agentleFS
Sign inStart free
MuhammadUsmanGMMuhammadUsmanGM/claude-code-best-practices/.claude/skills/lint-docs/SKILL.md

lint-docs

Skill105 starsChanged 31 days agoMITView on GitHub

Run this repo's documentation and shell quality gates (shellcheck, markdownlint, lint-claude-md) the same way CI runs them. Invoke before opening a PR, or when the user asks to lint, validate, or pre-flight the docs.

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:

    Run the same three checks CI runs and report pass/fail per check.

    line 9
  2. Distinctive:

    If any check fails, print the first 20 lines of its output below the table and stop.

    line 30
  3. Very specific:

    If shellcheck or markdownlint isn't installed, say so and skip that check — don't silently pass.

    line 35
  4. Distinctive:

    Do not modify files. This skill is diagnostic only.

    line 37

≈ “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

Lint Docs

Run the same three checks CI runs and report pass/fail per check.

Steps

  1. shellcheck — find every .sh under the repo and run shellcheck on it.
    find . -name '*.sh' -not -path './.git/*' -print0 | xargs -0 shellcheck
  2. markdownlint — run markdownlint on README.md, CONTRIBUTING.md, CHANGELOG.md, and everything under guides/, examples/, plugins/, tools/hooks/. Use .markdownlint.json at repo root.
  3. lint-claude-md — run bash tools/lint-claude-md.sh against every examples/claude-md-*.md template and the repo's own CLAUDE.md.

Output

Print a single summary table, one row per check:

CheckStatusDetails

If any check fails, print the first 20 lines of its output below the table and stop. Do not try to auto-fix unless the user asks.

Rules

  • If shellcheck or markdownlint isn't installed, say so and skip that check — don't silently pass.
  • Do not modify files. This skill is diagnostic only.

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