agentleFS
pantheon-orgpantheon-org/tekhne/skills/documentation/markdown-authoring/SKILL.md

markdown-authoring

Skill10 starsChanged 39 days agoMITView on GitHub

Author high-quality Markdown documentation with deterministic structure, lint compliance, and CI integration. Use when writing README files, creating docs pages, fixing markdownlint failures, defining style rules, or wiring markdown checks into pre-commit and pipelines. Keywords: markdown, markdownlint, readme, docs, headings, lists, code fences, links, images, lint config, ci, documentation style.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 8 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the task involves Markdown content, linting, or documentation standards.

    line 10
  2. Very specific:

    Do not use this skill for non-Markdown document formats (for example .adoc or .rst) unless conversion is part of the task.

    line 14
  3. Distinctive:

    Keep Markdown lint-clean and deterministic.

    line 19
  4. Distinctive:

    Use code fences with explicit language tags.

    line 20
  5. Distinctive:

    Keep file-level conventions consistent across the repository.

    line 21
  6. Distinctive:

    Write content with concise headings and actionable examples.

    line 27
  7. Distinctive:

    Run markdownlint locally and fix violations.

    line 28
  8. Distinctive:

    BAD: Use plain triple backticks for code samples.

    line 88
  9. Very specific:

    GOOD: Use typed fences like bash or ts .

    line 89
  10. Distinctive:

    GOOD: Keep one list style and normalized table formatting.

    line 118

≈ “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

Markdown Authoring

When to Use

Use this skill when the task involves Markdown content, linting, or documentation standards.

When Not to Use

Do not use this skill for non-Markdown document formats (for example .adoc or .rst) unless conversion is part of the task.

Principles

  1. Structure first, wording second.
  2. Keep Markdown lint-clean and deterministic.
  3. Use code fences with explicit language tags.
  4. Keep file-level conventions consistent across the repository.

Deterministic Workflow

  1. Identify document type (README, guide, API doc, changelog).
  2. Apply template and section order from references.
  3. Write content with concise headings and actionable examples.
  4. Run markdownlint locally and fix violations. Re-run until zero errors are reported. If a violation persists: identify the specific rule, fix the source content or apply a narrow, justified inline exception, then re-lint. Do not proceed until lint is clean.
    • Lint-fix loop: lint fails → identify rule → fix source or add justified exception → re-lint → proceed only when clean
  5. Validate CI/pre-commit integration for regression prevention.

Quick Commands

Lint all Markdown files

rumdl check .

Expected result: no errors for staged or target files. This repository lints with rumdl; for a repository that uses markdownlint, see Lint: CLI.

Lint one skill folder

rumdl check skills/documentation/markdown-authoring

Expected result: folder-specific Markdown issues reported or zero errors.

Run repository checks

bunx @biomejs/biome check .

Expected result: non-Markdown formatting/lint issues also caught.

Evaluate this skill quality

pantheon-skill-auditor evaluate documentation/markdown-authoring --json

Expected result: updated dimension scores and grade.

Read a specific reference

./scripts/read-reference.sh syntax-headings

Expected result: displays reference content for the requested topic.

Check document style compliance

bun run check-style "path/to/document.md"

Expected result: style validation report printed to stdout.

Anti-Patterns

NEVER ship Markdown with missing fence language tags

WHY: Untyped code blocks reduce readability and tooling support.

BAD: Use plain triple backticks for code samples. GOOD: Use typed fences like ```bash or ```ts.

Consequence: Syntax highlighting and lint checks become inconsistent.

NEVER ignore markdownlint violations by disabling broad rules

WHY: Global suppression hides real quality and maintainability issues.

BAD: Turn off multiple rules to make CI green quickly. GOOD: Fix source content or apply narrow, justified exceptions.

Consequence: Documentation quality degrades release-over-release.

NEVER use heading levels out of sequence

WHY: Skipped heading levels break document hierarchy.

BAD: Jump from ## to #### with no ###. GOOD: Increase heading levels one step at a time.

Consequence: Navigation and accessibility suffer.

Consider adding a table of contents for documents longer than 300 lines. Optionally include anchor links in headings to improve internal navigation.

NEVER mix inconsistent list and table styles in one document

WHY: Style drift makes docs harder to scan and review.

BAD: Alternate list markers and inconsistent table pipe spacing. GOOD: Keep one list style and normalized table formatting.

Consequence: Diff noise increases and review confidence drops.

References

  • Syntax: Headings
  • Syntax: Lists
  • Syntax: Code Blocks
  • Syntax: Links & Images
  • Syntax: Formatting
  • Syntax: Other Elements
  • Docs: README
  • Docs: Organization
  • Docs: Writing Style
  • Docs: API
  • Docs: Changelog
  • Lint: Config
  • Lint: Rules
  • Lint: CLI
  • Lint: CI
  • Lint: API

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.