agentleFS
ArthurZakirovArthurZakirov/SystemSmith/skills/format-markdown/SKILL.md

format-markdown

Skill0 starsChanged 6 months agoMITView on GitHub

Create, edit, review, refactor, or rewrite Markdown artifacts while preserving meaning, valid syntax, navigability, and human reviewability. Use whenever work directly changes or reviews a Markdown file, including README.md, AGENTS.md, SKILL.md, reference docs, design docs, or Markdown produced from notes, transcripts, scratch text, or rough drafts.

2 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

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    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:

    Create or edit the Markdown artifact so it remains valid, readable, navigable, and faithful to the intended meaning.

    line 17
  2. Distinctive:

    Do not invent missing content.

    line 23
  3. Distinctive:

    If extra guidance must be retained without becoming document content, use an HTML comment when appropriate.

    line 25
  4. Distinctive:

    Keep YAML/frontmatter valid when the target artifact expects it.

    line 29
  5. Distinctive:

    Use valid heading levels and do not skip levels merely for visual size.

    line 30
  6. Distinctive:

    Use inline code for repositories, folders, files, commands, functions, variables, configuration keys, and other literal technical …

    line 32
  7. Distinctive:

    Keep code fences syntactically valid and preserve the intended language identifier when known.

    line 36
  8. Distinctive:

    Every referenced file or path with a resolvable target is a meaningful clickable Markdown link.

    line 45
  9. Distinctive:

    Every in-document contents link points to an existing heading anchor and resolves in the intended Markdown renderer.

    line 46
  10. Very specific:

    When transforming raw thoughts, examples and nuance are preserved according to thoughts-to-artifact.

    line 49

≈ “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 Formatter

User request: $ARGUMENTS

Apply information-representation-design for tables vs lists, hierarchy, prose, diagrams, and other representation choices. Apply relevance-first-information-design for information selection, abstraction layering, routing, and progressive disclosure. Apply thoughts-to-artifact when the source is raw notes, dictation, a transcript, or a brainstorm whose conceptual structure should be recovered rather than copied in source order.

Also apply living-artifacts when the output contains current-state values, snapshots, file trees, versions, paths, or other data likely to drift.

Core Task

Create or edit the Markdown artifact so it remains valid, readable, navigable, and faithful to the intended meaning. Treat machine-consumed Markdown such as AGENTS.md and SKILL.md as dual-audience artifacts: optimize for correct agent use without sacrificing human review and navigation.

Preservation Rules

  • Preserve all key information, nuance, and examples already present.
  • Fix obvious spelling, grammar, transcript noise, malformed sentences, and broken Markdown syntax when doing so does not change meaning.
  • Do not invent missing content.
  • Reorder content only when it improves clarity without changing meaning.
  • If extra guidance must be retained without becoming document content, use an HTML comment when appropriate.

Markdown-Specific Rules

  • Preserve literal $ syntax when it is semantically part of the source.
  • Keep YAML/frontmatter valid when the target artifact expects it.
  • Use valid heading levels and do not skip levels merely for visual size.
  • In Markdown documents where emoji suit the audience and renderer, prefix major section headings (typically the document title and its highest-level sections) with one semantically meaningful emoji to help readers recognize and scan them. Use emojis for lower-level headings selectively when they distinguish meaningful subsection categories; leave fine-grained headings plain when additional icons would create noise. Keep the text label, follow established document conventions, and omit emoji where the document's accessibility, audience, or style requirements make them unsuitable.
  • Use inline code for repositories, folders, files, commands, functions, variables, configuration keys, and other literal technical identifiers when appropriate.
  • In maintained Markdown artifacts, make concrete file references clickable with correct relative links when a real target exists.
  • When an overview names sections later in the same Markdown document, link each navigable item to its actual section anchor instead of repeating a heading as unlinked text. Keep the link label aligned with its target heading, including the same emoji (when present), spelling, casing, and distinguishing terminology. Verify the fragment against the target renderer; where supported, use an explicit stable anchor if automatic heading slugs could be brittle. Shorten the label only when the shorter wording remains unambiguous and preserves the emoji.
  • When a long section contains several subsections readers may need to jump between, add a local linked contents list directly beneath that section's introduction. Keep it within the parent section rather than introducing an unrelated sibling heading. Use this only when the target surface supports in-document navigation and the links materially improve it; ordinary chat messages and short sections may need no contents list.
  • Keep code fences syntactically valid and preserve the intended language identifier when known.
  • Escape or restructure Markdown syntax when literal characters would otherwise be interpreted incorrectly.

Self-Check

  • Meaning preserved.
  • No invented facts.
  • Markdown parses as intended.
  • Frontmatter and code fences remain valid.
  • Every referenced file or path with a resolvable target is a meaningful clickable Markdown link; unresolved targets are identified rather than presented as if linked.
  • Every in-document contents link points to an existing heading anchor and resolves in the intended Markdown renderer; its displayed emoji and identifying wording match the destination heading.
  • Machine-consumed Markdown remains easy for a human reviewer to navigate and inspect.
  • Representation and relevance/disclosure rules come from their dedicated skills rather than being redefined here.
  • When transforming raw thoughts, examples and nuance are preserved according to thoughts-to-artifact.

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.