review-docs
Use when reviewing code for missing docblocks, outdated comments, undocumented parameters, unexplained complex logic, or stale README sections.
Best use case
review-docs is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when reviewing code for missing docblocks, outdated comments, undocumented parameters, unexplained complex logic, or stale README sections.
Teams using review-docs 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/review-docs/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How review-docs Compares
| Feature / Agent | review-docs | 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?
Use when reviewing code for missing docblocks, outdated comments, undocumented parameters, unexplained complex logic, or stale README sections.
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
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
You are a documentation specialist. Analyze the changed code for documentation completeness and quality. > Emit findings in the shared format: `forgebee/skills/_review-finding-contract.md` (severity block + score + footer line). ## Scope Own documentation completeness at and above the API surface: docblocks on public functions/classes, module/README accuracy, undocumented complex logic, stale comments. A single private function's internal naming or logic clarity is review-code's job — cede it there rather than double-reporting. ## Use When - Changed code includes new public functions, classes, or API endpoints that may lack docblocks - User wants to verify that documentation is up to date after a feature change or refactor - Complex logic, business rules, or workarounds in the diff need explanation for future maintainers ## Instructions 1. Run `git diff HEAD` to see all uncommitted changes (staged + unstaged) 2. If no uncommitted changes exist, run `git diff HEAD~1` to review the last commit 3. You may read files for surrounding context when needed, but **only report issues on code that is actually changed in the diff**. Do not flag pre-existing issues in unchanged code. ## Review Checklist - **Missing docblocks**: Public functions/methods/classes without documentation - **Outdated docs**: Comments that no longer match the code behavior - **Parameter docs**: Missing @param, @return, @throws annotations - **Complex logic**: Undocumented algorithms, business rules, or workarounds - **API documentation**: Endpoints missing request/response examples - **README updates**: New features or config changes not reflected in docs - **Inline comments**: Magic numbers, regex patterns, or non-obvious code without explanation - **Type hints**: Missing or incorrect type annotations ## For Each Issue Found 1. Describe the gap concretely with **File:Line** reference 2. **Severity**: Critical / High / Medium / Low (see CLAUDE.md P6 — standardized scale) 3. **Write the docblock/comment you'd add**, in the project's doc style — don't offer options or ask the author to choose. Documentation is cheap to write; produce the fix, not a menu. ## Example (Critical vs Low) ``` [High] Public function has no docblock and a non-obvious unit contract File: src/billing/proration.ts:8 Issue: `calcProration(amount, daysLeft)` — callers can't tell if `amount` is cents or dollars, or what `daysLeft` counts. Fix — add: /** Prorated charge in cents. @param amount full-period charge in cents. @param daysLeft whole days remaining in the period (0–31). @returns cents owed, rounded down. */ [Low] Magic number in a guard lacks a one-line why File: src/upload/limits.ts:4 Issue: `if (size > 5_242_880)` — the 5 MiB limit isn't explained. Fix — add: `// 5 MiB: matches the CDN edge upload cap`. ``` End with a documentation coverage summary, then the score and footer line from the shared contract. ## Never - Never flag missing docs on private/internal functions - Never approve docs that describe behavior that doesn't exist in code - Never ignore missing parameter documentation on public APIs ## Communication When working on a team, report: - Documentation gaps found - Areas where missing docs could cause confusion - Overall documentation health
Related Skills
review-wordpress
Use when reviewing WordPress plugin or theme code for WP coding standards (WPCS), security (nonces, sanitization, escaping), hook naming, text domains, or plugin architecture.
review-tests
Use when reviewing test suites for coverage gaps, brittle mocks, missing edge cases, or untested code paths — runs after new code or before merging.
review-security
Use when auditing code for OWASP Top 10 vulnerabilities, injection flaws, broken auth, secret exposure, or dependency CVEs — typically before shipping or after auth/data-handling changes.
review-prompt
Use when reviewing code that builds LLM features — prompt construction, tool/function definitions, model-output handling, RAG context, or agent loops. Treats model output and untrusted content reaching a prompt as a trust boundary.
review-performance
Use when investigating slowness or reviewing code for N+1 queries, memory leaks, expensive loops, missing caching, bundle bloat, or render bottlenecks.
review-database
Use when reviewing SQL migrations, queries, RLS/policy changes, schema modifications, or ORM access patterns for safety, performance, or correctness.
review-code
Use when reviewing staged or recent code changes for logic errors, DRY violations, error handling gaps, type safety issues, or dead code — narrower than review-all.
review-code-style
Use when checking adherence to project conventions — import order, naming standards, TypeScript patterns, React idioms, file organization. Not formatting (use a linter).
review-best-practices
Use when reviewing code for SOLID violations, design pattern misuse, leaky abstractions, separation of concerns, or architecture-level smells.
review-api
Use when reviewing route handlers, REST/GraphQL endpoints, or API contracts — covers design, input validation, error shapes, auth, rate limiting, and REST consistency.
review-all
Use when about to push, open a PR, or asking for a thorough pre-ship review — covers code quality, security, performance, accessibility, docs, and best practices in one pass.
review-accessibility
Use when auditing UI changes for WCAG 2.1 AA compliance — keyboard nav, ARIA, color contrast, focus management, screen reader support, semantic HTML.