agentleFS
mikeparcewskimikeparcewski/wicked-garden/skills/engineering/docs/SKILL.md

wicked-garden-engineering-docs

Skill9 starsChanged 7 months agoMITView on GitHub

Use when generating documentation from code, auditing documentation coverage for gaps, or detecting code-doc drift after a refactor. Covers generate (API docs, READMEs), audit (coverage metrics, undocumented exports), and sync (stale docs detection) in one skill. NOT for architecture documentation (use the architecture skill) or product requirements (use product/requirements-analysis).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create or update README files

    line 50
  2. Distinctive:

    Add inline comments where missing

    line 51
  3. Very specific:

    Use the wicked-garden-search skill to scope the file set before auditing

    line 91
  4. Distinctive:

    Run sync after every significant refactor — don't let drift accumulate

    line 99

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Documentation Engineering Skill

Generate, audit, and sync documentation across the codebase.

Quick Start

Generate docs from code

wicked-garden-engineering docs <file-or-component> --type api|readme|guide|inline

Extracts types, signatures, and comments to produce API docs, READMEs, or inline comments (the docs action of the engineering domain skill routes here).

Audit documentation coverage

wicked-garden-engineering docs <path> --audit

Reports coverage (documented vs total exports), quality score, and prioritized gaps.

Detect stale docs after code changes

wicked-garden-engineering docs <path> --sync

Identifies documentation that has drifted from implementation after a refactor or rename.

Generate

Transform code into documentation:

  • Extract types, method signatures, and inline comments
  • Generate API reference (JSDoc / docstring style)
  • Create or update README files
  • Add inline comments where missing

Output: Markdown docs ready to commit, or inline comment patches.

Audit

Evaluate documentation health across the codebase:

  • Find undocumented exported functions, classes, and API endpoints
  • Calculate coverage percentage and quality score (description + params + examples)
  • Prioritize gaps: High = public APIs, Medium = internal utilities, Low = private/test

Quality Score (0-100):

  • Has description: +25
  • Has parameters: +25
  • Has examples: +30
  • Has edge cases: +20

Coverage Report format:

# Documentation Coverage Report

## Summary
| Category  | Total | Documented | Coverage |
|-----------|-------|------------|----------|
| Functions | 145   | 98         | 67.6%    |

## Top Issues
### Undocumented Public Functions (12)
- `src/api/auth.ts::authenticate` — Core auth

Sync

Detect and fix documentation drift:

  • Compare code signatures against existing doc strings
  • Flag mismatched parameter names, changed return types, removed methods
  • Suggest specific doc updates with before/after diffs

Integration

  • Use the wicked-garden-search skill to scope the file set before auditing
  • Native TaskCreate (with metadata.event_type="task") tracks doc tasks
  • CI: run audit in --report mode to gate PRs that drop below coverage threshold

Best Practices

  1. Prioritize public APIs first — that is what users see
  2. Set realistic targets — 80% with good quality beats 100% with stubs
  3. Run sync after every significant refactor — don't let drift accumulate
  4. Automate in CI — block PRs that reduce coverage

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.