Skills matching the name, description or GitHub author.
Routes tasks to appropriate Task tool agents (subagents). Triggers on complex multi-step tasks, research, code review, exploration, or any task benefiting from specialized agent execution. Matches intent to age...
Full-context code review with multi-pass synthesis
AI-powered code review using CodeRabbit CLI. Use when reviewing code changes, checking PR readiness, getting feedback on staged/committed changes, or when the user mentions code review, CodeRabbit, or wants the...
Reviews code for logic flaws, edge cases, performance bottlenecks, security vulnerabilities, maintainability concerns, architecture best practices, and adherence to local patterns and CLAUDE.md guidelines. Use...
Get git records for specified users and days, perform code review for each commit, and generate detailed code review reports
Write and generate code using memex-cli with Codex backend. Use when (1) Generating code files and scripts, (2) Refactoring existing code, (3) Writing tests, (4) Creating project scaffolds, (5) Implementing alg...
Right-side-of-V verification/validation orchestration for a change or PR. Produces a single Quality Gate Report with evidence covering: code review, security audit, performance regression risk, requirements tra...
Use when collaborating with other AI assistants (Codex, Gemini, Aider, Cursor, OpenCode), delegating tasks, or requesting code review.
Review and finalize (REVIEWER + DOCUMENTER phases) - runs adversarial code review, commits changes, completes task, and records reflection to capture pattern outcomes.
Review and finalize (REVIEWER + DOCUMENTER phases) - runs adversarial code review, commits changes, completes task, and submits reflection to update pattern trust scores.
This skill should be used when writing code in any opinionated framework's distinctive style. It applies when writing framework-based applications, creating models/controllers/views, or any framework code. Trig...
This skill should be used when managing the file-based todo tracking system in the .claude/todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and in...
Code review checklist and patterns for thorough PR reviews
Assists with code review by analyzing code changes for quality, best practices, security, and potential issues. Activates after implementing code features, bug fixes, or refactorings. Provides structured feedba...
Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating with Grok, Gemini, GPT-5, DeepSeek, or Claudish proxy for code review, consensus analysis,...
Software engineering best practices for code review. Use when reviewing code, analyzing code quality, checking for bugs, security vulnerabilities, or providing feedback on code changes.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
Systematic code review workflow. Use this when asked to review code, PRs, or assess code quality.
Comprehensive code review before committing changes. Verifies alignment with specifications, ensures consistency, runs tests with 50%+ coverage requirement, and evaluates architecture and maintainability. Use w...
Comprehensive GitHub code review with AI-powered swarm coordination
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Fe...
This skill should be used when working on architectural decisions, complex refactoring, system design, API redesign, or multi-component implementations. Also use when asked to "consult codex", "get a second opi...
Reviews code for quality, security, and maintainability. Use after implementing features, completing significant work, or when user asks for code review.
Reviews code for quality, security, and maintainability. Use after implementing features, completing significant work, or when user asks for code review.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.