agentleFS
zazzcodezazzcode/zazz-skills/.agents/skills/doc-check/SKILL.md

doc-check

Skill4 starsChanged 3 months agoMITView on GitHub

Run or choose repository-local formatting, linting, and consistency checks for markdown, text, and documentation files before committing. Use when documentation files changed, standards docs were edited, or the user asks to verify docs formatting.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run documentation checks using the repository's own tooling.

    line 8
  2. Very specific:

    Read repo instructions (AGENTS.md, README, contributing docs) and hook configuration files such as .pre-commit-config.yaml, package.json, …

    line 13
  3. Very specific:

    Prefer the narrowest repo-declared command that checks the changed docs.

    line 14
  4. Distinctive:

    If a formatter modifies files, rerun the same check once to verify stability.

    line 16
  5. Distinctive:

    Do not run all-docs or all-files checks by default when a file-scoped command exists.

    line 21
  6. Distinctive:

    Do not touch unrelated formatting churn.

    line 22
  7. Distinctive:

    If the repo uses a virtual-branch or stacked-diff tool, identify which changed files belong to the current unit of work before running …

    line 23
  8. Distinctive:

    If no doc tooling exists, perform a manual pass for broken links, stale paths, private local paths, merge markers, trailing whitespace, and …

    line 24

“Common” is measured: kept by at least 6 in 10 of the 3 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

Document Check

Run documentation checks using the repository's own tooling. Do not install or invent formatters when the repo already declares hooks, package scripts, make targets, or CI jobs.

Workflow

  1. Identify changed documentation files with git status --short and, when needed, git diff --name-only.
  2. Read repo instructions (AGENTS.md, README, contributing docs) and hook configuration files such as .pre-commit-config.yaml, package.json, pyproject.toml, justfile, Makefile, or markdownlint config.
  3. Prefer the narrowest repo-declared command that checks the changed docs. Common examples include pre-commit run --files ..., prek run --files ..., npm run lint:docs, markdownlint, mdformat, or a repo-specific just target.
  4. Include all text-like files affected by the change, not only .md, when hooks apply to trailing whitespace, final newline, merge conflict markers, YAML, TOML, or generated docs.
  5. If a formatter modifies files, rerun the same check once to verify stability.
  6. Report commands, results, and any files changed by formatting.

Boundaries

  • Do not run all-docs or all-files checks by default when a file-scoped command exists.
  • Do not touch unrelated formatting churn.
  • If the repo uses a virtual-branch or stacked-diff tool, identify which changed files belong to the current unit of work before running broad fixers.
  • If no doc tooling exists, perform a manual pass for broken links, stale paths, private local paths, merge markers, trailing whitespace, and missing final newline.

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.