LLM & Agents

Build agentic systems using Claude CLI in headless mode or the Claude Agent SDK. Use when building automation pipelines, CI/CD integrations, multi-agent orchestration, or programmatic Claude interactions. Covers CLI flags (-p, --output-format), session management (--resume, --continue), Python SDK (claude-agent-sdk), custom tools, and agent loop patterns.

콘텐츠 품질 점검 규칙. 연령 등급, 태그, 형식 검사 기준 정의. content-quality-checker Agent가 참조.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an AI agent's capabilities with specialized knowledge, workflows, or tool integrations.

Workflow for long-running agentic development across multiple context windows. Use when working on multi-phase projects, complex feature implementations, or any development task spanning multiple sessions. Provides structured progress tracking, session handoff protocols, and incremental development patterns adapted from Anthropic's research on effective agent harnesses.

콘텐츠 생성 전체 워크플로우. "00 컨텐츠 만들자", "퀴즈 만들어줘", "투표 만들어줘" 요청 시 자동 실행. 2개 Agent 순차 호출로 2중 검증.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Configure Claude Code sandbox security with file system and network isolation boundaries

Expert on Shelby Protocol architecture, erasure coding, placement groups, read/write procedures, Clay Codes, chunking, storage providers, RPC servers, and decentralized storage system design on Aptos blockchain. Triggers on keywords Shelby Protocol, erasure coding, Clay Codes, placement groups, Shelby architecture, storage provider, blob storage, chunking, Shelby whitepaper.

Write strategic, minimal tests focusing on core user flows and critical paths, deferring edge cases and implementation details until dedicated testing phases. Use this skill when adding test files for features after implementation is complete, when writing unit tests for critical business logic, or when creating integration tests for primary user workflows. Use this skill when working with test files in tests/, __tests__/, specs/, or similar test directories. Use this skill when using testing frameworks like Jest, pytest, RSpec, or Vitest, when mocking external dependencies, or when deciding test coverage priorities. Use this skill when writing tests that focus on behavior rather than implementation details, keeping tests fast and maintainable.

Fork, clone to ~/.clank, run installer, edit CLAUDE.md

AUTOMATICALLY run Codex review after writing security-sensitive code (auth, crypto, SQL) - get a second opinion from OpenAI Codex

OpenAI REST API integration guide. Use when: making direct HTTP calls to OpenAI API,understanding API structure without SDK, debugging API requests, learning request/responseformats, handling errors and rate limits. Covers: authentication, Chat Completions,Embeddings, Images (DALL-E), Audio (Whisper/TTS), error handling, streaming.

Use for quick self-review of small changes. For comprehensive review or cross-domain changes, dispatch @code-reviewer agent instead.

Analyzes and transforms prompts using 7 research-backed frameworks (CO-STAR, RISEN, RISE-IE, RISE-IX, TIDD-EC, RTF, Chain of Thought, Chain of Density). Provides framework recommendations, asks targeted questions, and structures prompts for maximum effectiveness. Use when users need expert prompt engineering guidance.

Discovers all Claude Code agents in the system including built-in, plugin, project, and user-level agents. Use when you need to find which agents are available, understand the agent ecosystem, or prepare agents for Actoris registration.

Generates .prettierignore to exclude build outputs, dependencies, and generated files from Prettier formatting. Prevents formatting of dist/, node_modules/, and coverage/ directories.

Analyze vague user ideas and recommend architecture based on actual needs, not predefined categories. Front-end for clarifying ambiguous requests before routing to appropriate skillmaker tools.

Agent spécialisé dans l'extraction de communications email liées au financement via Gmail MCP.

Configure pgvector extension for vector search in Supabase - includes embedding storage, HNSW/IVFFlat indexes, hybrid search setup, and AI-optimized query patterns. Use when setting up vector search, building RAG systems, configuring semantic search, creating embedding storage, or when user mentions pgvector, vector database, embeddings, semantic search, or hybrid search.

Use the VSCode CLI to open files at specific line and column positions when explaining code, debugging, pointing to TODOs, or guiding users to specific locations in files. Automatically invoked when Claude needs to show users exactly where in a file to look.