afk
AFK (Away From Keyboard) mode - enable tiered modes, check status, review sessions. Use /afk [operation] where operation is full|plan|research|monitor|off|status|review
Découvrez les skills tools llm ai, comparez leurs dépôts et consultez leurs instructions.
AFK (Away From Keyboard) mode - enable tiered modes, check status, review sessions. Use /afk [operation] where operation is full|plan|research|monitor|off|status|review
技能创建指南。当用户需要创建新技能(Skill)或更新现有技能时使用此技能。帮助扩展 Claude 在特定领域的专业能力。
MCP(Model Context Protocol)服务器开发指南。当用户需要开发 MCP 服务器、创建 LLM 工具集成、或构建 AI 代理与外部服务交互的接口时使用。
Generate or refactor AGENTS.md files following progressive disclosure principles for optimal context efficiency.
LLM working files and session context management. Use at the start of sessions to restore context, and during work to maintain state across conversations.
Deep Agents library for building complex, multi-step AI agents with planning, context management, and subagent delegation.
Git commands optimized for AI agent workflows with porcelain output and deterministic execution patterns.
Convert text to Google Chat compatible formatting (Markdown to Google Chat syntax). Use when formatting messages for Google Chat, converting Markdown documents for Google Chat, or when the user mentions Google...
GitHub Actions security and authentication for Claude Code including API keys, OIDC, AWS Bedrock, Google Vertex AI, secrets management, and permission scoping. Use when setting up authentication or discussing s...
Claude Code workflow design and automation patterns for PR reviews, issue triage, and CI/CD integration. Use when creating or modifying GitHub Actions workflows that integrate Claude Code.
Coordinate multi-agent workflows: sequential, parallel, and iterative patterns. Defines agent handoffs, dependencies, communication protocols, and integration. Use when designing multi-agent workflows, coordina...
Access Claude Blog for latest Claude Code improvements, usage patterns, and best practices. Use when researching Claude Code features, CLAUDE.md optimization, or staying current with Claude capabilities. Checks...
File-based context sharing for multi-agent workflows. Provides directory organization, agent output templates, progress tracking, and inter-agent context. Use when setting up multi-agent workflows, reading/writ...
LangGraph framework for building stateful, multi-step AI agents with graph-based workflows, persistence, and human-in-the-loop support.
Detect PRD/ADR/PRP opportunities in conversations and prompt for document creation. Activates when users discuss features, architecture decisions, or implementation planning.
LangChain JS/TS framework for building LLM-powered applications - models, chains, tools, and RAG patterns.
Orchestrate complex multi-agent workflows for development, infrastructure, and research. Provides workflow templates, agent sequences, and integration patterns. Use when planning complex projects, coordinating...
GitHub CLI commands optimized for AI agent workflows with JSON output and deterministic execution patterns.
撰写提示词、优化提示词、改写 Prompt、Prompt 优化。将模糊的想法转化为精确有效的 AI 提示词,支持 ChatGPT、Claude、Gemini、DeepSeek、豆包、智谱等多平台。
创建 Skill、写 Skill、Skill 模板。帮助创建和优化 Claude Code Skills,遵循 Testany 公司规范。
Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, CLAUDE.md bi-sync, faf-cli commands, MCP server configuration, or AI-readines...
Full-stack AI application generator with Next.js, AI SDK, and ai-elements. Use when creating chatbots, agent dashboards, or custom AI applications. Triggers: chatbot, chat app, agent dashboard, AI application,...
Vercel AI SDK v6 development. Use when building AI agents, chatbots, tool integrations, or streaming applications with the ai package.
OpenAI Agents SDK (Python) development. Use when building AI agents, multi-agent workflows, tool integrations, or streaming applications with the openai-agents package.
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.