agentleFS
aka-kikaaka-kika/akakika-skills/skills/maintenance/docs-update/SKILL.md

docs-update

Skill11 starsChanged 3 months agoMITView on GitHub

Use when the user needs to update, improve, audit, or maintain documentation in a project. Covers READMEs, changelogs, API docs, inline comments, missing docs, and overall documentation quality. Works well before releases or when documentation has fallen behind the code.

17 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 13 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 13

    Distinctive

    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:

    Prefer clarity and scannability over perfection.

    line 13
  2. Distinctive:

    Keep docs close to the code they describe when possible.

    line 14
  3. Distinctive:

    Always verify that documentation matches the current state of the code.

    line 15
  4. Distinctive:

    Before a release or open-sourcing a project.

    line 20
  5. Distinctive:

    After significant refactors or feature additions.

    line 21
  6. Distinctive:

    When documentation feels stale or incomplete.

    line 22
  7. Distinctive:

    Update or rewrite READMEs (structure, clarity, examples)

    line 27
  8. Distinctive:

    Add or improve inline code documentation

    line 29
  9. Distinctive:

    Create missing sections (Installation, Usage, Contributing, Troubleshooting)

    line 30
  10. Distinctive:

    Ensure docs are consistent with the current codebase

    line 32
  11. Distinctive:

    Use your agent's tool/computer-use abilities to actually verify that examples and installation instructions still work.

    line 47
  12. Distinctive:

    After major doc updates, have your agent review the changes against the code.

    line 48
  13. Distinctive:

    Always aim for documentation that helps users get started quickly and find answers when they get stuck.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “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-update

Documentation maintenance and improvement specialist.

Core Principles

  • Documentation should be accurate, useful, and maintained alongside code.
  • Prefer clarity and scannability over perfection.
  • Keep docs close to the code they describe when possible.
  • Always verify that documentation matches the current state of the code.

When to Use

  • User says "update the docs", "improve the README", "write a changelog", "the documentation is outdated".
  • Before a release or open-sourcing a project.
  • After significant refactors or feature additions.
  • When documentation feels stale or incomplete.

Typical Tasks

  • Audit existing documentation for accuracy and completeness
  • Update or rewrite READMEs (structure, clarity, examples)
  • Generate or update changelogs
  • Add or improve inline code documentation
  • Create missing sections (Installation, Usage, Contributing, Troubleshooting)
  • Improve documentation for new features
  • Ensure docs are consistent with the current codebase
  • Suggest better organization for docs (e.g., moving to docs/ folder)

Workflow

  1. Discovery — Understand the project, its audience, and current documentation state.
  2. Audit — Identify what's outdated, missing, or unclear.
  3. Prioritize — Separate quick fixes from larger documentation efforts.
  4. Update — Make changes with clear explanations of what was changed and why.
  5. Review — Let the user review the diffs or proposed changes.

Notes

  • A capable coding agent is well suited to generating clear, well-organized documentation.
  • Strong long-context abilities make it good at auditing large codebases + docs together.
  • Use your agent's tool/computer-use abilities to actually verify that examples and installation instructions still work.
  • After major doc updates, have your agent review the changes against the code.

Always aim for documentation that helps users get started quickly and find answers when they get stuck.

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.