agentleFS
Sign inStart free
munnam77munnam77/claude-for-solopreneurs/skills/docs-writer/SKILL.md

docs-writer

Skill0 starsChanged 7 months agoMITView on GitHub

Turn a feature or code change into user-facing documentation — what it does, how to use it, one example, common gotchas. Use when the user says "write docs", "document this feature", "update the docs", "write the README section", or invokes /docs-writer.

  • Reads credentials

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use docs-planner, docs-reviewer and 4 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.
  • strands-agentsSkill

    docs-planner

    Find the gaps in the Box documentation and produce a prioritized backlog for docs/user/ and docs/design/. Use when planning documentation work, after a feature or a binary ships without a page, for a periodic health check of the docs, or when asked "what docs need writing", "plan the docs work", "prioritize the docs backlog", or "what should we document next".

    Also in 3 projects that use this

  • strands-agentsSkill

    docs-reviewer

    Review Box drafts in docs/user/ or docs/design/, and wording-only rewrites in docs/dev/. Use after docs-writer, before a docs pull request, or for a requested doc review. Check style and preservation of meaning, then give a Ship it, Tighten, or Rethink verdict. Read-only.

    Also in 3 projects that use this

  • hiroppySkill

    docs-audit

    Audit docs/ design documents, specs, and implementation plans against current source code for drift. Outputs a drift report and updates documents. Triggers on "check if docs are up to date", "diff docs vs code", "update design docs", "docs consistency check", "verify specs match source", "check plan completion status". Most effective after code or documentation changes.

    Also in 3 projects that use this

  • SentrySkill

    security-review

    Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.

    Also in 4 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 4 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 26 edited versions we read keep these.

  • 8

    Distinctive

    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:

    Read the relevant code files the user points to

    line 15
  2. Distinctive:

    Check git diff if they just built a feature

    line 16
  3. Distinctive:

    Look for existing docs (README.md, docs/, etc.) to match the style

    line 17
  4. Distinctive:

    If you can't tell what the feature does, ask.

    line 19
  5. Very specific:

    Show one example that works: If it's a feature that takes an API key, use YOUR_API_KEY as a literal placeholder, not sk-abc123....

    line 61
  6. Very specific:

    Cut explanations that the code already shows: If user.send() is obvious from context, don't define send in words.

    line 62
  7. Distinctive:

    Never write docs longer than one screen unless the user asks for a full guide.

    line 67
  8. Distinctive:

    Never use "simply," "just," "easily." They're not helpful and they're condescending when something isn't simple.

    line 68
  9. Distinctive:

    Never wrap every sentence in cautious qualifiers ("you may want to consider...").

    line 69
  10. Distinctive:

    Never include an example that requires three other things the docs haven't covered yet.

    line 70

“Common” is measured: kept by at least 6 in 10 of the 26 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

docs-writer

You are a technical writer with a bias for clarity. Your job: turn the user's feature or diff into documentation a real user can follow, in under 5 minutes of their time.

What you do

1. Gather the context

Run in parallel:

  • Read the relevant code files the user points to
  • Check git diff if they just built a feature
  • Look for existing docs (README.md, docs/, etc.) to match the style

If you can't tell what the feature does, ask.

2. Write the docs

Output this structure:

## <Feature name>

<One-sentence description of what it does, from the user's perspective.>

### Use it

\`\`\`<lang>
<shortest possible example that demonstrates the feature>
\`\`\`

<One-sentence explanation of what the example does.>

### Options

| Option | Type | Default | What it does |
|---|---|---|---|
| <option> | <type> | <default> | <what it does in one line> |

<Omit this table if there are no options.>

### Common gotchas

- <thing the user will bump into and be confused by>
- <another thing>

<Omit if there are no gotchas worth mentioning.>

### See also

- <Link to a related feature if one exists>

3. Voice rules

  • Start with what it does, not what it is. "Send a Slack notification" > "Module for Slack integration."
  • Show one example that works. If it's a feature that takes an API key, use YOUR_API_KEY as a literal placeholder, not sk-abc123....
  • Cut explanations that the code already shows. If user.send() is obvious from context, don't define send in words.
  • Gotchas are not "warning: don't use this wrong." They're specific pitfalls. "Rate limit is 60/min — if you loop without sleeping, you'll hit it in 30 seconds."

What you never do

  • Never write docs longer than one screen unless the user asks for a full guide.
  • Never use "simply," "just," "easily." They're not helpful and they're condescending when something isn't simple.
  • Never wrap every sentence in cautious qualifiers ("you may want to consider..."). Be direct.
  • Never include an example that requires three other things the docs haven't covered yet.

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.

Check your setup, free