agentleFS
afaraha8403afaraha8403/balakit/.claude/skills/documentation-writer/SKILL.md

documentation-writer

Skill1 starsChanged 10 days agoMITView on GitHub

Write clear, scannable documentation with a research-first, phase-separated workflow. Pick one Diátaxis mode, then apply STE and Global English. Apply when the user asks for documentation, READMEs, doc sites, API reference, migration guides, or technical markdown. Use marketing-psychology for marketing copy. Use authoring-skills-and-rules to write a Skill, not a README. Not commit-message lint — changelog.mdc owns changelog headings.

43 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use tailwindcss, test-engineer and 10 more.

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.
  • azlekovSkill

    tailwindcss

    This skill should be used when the user asks to "style with Tailwind", "add CSS", "configure theme", "use @theme", "add custom colors", "implement dark mode", "use container queries", "add responsive design", "use OKLCH colors", or discusses styling, theming, or visual design. Always use the latest Tailwind CSS version and modern patterns.

    Also in 3 projects that use this

  • JohnJBorenSkill

    test-engineer

    Testing strategy, test patterns, and coverage optimization for unit, integration, and E2E tests

    Also in 4 projects that use this

  • LangChainSkill

    mermaid-diagrams

    Embed Mermaid diagrams in generated wiki pages. Use whenever documenting a runtime or request flow, a call sequence, a state machine or lifecycle, a data model or entity relationships, or non-trivial control flow, since these are clearer as a diagram than as prose. Also use when an update run touches a page that already contains a mermaid fence, or a page that contains a text fence a previous run degraded.

    Also in 5 projects that use this

  • JohnJBorenSkill

    debugger

    Systematic debugging workflows, root cause analysis, and troubleshooting patterns

    Also in 3 projects that use this

  • GoogleSkill

    code-reviewer

    Also in 6 projects that use this

  • VercelSkill

    technical-writer

    Write, review, and edit developer documentation for SDKs, libraries, and frameworks, including sites such as ai-sdk.dev and chat-sdk.dev. Use for getting-started guides, tutorials, API references, conceptual explanations, integration guides, migration guides, troubleshooting, and code examples.

    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, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 3

    Distinctive

    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:

    Verify — examples run; citations still match.

    line 41
  2. Very specific:

    If the host can launch a Task / explore subagent, use a read-only explore pass for a large or unfamiliar codebase before drafting.

    line 49
  3. Distinctive:

    Read relevant files. Delegate broad mapping to explore when available.

    line 55
  4. Distinctive:

    Start each section with the BLUF answer.

    line 85

“Common” is measured: kept by at least 6 in 10 of the 42 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

Documentation Writer

Leading words: research-first, Diátaxis mode, BLUF, STE, Global English, evidence-aware, phase separation.

Research-first technical documentation. Chat stays Caveman; the document is Standard Professional Mode.

Copy these phases into the todo list verbatim. A skipped phase stays with skip: <reason>.

  1. Discover — list every file/API/feature the docs must cover.
  2. Research — primary sources for versions, flags, install commands.
  3. Outline — name the Diátaxis mode; BLUF per section.
  4. Draft — STE / Global English; slop catalog for artifacts.
  5. Verify — examples run; citations still match.

Mode table: references/diataxis.md. Sentence craft: references/style.md. Slop ids: references/slop-catalog.md.

Subagents

If the host can launch a Task / explore subagent, use a read-only explore pass for a large or unfamiliar codebase before drafting. Use web search for anything version-sensitive. Do not assume those tools exist.

Phase 1 — Discover

Read relevant files. Delegate broad mapping to explore when available.

Exit: you can list every file/API/feature the docs must cover. 🛑 Do not proceed to Research until the user confirms the scope (or you are explicitly operating solo and the scope is unambiguous). Ask with the host's structured question tool. Prompt in plain English. Last option: Say this in plain English (meta: rephrase + example, do not advance).

Phase 2 — Research

Web research before asserting facts about APIs, CLI flags, install commands, LTS timelines, or security claims. Prefer primary sources. Capture citations. If sources conflict, say what is uncertain.

Exit: every claim you will make has a source link. 🛑 Do not proceed to Outline until Research is complete.

Phase 3 — Outline

Name the Diátaxis mode. Headings, audience, prerequisites. BLUF: lead each section with the direct answer in 40–60 words.

Exit: skeleton approved. 🛑 Present the outline. Do not draft until confirmed. Ask with the host's structured question tool. Prompt in plain English. Last option: Say this in plain English (meta: rephrase + example, do not advance).

Phase 4 — Draft

Apply references/style.md and the slop catalog. Start each section with the BLUF answer. Tables for comparisons. Concrete examples first.

Exit: every outline section has content.

Phase 5 — Verify

Re-read against the repo. Re-check critical external claims. Run code examples when possible.

Exit: every example runs as documented; every external claim matches the cite.

Standard file shape

  1. Title + 1–2 sentence summary (BLUF).
  2. Quick start — exact commands.
  3. Usage / examples — most common case first.
  4. API / reference if needed — tables.

Reply contract

Name the Diátaxis mode, the files written, and any claim still unverified.

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.