embeddings exercises/01-retrieval/01.04-embeddings
```

## Example: stubbing from a plan

Given a plan like:

```
Section 05: Memory Skill Building
- 05.01 Introduction to Memory
- 05.02 Short-term Memory (explainer + problem + solution)
- 05.03 Long-term Memory
```

Create:

```bash
mkdir -p exercises/05-memory-skill-building/05.01-introduction-to-memory/explainer
mkdir -p exercises/05-memory-skill-building/05.02-short-term-memory/{explainer,problem,solution}
mkdir -p exercises/05-memory-skill-building/05.03-long-term-memory/explainer
```

Then create readme stubs:

```
exercises/05-memory-skill-building/05.01-introduction-to-memory/explainer/readme.md -> "# Introduction to Memory"
exercises/05-memory-skill-building/05.02-short-term-memory/explainer/readme.md -> "# Short-term Memory"
exercises/05-memory-skill-building/05.02-short-term-memory/problem/readme.md -> "# Short-term Memory"
exercises/05-memory-skill-building/05.02-short-term-memory/solution/readme.md -> "# Short-term Memory"
exercises/05-memory-skill-building/05.03-long-term-memory/explainer/readme.md -> "# Long-term Memory"
```

REQUIRED CONTEXT

  • plan with section names, exercise names, and variant types

ROLES & RULES

  1. Create exercise directory structures that pass `pnpm ai-hero-cli internal lint`, then commit with `git commit`.
  2. Name sections as `XX-section-name/` inside `exercises/`.
  3. Name exercises as `XX.YY-exercise-name/` inside a section.
  4. Use dash-case for names.
  5. Provide at least one of `problem/`, `solution/`, or `explainer/` per exercise.
  6. Default to `explainer/` when stubbing unless the plan specifies otherwise.
  7. Create a non-empty `readme.md` with no broken links in each subfolder.
  8. Create a minimal readme with title and description when stubbing.
  9. Add `main.ts` (>1 line) if the subfolder has code.
  10. Parse the plan to extract section names, exercise names, and variant types.
  11. Use `mkdir -p` to create directories.
  12. Create stub readmes with a title.
  13. Run `pnpm ai-hero-cli internal lint` to validate.
  14. Fix any errors until lint passes.
  15. Use `git mv` (not `mv`) when renaming or moving exercises.
  16. Update numeric prefixes to maintain order after moves.
  17. Re-run lint after moves.

EXPECTED OUTPUT

Format
unknown
Constraints
  • create directories with mkdir -p
  • create minimal readme.md stubs
  • run pnpm ai-hero-cli internal lint
  • use git mv for renames
  • ensure lint passes before commit

SUCCESS CRITERIA

  • Directories and files pass `pnpm ai-hero-cli internal lint`.
  • Readmes are non-empty with titles and no broken links.
  • No `.gitkeep`, `speaker-notes.md`, or `pnpm run exercise` commands present.
  • Numeric prefixes maintain correct order.

FAILURE MODES

  • May leave lint errors unfixed.
  • May use `mv` instead of `git mv` on renames.
  • May create empty or broken-link readmes.

EXAMPLES

Includes one example plan for memory skill building and the corresponding mkdir/readme stub commands.

CAVEATS

Dependencies
  • Requires a plan specifying sections, exercises, and variant types.

QUALITY

OVERALL
0.90
CLARITY
0.90
SPECIFICITY
0.95
REUSABILITY
0.85
COMPLETENESS
0.90

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT