Code Review & Quality

Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.

Guidelines for writing conventional commit messages that follow project standards and trigger automated releases

一个全面的 Claude Code 会话验证系统。

Claude Code architecture advisor. Provides holistic guidance on component design and refactoring. Use when restructuring skills, rules, commands, subagents, or CLAUDE.md to ensure architectural consistency.

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

Use this skill to run npm run lint and fix linting issues. Triggers on fixing lint errors after code changes or validating code against project style guidelines.

Use when working with comprehensive review full review

Validate skill quality, completeness, and adherence to standards. Use before packaging to ensure skill meets quality requirements.

TypeScript standards and best practices with modern tooling. Use when working with TypeScript or TypeScript React files.

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

This skill should be used when the user asks to "refactor duplicate code", "apply DRY principles", "eliminate code repetition", "extract common functionality", or mentions code duplication, similar patterns, repeated logic, or reusable abstractions.

This skill should be used when retrieving and managing GitHub pull request reviews, particularly for accessing unresolved review comments, pending reviews, and reviewer feedback. Use this skill when asked to fetch PR review data, display pending comments, or check review status for a specific pull request. Also can be triggered by phrase like 'load pr review'

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

Provide concrete and actionable code-review feedback to surface bugs, risks, and testing gaps.

**Core Rule:** Use uv for all package operations, pytest for testing, ruff for formatting/linting. Write self-documenting code with minimal comments.

Audit claude-skills repository documentation with systematic 9-phase review: standards compliance, official docs verification via Context7/WebFetch, code examples accuracy, cross-file consistency, and version drift detection. Auto-fixes unambiguous issues with severity classification. Use when: investigating skill issues, major package updates detected (e.g., v1.x → v2.x), skill not verified >90 days, before marketplace submission, or troubleshooting outdated API patterns, contradictory exam...

Generate descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.

Review GitHub pull requests for code quality, security, and best practices. Use for automated PR feedback and approval workflows.

Deep analysis and investigation

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

Ultracite Rules - AI-Ready Formatter and Linter Applies to files matching: **/*.{ts,tsx,js,jsx,json,jsonc,html,vue,svelte,astro,css,yaml,yml,graphql,gql,md,mdx,grit}.

Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.

Enforce SOLID, DRY, KISS principles during implementation.

CPU profiling, benchmarking, and memory analysis for Rust applications. Use when code is slow, memory usage is high, or optimization is needed.