Total 50,405 skills, Code Quality has 2287 skills
Showing 12 of 2287 skills
Check work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause points, before PRs, or when something feels off.
Comprehensive Biome (biomejs.dev) integration for professional TypeScript/JavaScript development. Use for linting, formatting, code quality, and flawless Biome integration into codebases. Covers installation, configuration, migration from ESLint/Prettier, all linter rules, formatter options, CLI usage, editor integration, monorepo setup, and CI/CD integration. Use when working with Biome tooling, configuring biome.json, setting up linting/formatting, migrating projects, debugging Biome issues, or implementing production-ready Biome workflows.
.NET static analysis and code quality tools. Use when configuring analyzers, fixing warnings, or enforcing code standards.
Development workflow and quality gates for the Bun + TypeScript stack. **ALWAYS use before commits** to ensure quality gates are met. Also use when starting development or when user asks about workflow process. Examples - "before commit", "quality gates", "workflow checklist", "bun commands", "pre-commit checks".
Deep architectural audit focused on finding dead code, duplicated functionality, architectural anti-patterns, type confusion, and code smells. Use when user asks for architectural analysis, find dead code, identify duplication, or assess codebase health.
Predicts future bug hotspots by analyzing code complexity, churn, and historical defect patterns. Warns developers before a bug is even written.
Use when deciding where to catch errors. Use when errors propagate too far or not far enough. Use when designing component/service isolation.
Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md.
Review pull requests. Use when user asks to "review a PR", "/review-pr", or wants to review a pull request.
Review a spec document against codebase reality, identifying gaps and ensuring sound, robust implementations.
Research-driven code review and validation at multiple levels of abstraction. Two modes: (1) Session review — after making changes, review and verify work using parallel reviewers that research-validate every assumption; (2) Full codebase audit — deep end-to-end evaluation using parallel teams of subagent-spawning reviewers. Use when reviewing changes, verifying work quality, auditing a codebase, validating correctness, checking assumptions, finding defects, reducing complexity. NOT for writing new code, explaining code, or benchmarking.
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"