Data & AI

Scaffold, structure, and deploy the Physical AI textbook in Docusaurus with book-aware content and RAG-ready exports. Use when creating or updating the Docusaurus site, adding chapters, configuring sidebar, or deploying to GitHub Pages/Vercel.

Multi-agent architectures with LangGraph. Use when building systems with multiple collaborating agents, implementing supervisor or swarm patterns, creating hierarchical agent workflows, or designing agent handoff mechanisms. Covers langgraph-supervisor, langgraph-swarm, agent-as-tool patterns, and context engineering for multi-agent systems.

Use when request is vague, complex, or needs design exploration BEFORE implementation. Ask questions one at a time. Do NOT use for clear, mechanical tasks. Output: design ready for OpenSpec proposal.

Interactive hook creator for Claude Code. Triggers when user mentions creating hooks, PreToolUse, PostToolUse, hook validation, hook configuration, settings.json hooks, or wants to automate tool execution workflows.

Document user-facing features in a codebase. Use when asked to document features, explain what software does, or generate feature docs. Identifies features (not technical layers), then produces numbered markdown files per feature. Works with any language.

Run PHPUnit tests and fix failures using intelligent agent delegation. Use when user requests to:- Run tests (full suite, specific path, or single file)- Fix failing tests- Analyze test failures- Check test coverageDelegates to runner agent (haiku) for execution and fixer agent (sonnet) for fixes.Automatically cycles between run and fix until tests pass or human intervention needed.

프론트엔드 프로젝트 구조를 분석하고 정리하여 AI 에이전트가 활용할 수 있는 컨텍스트 문서를 생성하는 스킬. "프로젝트 구조 잡아줘", "폴더 구조 정리해줘", "아키텍처 문서화해줘", "프로젝트 초기 설정해줘" 등의 요청에 트리거된다. Next.js, Supabase, React 등 다양한 프론트엔드 스택에서 범용적으로 사용 가능하다.

VeloxTS framework assistant for building full-stack TypeScript APIs. Helps with procedures, generators (velox make), REST routes, authentication, validation, and common errors. Use when creating endpoints, adding features, debugging issues, or learning VeloxTS patterns.

Multi-agent and MCP pipeline security with 5-layer defense architecture. Use when building MCP servers, multi-agent systems, or any pipeline that handles user input to prevent prompt injection and ensure proper authorization.

Why pinning GitHub Actions to SHA-256 commits matters for supply chain security. Attack vectors from unpinned actions and comparison of tag vs SHA pinning.

Enterprise CLI tool architecture with multi-language patterns, UX/DX optimization, and production deployment strategies

Guide for building production-ready LiveKit voice AI agents with multi-agent workflows and intelligent handoffs. Use when creating real-time voice agents that need to transfer control between specialized agents, implement supervisor escalation, or build complex conversational systems.

Searches the NIST NVD database for CVE vulnerabilities using API 2.0. Returns CVE details, CVSS scores, affected software, and references. Use when user asks about "CVE", "vulnerability database", "NIST", "NVD", "security advisory", "CVE-2024", "CVE-2023", "脆弱性", "セキュリティアドバイザリ", or wants to find known vulnerabilities for specific software.

MLOps Captain - Model training, deployment, monitoring, and ML lifecycle management

Master Ancient Greek philosophical methods, vocabulary, and debates. Use for: Socratic method, Platonic dialogues, Aristotelian analysis, Stoic ethics, Epicurean philosophy, pre-Socratic thought. Triggers: 'Socrates', 'Plato', 'Aristotle', 'Stoic', 'Epicurean', 'eudaimonia', 'virtue ethics', 'elenchus', 'four causes', 'Forms', 'nous', 'logos', 'phronesis', 'ataraxia', 'apatheia', 'dialectic', 'maieutic', 'pre-Socratic', 'Heraclitus', 'Parmenides', 'the Good', 'unmoved mover'.

Manages Infisical configuration. Use when user says "Infisical에 업데이트해줘", "환경변수 동기화해줘", "이 config Infisical에 저장해줘", "strategy config 업데이트", "YAML을 Infisical로", "JSON config 저장", or wants to sync environment variables to Infisical.

Single-model conversational interaction with threading support for general-purpose queries

Analyze emotional tone, sentiment polarity, and psychological impact of text. Execute Python script for detailed sentiment analysis. Use when analyzing mood, attitude, or emotional content.

Expert guidance on dockerfile optimization, multi-stage builds, layer caching strategies, and base image selection. Activates when working with "dockerfile", "docker-compose", "multi-stage", "container optimization", "image layers", or "build cache".

Use when creating UI designs to avoid generic "AI slop" aesthetics. Enforces distinctive typography, cohesive color systems, purposeful motion, and atmospheric backgrounds. Critical for landing pages, dashboards, and branded interfaces.