Découvrez les skills databases automation tools, comparez leurs dépôts et consultez leurs instructions.
Automated deployment orchestration supporting multiple environments, infrastructure as code, CI/CD pipeline management, rollback procedures, and monitoring integration. Use when Claude needs to manage deploymen...
Automated test coverage analysis with support for multiple testing frameworks, coverage reporting, gap identification, metric tracking, and quality gate enforcement. Use when Claude needs to analyze test covera...
Automated code review assistance including best practices evaluation, security vulnerability detection, performance optimization suggestions, code quality assessment, and style guide enforcement. Use when Claud...
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include website...
Code refactoring patterns and techniques for improving code quality without changing behavior. Use for cleaning up legacy code, reducing complexity, or improving maintainability.
Safely restructure code without changing behavior. Use when refactoring, cleaning up code smells, or improving code quality.
Perform comprehensive code review for quality, security, and maintainability. Use when reviewing code changes, PRs, or when asked to check code quality.
Create well-formatted git commits following conventional commit standards. Use when committing changes, writing commit messages, or asked to commit code.
Coordinate multiple AI agents working in parallel using git worktree. Use when setting up parallel development across multiple worktrees or coordinating agent work.
Self-review before completing tasks. Multi-perspective verification using Gemini CLI + Claude subagent.
Enterprise-ready web development for Next.js 16, React, and TypeScript incorporating Kaizen (continuous improvement) and Monozukuri (meticulous craftsmanship) principles. Use this skill when building web applic...
批量重命名文件，支持模式匹配和编号
分析 Git diff 并生成符合规范的提交信息
Synchronize and update documentation across the monorepo. Use when you need to "update docs", "propagate" changes, run "pnpm test" docs validation, or modify "README", "AGENTS.md", "CLAUDE.md", or ".codex" file...
Run and interpret pnpm lint, pnpm typecheck, pnpm build, and pnpm format in a Turborepo monorepo; diagnose CI-style failures; propose minimal diffs; and deliver a fix plan, files touched, and validation command...
Fast codebase search using Amp's Search tool for semantic search plus parallel Grep/glob for exact matches. Use when you need quick, comprehensive codebase reconnaissance.
Documentation specialist that writes and maintains technical docs, JSDoc/TSDoc comments, README files, API docs, and guides. Has file access (Read, create_file, edit_file). Use when creating or updating documen...
Maximum performance mode using Amp's built-in oracle, librarian, and Search tools in parallel for comprehensive analysis. Activates when you need deep, multi-dimensional research across codebase and external do...
Ruthlessly critical plan reviewer that catches gaps, ambiguities, and missing context. Read-only - cannot modify files. Use when reviewing Prometheus plans or any implementation specs before execution. Simulate...
Deep module investigation using Amp's Search for discovery, oracle for expert analysis, and mermaid for visualization. Use when you need to understand complex code, prepare for refactoring, or debug issues.
マルチモデルコードレビュー。LLMがコードレビューを行った後、GitHub Copilot CLIに精査させて双方の視点を統合した最終レビューを提供。Use when user wants multi-model code review, second opinion, or wants to cross-ch...
Git commit creation assistant with gitmoji prefixes and Japanese messages. Supports two modes staged-only (commits only staged changes) and smart-commit (analyzes all changes and creates multiple commits with a...
Manage git commit workflow with size limits and conventional commits. Use before any commit. Enforces max_commit_change_lines policy. NOTE: CHANGELOG is updated only during merge, not during individual commits.
Complete QA, playtesting, and code quality team for game development. Use when evaluating player experience, fun factor, game feel, code quality, test coverage, refactoring, performance testing, or build valida...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.