Total 54,172 skills, Code Quality has 2444 skills
Showing 12 of 2444 skills
Comprehensive code review combining PR review, self-review, and quality checks. Supports reviewing PRs by number or comparing branches.
Refines code changes for better reviewability. Validates change cohesion (no mixed concerns), generates clear commit messages, creates PR/MR with reviewer-focused descriptions. Use when committing, reviewing, creating PR/MR, or mentions "commit", "review", "PR", "MR", "pull request", "merge request", "refine", "提交", "审查".
Full-codebase audit using 1M context window. Security, architecture, and dependency analysis in a single pass. Use when you need whole-project analysis.
Remove AI-generated code slop from the current branch. Use when the user says "deslop" or asks to clean up AI slop, remove AI code patterns, or clean the branch before committing.
Use when writing code - follow Google style guides where available, otherwise follow established best practices for the language
Review SQL and query code for injection risk, parameterization, indexing and performance, transactions, NULL and constraints, and dialect portability. Language-only atomic skill; output is a findings list.
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.
Unified codebase quality review: merge readiness verdict + maintainability (Clean Code) + docs-vs-code consistency. Use for code review, quality check, refactor check, outdated docs check, or merge/production readiness.
[DevOps & Infra] Run linters and fix issues for backend or frontend
This skill should be used when performing a code review on local changes on the current branch compared to the main branch. It uses multiple parallel agents to check for bugs, CLAUDE.md compliance, git history context, previous PR comments, and code comment adherence, then scores and filters findings by confidence level.
Use when explicitly asked to run the code-reviewer subagent or when another skill requires the code-reviewer agent card.
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.