agentleFS
Sign inStart free
ArcQian-bitArcQian-bit/codex-real-engineer-skills/skills/docs-keeper/SKILL.md

docs-keeper

Skill1 starsChanged 5 months agoMITView on GitHub

Keep repository documentation accurate after code, CLI, API, config, workflow, or release changes. Use when the user asks to update README, docs, examples, migration guides, comments, help text, or public-facing instructions so they match implemented behavior. Do not use for broad content marketing or document file formats handled by a more specific skill.

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Update docs as part of the same engineering change.

    line 8
  2. Distinctive:

    Update only the docs that readers would actually use.

    line 14
  3. Distinctive:

    Keep examples runnable and consistent with tests.

    line 15
  4. Distinctive:

    Remove stale claims rather than adding caveats around them.

    line 16
  5. Distinctive:

    Verify links, commands, and file names.

    line 17
  6. Distinctive:

    Prefer direct, task-oriented prose.

    line 30
  7. Distinctive:

    Put warnings near the command or behavior they affect.

    line 32
  8. Distinctive:

    Keep generated docs out of hand-edited sections unless the repo already does that.

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Docs Keeper

Update docs as part of the same engineering change.

Workflow

  1. Inspect the changed behavior, public API, CLI flags, config names, defaults, errors, and install paths.
  2. Find docs that mention the changed surface with rg.
  3. Update only the docs that readers would actually use.
  4. Keep examples runnable and consistent with tests.
  5. Remove stale claims rather than adding caveats around them.
  6. Verify links, commands, and file names.

What To Update

  • README quick start and feature list.
  • Install/upgrade instructions.
  • CLI help, config reference, and environment variables.
  • API examples and response shapes.
  • Migration notes and changelog entries.
  • Screenshots only when the UI meaningfully changed.

Style

  • Prefer direct, task-oriented prose.
  • Avoid marketing filler.
  • Put warnings near the command or behavior they affect.
  • Keep generated docs out of hand-edited sections unless the repo already does that.

Finish with docs changed and the behavior each doc now reflects.

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.

Check your setup, free