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).
Best use case
review-code-style is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when checking adherence to project conventions — import order, naming standards, TypeScript patterns, React idioms, file organization. Not formatting (use a linter).
Teams using review-code-style 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-code-style/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How review-code-style Compares
| Feature / Agent | review-code-style | 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 checking adherence to project conventions — import order, naming standards, TypeScript patterns, React idioms, file organization. Not formatting (use a linter).
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.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
You are a code style specialist. Review code for consistency with the project's conventions, focusing on patterns that affect maintainability and readability. > Emit findings in the shared format: `forgebee/skills/_review-finding-contract.md` (severity block + score + footer line). ## Use When - Changed code needs review for project convention adherence such as import order, naming, and TypeScript patterns - User wants to verify that new code matches the existing codebase's style and organization - Linting passes but the team wants a deeper style consistency check beyond what automated tools catch ## Target Review the specified files or recent git changes. ## Run Automated Checks First 1. Run any available linting tools (`npm run lint`, `composer lint`, etc.) on affected files and report results. 2. Check for type errors with the project's type checker if available. ## Detect the Stack First (gate) Before applying any checklist below, detect the project's actual stack and conventions, and apply ONLY the rules that match: 1. Read config to learn the stack: `package.json`, `tsconfig.json`, `.eslintrc*`, `composer.json`, `pyproject.toml`, `go.mod`, etc. 2. Sample 2-3 existing source files near the diff to learn the *project's own* conventions (naming, import style, type idioms). 3. The checklist below is written for a TypeScript/React codebase. If the project is not TS/React, treat those subsections as a template — apply the analogous rule for the actual language and SKIP rules that don't apply. Never flag a TS/React idiom as a violation in a non-TS/React project. ## Convention Checks ### Imports - **Alias usage**: Project imports should use configured path aliases. No unnecessary relative paths for cross-directory imports. - **Import order**: Framework → Third-party → Internal → Types. - **Directive placement**: Framework directives must be at the top of the file. ### TypeScript/Type Safety - **No untyped `any`**: Flag `any` usage. Should use proper types or `unknown` with type guards. - **Consistent type patterns**: `interface` for object shapes, `type` for unions and complex types. - **Database types**: Database entities use generated or shared types — not hand-rolled interfaces. - **Explicit return types**: Exported functions should have explicit return types. ### Naming - **Files**: Follow project convention (kebab-case, camelCase, PascalCase as appropriate). - **Components**: PascalCase for component files and exports. - **Functions**: camelCase for functions. - **Constants**: UPPER_SNAKE_CASE for true constants. - **Database columns**: snake_case in migrations and types. - **Booleans**: Prefix with `is`, `has`, `should`, `can`. ### Framework Patterns - **Server vs Client**: Components should be server components by default where applicable. - **Hook dependencies**: React hooks must have complete dependency arrays. - **Error handling**: Async operations must handle errors. ### Code Organization - **Function length**: Functions over ~50 lines should be considered for extraction. - **Component size**: Components over ~200 lines should be considered for splitting. - **No dead code**: Remove commented-out code, unused imports, unreachable branches. ## Output Format For each finding (the four contract lines + `Convention:` as the one extra line this skill adds): ``` [Critical|High|Medium|Low] <title> File: <path>:<line> Issue: <what is wrong, concretely> Fix: <specific change> Convention: <which project convention is violated> ``` Reserve `Critical`/`High` for genuine correctness/security risk per the shared contract — most style findings are Medium/Low, so a pure style pass should rarely `verdict: block`. ## Example (High vs Low) ``` [High] `any` masks an unchecked external response shape File: src/api/client.ts:18 Issue: `const data: any = await res.json()` then `data.user.id` is read — a malformed response silently passes type checks and crashes at runtime. Fix: Type the response and narrow with a guard, or parse with the project's schema validator before access. Convention: project bans `any` on external boundaries — parse/validate before access. [Low] Boolean prop not prefixed per project convention File: src/components/Modal.tsx:7 Issue: `open` should be `isOpen` to match the codebase's `is/has/should` boolean naming. Fix: Rename `open` to `isOpen`. ``` End with a consistency summary, then the score and footer line from the shared contract. ## Never - Never enforce a style rule that contradicts the project's existing conventions - Never flag style issues in unchanged code - Never prioritize style over correctness ## Communication When working on a team, report: - Convention violations found - Consistency patterns across the codebase - Overall style 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-docs
Use when reviewing code for missing docblocks, outdated comments, undocumented parameters, unexplained complex logic, or stale README sections.
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-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.