发现 数据与 AI 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。
Install, configure, and manage Claude Code security hooks that block dangerous commands and protect sensitive files. Use when setting up security protection, blocking destructive commands (rm -rf, git reset --h...
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage wo...
Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding...
Expert guidance for SQLAlchemy 2.0 + Pydantic + PostgreSQL. Use when setting up database layers, defining models, creating migrations, or any database-related work. Automatically activated for DB tasks.
Generates Product Requirements Documents for new features through guided discovery. Use when starting a new feature, creating specifications, or when user needs help defining requirements with clarifying questi...
Interviews users to build comprehensive project specifications. Use when starting a new project, feature, or when user needs help defining requirements through guided discovery.
Expert guidance for writing high-quality pytest tests. Use when writing tests, setting up fixtures, parametrizing, mocking, or reviewing test code.
Converts Product Requirements Documents into prd.json format for the Ralph autonomous agent system. Use when preparing PRDs for Ralph execution, breaking down features into atomic user stories, or when the user...
Git operations for committing, pushing, and opening PRs using gh CLI. Use when performing version control tasks.
Orchestrates the full Ralph autonomous agent pipeline from requirements gathering to execution. Use when building new features, platforms, or complex tasks that need structured development through spec-intervie...
Get plan reviewed by Gemini-3-Pro and GPT-5.2 via OpenCode. Use when reviewing plans, architecture decisions, or asking for multi-model fact-checking.
Search memory store when past insights would improve response. Recognize when user's stored breakthroughs, decisions, or solutions are relevant. Search proactively based on context, not just explicit requests.
Recognize breakthrough moments, blocking resolutions, and design decisions worth preserving. Detect high-value insights that save future time. Suggest distillation at valuable moments, not routine work.
Save complete conversation as checkpoint. Only when user explicitly requests ("save session", "checkpoint this"). Use nmem t save to automatically import Claude Code sessions.
Post Q&A entries from office hours writeups as comments to a GitHub Discussion. Use when the user wants to post writeup content to a discussion thread.
Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Supports out...
Use this skill when the user asks about email, calendar, or Gmail/Google Calendar management via GroundEffect CLI. Triggers include "search my email", "list recent emails", "check my calendar", "what's on my ca...
Creates and manages AGENTS.md files for AI agent integration. Use when the user asks to "에이전트해줘", "create agents", "AGENTS.md 만들어줘", "agents.md 업데이트", "agents 파일 검증", or needs to set up projec...
Creates git commits following team's version control guidelines. Use when the user asks to "commit changes", "create a commit", "make a commit", "커밋해줘", "변경사항 저장", "커밋 메시지 작성", "커밋 만들어줘",...
Suggests and performs code refactoring following best practices. Use when user asks to "리팩토링 해줘", "refactor this", "코드 개선해줘", "정리해줘", "클린 코드로", "중복 제거해줘", "이거 더 깔끔하게", or wants...
Performs code review following team's quality assurance guidelines. Use when the user asks to "review code", "check this code", "리뷰해줘", "코드 리뷰", "코드 검토", "이 코드 봐줘", "이거 괜찮아?", "확인해줘",...
Diagnoses and fixes errors following structured troubleshooting process. Use when user reports errors, bugs, or asks "왜 안돼?", "에러 났어", "문제 해결해줘", "디버깅 해줘", "이거 왜 이래?", "안 돼", "오류", or...
Generate multiple Vibes app variations in parallel with business models and rankings. Use when exploring different interpretations of a broad objective or loose creative prompt.
Generate React web apps with Fireproof database. Use when creating new web applications, adding components, or working with local-first databases. Ideal for quick prototypes and single-page apps that need real-...
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。