Skill Claude CodeCodex
Best practices for using Cursor—rules, commands, skills, subagents, ignore files, Agent security, workflows, and community resources. Use when setting up Cursor, initializing or creating the .cursor folder, writing .cursor/rules or AGENTS.md, creating commands or skills, configuring .cursorignore, working with Agent…
Agent
Reviews code for accessibility (a11y) compliance, ensuring WCAG standards and best practices are met. Use to ensure accessibility standards are met.
Agent
Reviews code for architectural patterns, design decisions, and structure; reports findings without editing code. Use for architectural reviews and design pattern analysis.
Agent
Investigates and identifies bugs in code, focusing on root cause analysis. Use for isolated debugging sessions separate from implementation.
Agent
Reviews and manages dependencies including updates, security audits, and compatibility checks. Use to keep dependencies up-to-date and secure.
Agent
Generates and updates documentation including API docs, README sections, inline comments, and architecture overviews. Use to keep documentation up-to-date as code changes.
Agent
Formats code according to project standards, ensuring consistent style. Use for dedicated formatting tasks or maintaining consistent code style.
Agent
Reviews code for linting and code style issues; reports findings without editing code. Use for parallel linting review while main agent implements features.
Agent
Handles code migrations including framework upgrades, API changes, and systematic refactoring with careful change tracking. Use for dedicated migration tasks with validation.
Agent
Analyzes code for performance issues and bottlenecks, identifying optimization opportunities. Use for performance-focused reviews separate from functional reviews.
Agent
Refactors code while maintaining functionality, focusing on code quality improvements. Use for dedicated refactoring tasks separate from feature development.
Agent
Reviews code for correctness, security, quality, and tests; reports findings without editing code. Use for parallel code review while main agent implements features.
Agent
Performs security-focused reviews for injection, auth, secrets, and dependencies; reports vulnerabilities without editing code. Use for dedicated security review separate from general code review.
Agent
Writes and updates tests for code changes, focusing on test coverage and quality. Use for parallel test writing while main agent implements features.
Agent
Generates types from schemas, APIs, or data structures including OpenAPI, GraphQL, JSON schemas, and API responses. Use for type generation from various sources.
Agent
Validates work by running tests, lint, and checks; reports pass/fail and any failures. Use for verification before considering a task complete.
Command
Analyze the project's dependency tree, identify unused or duplicate dependencies, and suggest optimizations.
Command
Check test coverage, identify gaps, and suggest which code needs tests.
Command
Review the code changes in this conversation (or the files I've @-mentioned) systematically.
Command
Generate or update documentation for the code I've @-mentioned (or the current feature/area we're working on).
Command
Command "fix-issue" from HKTITAN/cursor-best-practices, covering steps and rules.
Command
Format code according to the project's formatting standards.
Command
Generate TypeScript types or type definitions from schemas, APIs, or data structures.
Command
Run the project's linter, auto-fix what can be fixed, and report remaining issues.