agentleFS
diriendirien/yet-another-agent-harness/.claude/skills/markdownlint/SKILL.md

markdownlint

Skill19 starsChanged 8 months agoMITView on GitHub

Validate markdown files against formatting standards. Auto-detects and installs markdownlint-cli if missing. Checks project config or falls back to sensible defaults. Supports auto-fix mode. Use when creating or modifying markdown files, validating documentation, or enforcing markdown conventions.

  • Installs packages

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If not installed, install globally:

    line 37
  2. Distinctive:

    If installation fails (permissions, no npm), stop validation and report the issue with remediation steps:

    line 43
  3. Very specific:

    Use sudo npm install -g ...

    line 46
  4. Distinctive:

    Use a Node version manager (nvm, volta, fnm)

    line 47
  5. Distinctive:

    Do not silently skip validation.

    line 50
  6. Very specific:

    Default config (see references/markdownlint-config.json)

    line 58
  7. Very specific:

    If no project config exists, create a temporary .markdownlint.json using the default config from the reference file before running …

    line 60
  8. Distinctive:

    If markdownlint cannot be installed, report the error and provide remediation steps.

    line 107
  9. Distinctive:

    When validation fails, report each error with:

    line 112
  10. Very specific:

    After reporting errors, suggest running markdownlint --fix for auto-fixable issues and provide manual fixes for the rest.

    line 132

≈ “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
<!-- Copyright 2025-2026 Richard Shade. Licensed under Apache-2.0. --><!-- SPDX-License-Identifier: Apache-2.0 -->

Markdownlint

Validate markdown files follow formatting standards. Enables consistent documentation, readable diffs, and POSIX compliance.

What this skill does

  1. Checks if markdownlint-cli is installed; installs if missing.
  2. Detects project-specific markdownlint configuration or falls back to a minimal default config.
  3. Validates markdown files for formatting, structure, and style.
  4. Optionally auto-fixes common issues with --fix flag; reports errors with specific rules and fixes.

Installation check

# Check if markdownlint is available
markdownlint --version 2>/dev/null

If not installed, install globally:

npm install -g markdownlint-cli

If installation fails (permissions, no npm), stop validation and report the issue with remediation steps:

  • Use sudo npm install -g ... or fix npm permissions
  • Use a Node version manager (nvm, volta, fnm)
  • Install Node.js if not present

Do not silently skip validation.

Config detection priority

  1. .markdownlint.json in project root
  2. .markdownlint.yaml in project root
  3. .markdownlintrc in project root
  4. markdownlint field in package.json
  5. Default config (see references/markdownlint-config.json)

If no project config exists, create a temporary .markdownlint.json using the default config from the reference file before running validation.

Validation workflow

1. Check markdownlint installation
   ├─ Installed → continue
   └─ Missing → install, then continue (fail if install fails)

2. Detect project config
   ├─ Found → use it
   └─ Not found → use default config from references/

3. Run validation
   ├─ Check only:
   │    markdownlint <files-or-directories>
   └─ Auto-fix:
        markdownlint --fix <files-or-directories>

4. Report results
   ├─ Valid → confirm and proceed
   └─ Invalid → show errors, suggest fixes, re-validate after correction

Validation methods

Check files (default)

markdownlint README.md CHANGELOG.md docs/

Auto-fix common issues

markdownlint --fix README.md CHANGELOG.md docs/

Note: some issues (like MD001 heading-increment) cannot be auto-fixed and require manual correction. Re-run without --fix after fixing to confirm all issues resolved.

Error handling

Install failure

If markdownlint cannot be installed, report the error and provide remediation steps. Do not proceed with validation.

Validation failure

When validation fails, report each error with:

  • The rule that failed (e.g., MD022/blanks-around-headings)
  • What was wrong (e.g., heading not surrounded by blank lines)
  • A concrete fix

Example:

Validation failed:

1. MD022/blanks-around-headings: heading not surrounded by blank lines
   File: README.md:15
   Fix: add blank lines before and after the heading

2. MD047/single-trailing-newline: file does not end with newline
   File: CHANGELOG.md:89
   Fix: add a single newline at end of file

After reporting errors, suggest running markdownlint --fix for auto-fixable issues and provide manual fixes for the rest. Re-validate after corrections.

Format reference

See references/markdownlint-rules.md for the full rule reference, common fixes, and auto-fixable rules.

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.