code-review-documentation-checker
Verify if code changes require documentation updates. Use during code review to ensure documentation stays synchronized with code — prevents documentation drift.
Best use case
code-review-documentation-checker is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Verify if code changes require documentation updates. Use during code review to ensure documentation stays synchronized with code — prevents documentation drift.
Teams using code-review-documentation-checker 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/code-review-documentation-checker/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How code-review-documentation-checker Compares
| Feature / Agent | code-review-documentation-checker | 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?
Verify if code changes require documentation updates. Use during code review to ensure documentation stays synchronized with code — prevents documentation drift.
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.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Documentation Checker Audit code changes against documentation to prevent documentation drift — the gradual divergence between what code does and what documentation says. ## Core Principles 1. **Documentation must reflect reality** — every public API, configuration option, and behavior should be accurately documented 2. **Outdated docs are worse than no docs** — misleading documentation causes more problems than missing documentation 3. **Examples must work** — code examples in documentation should be valid and current 4. **Changes propagate** — a change in one place often requires updates in multiple documentation locations ## Review Process ### 1. Identify Code Changes Analyze the git diff to identify: - New functions, methods, or classes - Modified function signatures (parameters, return types) - Changed or removed functionality - New configuration options or environment variables - Modified interfaces or type definitions - Changed error messages or codes - New dependencies or removed dependencies ### 2. Locate Related Documentation For each change, identify documentation that may need updates: **Project-level:** `*.md` in root, `docs/` directory, `CLAUDE.md` **Code-level:** JSDoc/TSDoc comments, inline comments explaining complex logic, type definitions **API documentation:** OpenAPI/Swagger specs, endpoint descriptions **User documentation:** `docs/`, configuration guides ### 3. Analyze Documentation Gaps For each identified change, check: **Accuracy:** Does documentation describe current behavior? Are parameter names, types, return values correct? Are examples still valid? **Completeness:** Is new functionality documented? Are all parameters documented? Are edge cases and error conditions described? **Consistency:** Is terminology consistent across docs? Do cross-references still work? ### 4. Prioritize Findings - **CRITICAL**: Documentation is actively misleading or examples are broken - **IMPORTANT**: New public API lacks documentation or significant behavior change undocumented - **SUGGESTION**: Minor improvements, enhanced clarity, or optional additions ## Output Format ```markdown ## Summary Brief overview of documentation analysis scope and key findings. ## Documentation Updates Required ### Critical Issues - **[file:section]**: [What's wrong and why it's critical] - Current: [What docs say] - Actual: [What code does] - Fix: [Specific update needed] ### Important Updates - **[file:section]**: [What needs updating] - Reason: [Why this matters] - Suggestion: [How to update] ### Suggestions - **[file:section]**: [Optional improvement] ## New Documentation Needed - **[function/type/feature]**: Missing documentation - Location: Where to add it - Content: What to document ## Verified Up-to-Date - List of documentation that was checked and is current ## Documentation Quality Score [1-10 rating with brief justification] ``` ## Special Considerations **Focus on public interfaces** — internal implementation details don't always need documentation. Public APIs, exported functions, and user-facing features are priority. **Consider the audience:** - `README.md` targets new users and evaluators - API docs target developers integrating with the code - `CLAUDE.md` targets AI assistants working with the codebase - `docs/` targets the team **Check for cascade effects** — a renamed function may be referenced in multiple docs. A changed config option may appear in examples throughout. **Verify examples** — mentally trace through code examples. Flag examples that use deprecated or renamed APIs. Note examples missing error handling that's now required.
Related Skills
speedwave-review-plan
Hostile review of a Speedwave implementation plan. Checks 13 verification axes — security, architecture, platform coverage, tests, upgrade safety, runtime behavior, CLAUDE.md compliance, and more. Use this skill to verify any implementation plan before starting work.
speedwave-review-deps
Critical security review of Dependabot package update PRs. Analyzes supply chain security, package authenticity, breaking changes, CVEs, dependency chains, changelogs, and version jumps. Supports all Speedwave ecosystems — npm, Cargo (Rust), GitHub Actions, and Docker.
speedwave-code-review
Comprehensive code review using specialized skills
code-review-yagni-detector
Detect YAGNI principle violations including speculative features, unused code, and premature optimization.
code-review-type-design-analyzer
Analyze type design for encapsulation, invariant expression, usefulness, and enforcement quality.
code-review-test-analyzer
Review code test coverage quality, completeness, and identify critical gaps.
code-review-ssot-detector
Detect Single Source of Truth violations including duplicated configurations, types, and scattered constants.
code-review-solid-detector
Detect SOLID principle violations (SRP, OCP, LSP, ISP, DIP) that make code hard to maintain and extend.
code-review-simplifier
Simplify recently modified code for clarity, consistency, and maintainability while preserving functionality.
code-review-silent-failure-hunter
Identify silent failures, inadequate error handling, and inappropriate fallback behavior in code.
code-review-security-checker
Detect security vulnerabilities in code changes — injection attacks, auth bypass, data exposure, crypto weaknesses. Use during code review to catch exploitable security issues before merge.
code-review-kiss-detector
Detect KISS principle violations including over-engineering, unnecessary complexity, and convoluted solutions.