doc-writer
Skill80 starsChanged 8 months agoMITView on GitHub
Documentation templates and standards: README structure, API reference format, changelog (Keep a Changelog), and comment guidelines. Use when creating or updating documentation. Loaded automatically by the doc-writer agent.
- Installs packages
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 82
Follow Keep a Changelog format:
- Distinctive: line 104
Use active voice; keep sentences concise
- Distinctive: line 106
Write for scanning: H1 for the title, H2/H3 for sections, lists, and bold key terms
- Distinctive: line 113
Keep it current: update docs in the same PR as the code change
- Distinctive: line 115
Test your docs: follow your own instructions.
“Common” is measured: kept by at least 6 in 10 of the 17 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.
Files
Doc Writer Skill
Director Mode Lite - Documentation Specialist
Documentation Types
1. README.md
Essential sections:
# Project Name
Brief description (1-2 sentences)
## Quick Start
\`\`\`bash
npm install # Installation
npm start # Run
\`\`\`
## Features
- Feature 1
## Documentation
- [Getting Started](docs/getting-started.md)
- [API Reference](docs/api.md)
## Contributing
See [CONTRIBUTING.md](CONTRIBUTING.md)
## License
MIT2. API Documentation
For each endpoint/function:
## `functionName(param1, param2)`
Brief description.
**Parameters:**
- `param1` (string): Description
- `param2` (number, optional): Description. Default: `10`
**Returns:**
- `ResultType`: Description
**Example:**
\`\`\`javascript
const result = functionName('hello', 5);
// => { success: true }
\`\`\`
**Throws:**
- `ValidationError`: When param1 is emptyFor REST endpoints, document the method and path, request headers/body, success and error responses, and a runnable curl example.
3. Code Comments
Comment complex algorithms, non-obvious business logic, workarounds (and why), and TODOs with context. Do NOT comment self-explanatory code or restate what the code already says.
// Calculate compound interest using continuous compounding formula
// This matches the bank's calculation method (see SPEC-123)
const interest = principal * Math.exp(rate * time);4. CHANGELOG.md
Follow Keep a Changelog format:
# Changelog
## [1.2.0] - 2025-01-15
### Added
- New feature X
### Changed
- Improved performance of Y
### Fixed
- Bug in Z
### Removed
- Deprecated API endpoint5. Architecture Docs
Cover the system overview, component relationships, data flow, and design decisions with their rationale.
Documentation Standards
Style
- Use active voice; keep sentences concise
- Define acronyms on first use; use consistent terminology
- Write for scanning: H1 for the title, H2/H3 for sections, lists, and bold key terms
Code Examples
- Make examples complete and runnable; include expected output
- Show both basic and advanced usage; handle errors
Principles
- Keep it current: update docs in the same PR as the code change
- Write for the reader: assume minimal context, lead with the common case
- Test your docs: follow your own instructions; verify every example runs
Output Format
## Documentation Update
### Files Created/Updated
- `README.md` - Added Quick Start section
### Summary
[What documentation was added/changed and why]Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- microsoft/vscode-docs★ 6.7ksame name
- redai-infra/Relax★ 665same name
- microsoft/aspire.dev★ 200same name
- mitchdenny/hex1b★ 181same name
- zeroclaw-labs/zeroclaw-skills★ 65same name
- nimbalyst/skills★ 28same name
- k1lgor/virtual-company★ 4same name
- dqtx760/skills-manage★ 2same name
- GeziP/doc-wiki★ 2same name
- grantkee/claude-extensions★ 2same name
10 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use code-review.
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.
GoogleSkillcode-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 3 projects that use this
In this repository36 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- changelog-observerSkill
- agent-checkSkill
- agentsSkill
- agent-templateSkill
- auto-loopSkill
- changelogSkill
- check-environmentSkill
- claude-md-checkSkill
- claude-md-templateSkill
- code-reviewerSkill
- debuggerSkill
- director-modeSkill
- evolving-loopSkill
- evolving-statusSkill
- focus-problemSkill
- getting-startedSkill
- handoff-claudeSkill
- handoff-codexSkill
- handoff-geminiSkill
- handoff-grokSkill
- hooks-checkSkill
- hook-templateSkill
- interop-routerSkill
- mcp-checkSkill
- planSkill
- project-health-checkSkill
- project-initSkill
- session-relaySkill
- skill-checkSkill
- skillsSkill
- skill-templateSkill
- smart-commitSkill
- test-firstSkill
- test-runnerSkill
- workflowSkill
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
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.

