agentleFS
dRafaleDdRafaleD/cybersec-skills/skills/engineering/lean-docs/SKILL.md

lean-docs

Skill2 starsChanged 55 days agoMITView on GitHub

Runs token-efficient documentation gap reviews for Cursor and Codex. Checks README for Install, Usage, and License, and flags public APIs without a nearby comment, then reports compact doc patches. Use when the user asks to update docs, README, API documentation, or fill missing usage. Do not dump entire files or rewrite unrelated prose.

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. Very specific:

    Run gaps. Queue missing README headings and exported functions with no docstring/comment.

    line 37
  2. Distinctive:

    Read the surrounding 20 lines.

    line 38
  3. Distinctive:

    Stop unless asked to write more.

    line 39
  4. Distinctive:

    Do not invent APIs. If you did not see it, do not document it.

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Lean Docs

Find the missing section. Patch the smallest gap. Do not rewrite the novel.

Let SKILL_ROOT be the folder that contains this SKILL.md. Prefer python3; on Windows use py -3.

python3 "$SKILL_ROOT/scripts/lean_docs.py" gaps .
python3 "$SKILL_ROOT/scripts/lean_docs.py" trim --chars 2500 path/to/out.txt

Mode

Default lean.

ModeBudget
leangaps + up to 8 slices; references/readme.md; ≤6 findings
standardup to 16 slices; ≤10 findings
deepstill no full-file rewrite; ≤16 findings

Workflow

  1. Run gaps. Queue missing README headings and exported functions with no docstring/comment.
  2. Read the surrounding 20 lines. Add the smallest accurate paragraph.
  3. Stop unless asked to write more.

Hard rules

  • Do not invent APIs. If you did not see it, do not document it.
  • Cap quotes at 12 lines. No README dump.
  • License: point at LICENSE; do not paste SPDX essays.

Report template

## Lean-docs (`<mode>`)

**Entry:** README.md

| Sev | Location | Gap | Fix |
|-----|----------|-----|-----|
| MED | README.md | no Install | add clone + one command |

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.