agentleFS
wado-langwado-lang/wado/.claude/skills/markdown/SKILL.md

markdown

Skill120 starsChanged 16 days agoMITView on GitHub

The rules for every Markdown file in the repository, inside docs/ or not: prose a reader understands on the first pass, MECE structure, headings rather than bold, checklists for TODOs. Read before writing or editing any Markdown (.md) file.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use typescript and documentation.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    typescript

    TypeScript best practices for this monorepo. Use this skill when: (1) writing new TypeScript code, (2) reviewing TypeScript code, (3) working with API responses, fetch calls, or JSON parsing, (4) adding or modifying types and interfaces.

    Also in 4 projects that use this

  • AnthropicSkill

    documentation

    Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing — API docs, architecture docs, or operational runbooks.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep a document simple and MECE.

    line 24
  2. Very specific:

    Do not use ... (bold) for sub-sections.

    line 25
  3. Very specific:

    Use a Markdown checklist for TODOs (- [ ] ...) and what's done (- [x] ...).

    line 26
  4. Very specific:

    Run mise run format after editing.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 12 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

Markdown

The goal is prose a reader understands on the first pass. Everything below serves that.

Prose

  • Plain words. One idea per sentence. The plain statement first, the reason for it after.
  • Three habits make a reader decode instead of read: a second clause hung off a dash, an abstract noun standing where a verb would do, and the clever phrasing of a point arriving before the obvious one. Undo each where you find it.
  • Correct and fresh. Keep the facts.
  • Cutting narration and redundancy is one way to get there. It is not the point. A passage that came out shorter and harder to follow has failed.

Structure

  • Keep a document simple and MECE.
  • Do not use **...** (bold) for sub-sections. Use Markdown sections instead.
  • Use a Markdown checklist for TODOs (- [ ] ...) and what's done (- [x] ...).

Numbers

  • A measured figure belongs in the table that holds its measurement, not in prose beside it: the table gets refreshed and the prose does not.
  • A table whose refresh you cannot see is a reason to find how it was measured, not to delete it. Name the command beside the table; deleting a measurement loses a fact.
  • Name the shape to grep for, not how many sites there are. A count goes stale with the next site.

Finish

Run mise run format after editing.

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.