Total 54,409 skills, Code Quality has 2450 skills
Showing 12 of 2450 skills
Use when requesting code review, receiving code review feedback, before merging, or when handling reviewer suggestions - covers both giving and receiving review
Identify CPU and memory bottlenecks in Python code using cProfile or memory_profiler. Use to optimize mission-critical Python services.
Detect common code smells and anti-patterns providing feedback on quality issues a senior developer would catch during review. Use when user opens/views code files, asks for code review or quality assessment, mentions code quality/refactoring/improvements, when files contain code smell patterns, or during code review discussions.
Performs comprehensive codebase audit checking architecture, tech debt, security vulnerabilities, test coverage, documentation, dependencies, and maintainability. Use when auditing a project, assessing codebase health, running security scans, checking for vulnerabilities, reviewing code quality, analyzing tech debt, or asked to audit/analyze the entire codebase.
Guiding principles for writing clear, concise, human readable and maintainable Python code.
Systematically debug and diagnose issues methodically. Uses diagnostic techniques to identify root causes and implement fixes.
Code quality standards — lint (eslint/oxlint), type check (tsc), pre-commit hooks, and comment conventions. All comments must be in English.
Analyze code for performance issues and suggest optimizations. Use when users ask to "optimize this code", "find performance issues", "improve performance", "check for memory leaks", "review code efficiency", or want to identify bottlenecks, algorithmic improvements, caching opportunities, or concurrency problems.
Generate an LLM-optimized project profile for any git repository. Outputs docs/{project-name}.md covering architecture, core abstractions, usage guide, design decisions, and recommendations. Trigger: "/project-profiler", "profile this project", "為專案建側寫"
Verify that a pull request fully implements the requirements described in its linked GitHub issue. Use when asked to "verify PR implementation", "check PR coverage", "does PR implement the issue", "verify PR against issue", "is PR complete", or "PR completeness check". Extracts the linked issue from the PR body or GitHub linked issues, analyzes the diff against issue requirements, and reports either missing items or confirms 100% coverage.
Generates dead code detection configurations for loom plan verification. Provides language-specific commands, fail patterns, and ignore patterns for Rust, TypeScript, Python, Go, and JavaScript. Use when adding code quality checks to acceptance criteria or truths fields in loom plans. Dead code detection catches incomplete wiring by identifying code that exists but is never called.
Guidelines for self-explanatory code and meaningful documentation. Activate when working with comments, docstrings, documentation, code clarity, API documentation, JSDoc, or discussing code commenting strategies. Guides on why over what, anti-patterns, decision frameworks, and language-specific examples.