Skills matching the name, description or GitHub author.
Detects orphaned code (files/functions that exist but are never imported or called in production), preventing "created but not integrated" failures. Use before marking features complete, before moving ADRs to c...
Advisor expert consultation for architecture design, second opinions, and code review. Use when: user requests Advisor, need alternative perspective, or get independent review. Advisor 是与 Claude 同等级别的顶...
A code review skill focused on identifying "leaky abstractions," architectural violations, and performance bottlenecks rather than just syntax errors.
Centralizes persona-driven code reviews (Carmack, React core, Anders, React Router, etc.) so Claude can pick or combine expert viewpoints when the user asks for a code review or perspective-specific critique.
Create custom subagents for specialized AI tasks. Use when the user wants to create a subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompt...
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...
This skill should be used when the user asks to "fix the issues", "apply the fixes", "fix what the review found", "auto-fix bugs", or wants to execute fixes for issues identified by a prior code review. Spawns...
Use when requesting code review after completing tasks, or when receiving and responding to code review feedback
Code Reviewer persona definition
Performs a human-level code review focusing on implementation, architecture, and project patterns.
Comprehensive code review with security, performance, and quality analysis
Generate a coaching guide from code review feedback to help tech leads conduct effective review discussions. Use when the user wants to discuss review items with authors, create discussion questions, or prepare...
Activates when user requests in-depth code explanation, design pattern tutorials, architecture guidance, or learning path recommendations. Do NOT use for production code reviews (use code-review). Examples: 'Ex...
Guide for writing and responding to code review comments with evidence-based claims. Use when writing PR review comments, responding to reviewer feedback, or engaging in technical discussions where claims shoul...
Python specialist for Faiston One Platform. Use when writing FastAPI endpoints, Google ADK agents, async patterns, Pydantic models, and Lambda handlers. PROACTIVE for code review and refactoring.
Create and manage workflows that guide the Agent through repetitive tasks. Use this skill when users want to create new workflows, update existing workflows, or need guidance on writing effective step-by-step w...
This skill should be used when the user asks to "finalize", "/finalize", "ship it", "ship this", "wrap up", "wrap this up", or "finish and commit". Orchestrates the complete workflow for finishing development w...
This skill should be used when the user asks to "review code", "code review", "check my changes", "review this PR", "review my implementation", "PR review", "look at my code", or when reviewing GUI automation c...
Comprehensive code review with failure scenario analysis, security checks, and prioritized fix suggestions. Use after /execute to validate implementation quality.
This skill provides guidance on using OpenAI's Codex CLI for detail-oriented code analysis. Use when the user explicitly invokes "/codex", asks to "use codex", "run codex", "have codex review", or when Claude d...
Expert-level frontend code review workflow focusing on maintainability, security, performance, and accessibility. Use when reviewing frontend diffs, PRs, components, SPAs, UI logic, or framework-specific code (...
Orchestrate multi-agent development workflows. Use when starting a new feature to coordinate architecture design, implementation, code review, and release through specialized sub-agents.
Code Reviewer persona definition
Security audit for code review and vulnerability analysis
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.