发现 databases automation tools 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Set up or update automated task implementation system with Ralph Wiggum Loop. Use when the user wants to create or update todolist.json, progress.txt, and ralph_wiggum_loop.sh files for automated AI-driven task...
Performs comprehensive code review on git diffs and generates review.md with quality scores, critical issues, performance concerns, and potential bugs. Use when user requests to review changes, check code quali...
Use this at the start of non-trivial work to quickly load the right runbooks (skills + path-scoped instructions) before making changes.
Reviews code changes for bugs, style issues, and best practices. Use when reviewing PRs, checking code quality, or validating changes before commit.
Fetch, preview, test, and merge GitHub PRs locally. Use when the user wants to evaluate a PR before merge.
Fetch, preview, test, and merge GitHub PRs locally. Use when the user wants to evaluate a PR before merge.
Use gh to locate failing PR checks, fetch GitHub Actions logs for actionable failures, summarize the failure snippet, then propose a fix plan and implement after explicit approval.. Use when When a user asks to...
The agent is capable of extraordinary work in this domain. These guidelines unlock that potential—they don't constrain it. Use judgment, adapt to context, and push boundaries when appropriate.. Use when When th...
Plan and guide Repo Prompt integration and usage in AI coding workflows. Use when integrating Repo Prompt with editors/agents.
Open-source repo mapping: hotspots, dependency tree, SAST, tests/coverage pointers.
Create, manage, scan, and clean up git worktrees for parallel development. Use when working on multiple branches simultaneously, isolating experiments, or when user mentions "worktree", "parallel branches", "fe...
Renovate が作成した GitHub PR の依存関係更新内容を詳細にチェックする。Renovate PR の URL が渡された時、または依存関係更新の PR をレビューする時に使用する。
Advanced codebase search using Mantic for finding files, understanding context, and analyzing code impact. Use this skill when searching for code, files, or understanding code relationships.
Build automation, task runners, and scripting tools
Enterprise-grade repository analysis with arc42/C4 architecture documentation, technical debt quantification, security assessment, and multi-stakeholder reporting
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoid...
Validates prompt files against best practices. Use after creating or editing rules, skills, agents, commands in .agents/ for quality review.
Provides code review expertise with constructive feedback. Use when conducting self-reviews before PR creation, quality checks, or best practice validation.
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...
Use pre-computed discovery files at .claude/state/ for codebase inventory questions. Triggers on component, hook, schema, form, type, inventory, what exists, list all, how many. Saves 90%+ tokens vs source scan...
Comprehensive full-stack codebase audit for Crispy CRM. Triggers on audit, deep audit, codebase review, quality check, after refactoring, new feature complete. Phased approach (Critical > Improvements > Polish)...
Evidence-based completion claims - BLOCKS claiming tests pass, builds succeed, features work, or tasks are done without running verification commands first. Enforces TDD for implementation tasks. Triggers on do...
Use when receiving or giving code review feedback, implementing review suggestions, addressing PR comments, or evaluating technical suggestions. Covers both directions - receiving feedback (verify before implem...
Guide experienced developers through REFACTOR phase of TDD cycle - improving code quality while maintaining green tests
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。