Loading...
Loading...
Found 817 Skills
Captures quality metrics baseline (tests, coverage, type errors, linting, dead code) by running quality gates and storing results in memory for regression detection. Use at feature start, before refactor work, or after major changes to establish baseline. Triggers on "capture baseline", "establish baseline", or PROACTIVELY at start of any feature/refactor work. Works with pytest output, pyright errors, ruff warnings, vulture results, and memory MCP server for baseline storage.
Detect Single Responsibility Principle (SRP) violations using multi-dimensional analysis. Use when reviewing code for "SRP", "single responsibility", "god class", "doing too much", "too many dependencies", before commits, during refactoring, or as quality gate. Analyzes Python, JavaScript, TypeScript files with AST-based detection, metrics (TCC, ATFD, WMC), and project-specific patterns. Provides actionable fix guidance with refactoring estimates.
Automates architecture validation for Clean Architecture, Hexagonal, Layered, and MVC patterns. Detects layer boundary violations, dependency rule breaches, and architectural anti-patterns. Use when asked to "validate architecture", "check layer boundaries", "architectural review", before major refactoring, or as pre-commit quality gate. Adapts to project's architectural style by reading ARCHITECTURE.md.
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 completed, during code reviews, or as part of quality gates. Triggers on "detect orphaned code", "find dead code", "check for unused modules", "verify integration", or proactively before completion. Works with Python modules, functions, classes, and LangGraph nodes. Catches the ADR-013 failure pattern where code exists and tests pass but is never integrated.
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or reviewing pull requests.
Code quality gatekeeper and auditor. Enforces strict quality gates, resolves the AI verification gap, and evaluates codebases across 12 critical dimensions with evidence-based scoring. Use when auditing code quality, reviewing AI-generated code, scoring codebases against industry standards, or enforcing pre-commit quality gates. Use for quality audit, code review, codebase evaluation, security assessment, technical debt analysis.
Coding rules generator — Extract and generate coding-rules.md from project conventions. Scans CLAUDE.md, AGENTS.md, config files, existing source code, and installed skills to produce a unified coding-rules.md that spec-implement uses as a quality gate. English triggers: "Generate coding rules", "Create coding-rules.md", "Extract project rules" 日本語トリガー: 「コーディングルールを生成」「coding-rules.mdを作成」「プロジェクトルールを抽出」
Dispatch code-reviewer agent for two-stage review. Use after completing implementation tasks.
面向团队工作流的子代理开发技能（阶段3）。基于已批准的计划，按任务派发子代理实现，并执行“规格合规→代码质量”双阶段审查，必要时同步 Jira 子任务状态。
Use this when receiving code review feedback, before implementing suggestions, especially when feedback seems unclear or technically problematic - requires technical rigor and verification, not protocol execution or blind implementation
This skill should be used when the user requests actions such as 'review code', 'do a code review', 'review my branch', 'review MR !1234', or 'review PR'