Documentation
Write project documentation including READMEs, API docs, and guides. Use this skill when documentation is requested or after a feature has shipped.
Best use case
Documentation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Write project documentation including READMEs, API docs, and guides. Use this skill when documentation is requested or after a feature has shipped.
Teams using Documentation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/documentation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Documentation Compares
| Feature / Agent | Documentation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Write project documentation including READMEs, API docs, and guides. Use this skill when documentation is requested or after a feature has shipped.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Skill: Documentation ## Metadata | Field | Value | |-------|-------| | **Skill ID** | SKL-0024 | | **Version** | 1.0 | | **Owner** | documenter | | **Inputs** | Task description, STATE.md, DECISIONS.md, source code, README.md, docs/ | | **Outputs** | Documentation files, STATE.md updated | | **Triggers** | `DOCS_REQUESTED`, `FEATURE_SHIPPED` | --- ## Purpose Make the project understandable to any developer who picks it up cold. Documentation is a first-class deliverable. Every public API is documented. Every setup step is tested. Every decision that affects future developers is recorded. --- ## Procedure 1. **Identify what needs documenting:** - Read STATE.md for recently completed tasks - Read DECISIONS.md for architectural context - Determine type: new README, feature update, API reference, setup guide, code comments, or changelog 2. **Identify the audience:** - **Solo developer (self):** terse, focus on "why" not "what" - **External developer / open source:** zero context assumed, cover prerequisites, setup, examples, common errors - **Non-technical stakeholder:** plain language, no code blocks, focus on what it does - **AI coding assistant:** structured, precise, explicit file paths, exact commands 3. **README structure** (when creating from scratch): - Project name + one-sentence description - What it does (2-4 sentences, user-facing, no jargon) - Quick start (minimum steps, every command tested and exact) - Configuration table (variable, required, description, example) - Project structure (directory tree with descriptions) - API reference (link or inline) - Contributing guide - License 4. **API documentation format** (for every public endpoint/function): - Method + path - Description (one sentence) - Auth required (yes/no) - Request body with types - Success response with example - Error responses table - curl example 5. **CHANGELOG format** (Keep a Changelog): - Version + date - Sections: Added, Changed, Fixed, Removed - One-sentence descriptions 6. **Quality checks before finishing:** - Every setup command is exact and tested - No placeholder text left unfilled - All code examples are syntactically correct - File paths match actual project structure - Prerequisites listed with minimum versions - Quick start gets user to working state in under 5 minutes 7. **Update STATE.md.** --- ## Constraints - Never modifies application logic (except adding inline comments) - Never documents features that don't exist yet - Never leaves placeholder text in delivered documentation - Always writes setup instructions as if reader has never seen the project - Always uses exact commands — never "run the install command" without specifying it --- ## Primary Agent documenter --- ## Definition of Done - [ ] Documentation matches actual project state - [ ] Quick start instructions are complete and correct - [ ] All public APIs documented with request/response examples - [ ] No placeholder text remaining - [ ] CHANGELOG updated if a feature was shipped - [ ] STATE.md updated with files created/modified ## Output Contract | Field | Value | |-------|-------| | **Artifacts** | Documentation files (`README.md`, `docs/*.md`, `CHANGELOG.md`, API references) | | **State Update** | `.claude/project/STATE.md` — mark task complete, log files modified | | **Handoff Event** | `TASK_COMPLETED` (no mandatory next step) |
Related Skills
Supply Chain Audit
Audit the dependency supply chain for security risks beyond what `npm audit` or `pip audit` catches. Analyzes dependency health, maintainer trust signals, typosquatting risk, and transitive dependency exposure.
SEO Audit
Audit web pages for search engine optimization: meta tags, heading hierarchy, structured data, image optimization, mobile-friendliness, and content quality. Complements SKL-0013 (Growth & Distribution) by validating what was built.
Pitch Deck
Create a structured pitch deck outline for investors, stakeholders, or partners. Covers problem, solution, market, traction, team, and ask. Natural output after PRD + Problem Stress Test validation.
Launch Checklist
Pre-launch validation covering everything deployment (SKL-0021) doesn't: analytics, error tracking, social meta, legal pages, email setup, DNS, SSL, and go-live readiness. Produces a launch readiness report with pass/fail checklist. Use this skill before going live on any project.
Insecure Defaults Detection
Detect insecure default configurations, hardcoded credentials, fail-open security patterns, and dangerous default values in application code and configuration files. Complements SKL-0015 (Security Audit) by focusing on configuration-level vulnerabilities that dependency scanners miss.
Differential Security Review
Security-focused review of code changes using git diff analysis. Identifies security implications of recent modifications — new attack surfaces, removed protections, changed auth logic, and risky refactors. Complements SKL-0016 (Code Review) with a security lens on diffs.
Copywriting
Write conversion-focused copy using proven frameworks (AIDA, PAS, BAB). Produces headlines, CTAs, landing page copy, email sequences, and micro-copy. Ensures copy matches brand voice and target audience.
Competitor Analysis
Structured competitor research: features, pricing, positioning, gaps, and differentiation strategy. Feeds into PRD Writing (SKL-0004) and Problem Stress Test (SKL-0027) with better market context.
UX Design
Design user experiences including wireframes, flows, and interaction patterns. Use this skill when UX design work is requested, including onboarding flows and interface layouts.
User Acceptance Testing
Structured QA testing with four modes: diff-aware (auto-scoped to branch changes), full (systematic exploration), quick (30-second smoke test), and regression (compare against baseline). Produces health score, structured reports, and actionable bug lists. Use this skill when UAT is requested or a feature is ready for acceptance testing.
Token Audit
Audit the current project for token waste patterns. Produces a Token Health Report with scored findings and actionable fixes. Use this skill when token usage feels high, sessions are hitting limits, or before optimizing costs.
Test Writing
Write automated tests for existing or new functionality. Use this skill when tests are requested, including unit tests, integration tests, and end-to-end tests.