Use this skill whenever the user wants to design, build, evaluate, or debug AI agent systems, RAG pipelines, or LLM-powered applications. Triggers include: any mention of 'agent', 'AI agent', 'agentic', 'autonomous agent', 'multi-agent', 'ReAct', 'chain of thought', 'tool use', 'function calling', 'RAG', 'retrieval augmented generation', 'vector search', 'semantic search', 'embedding pipeline', 'chunking strategy', 'LangChain', 'LangGraph', 'LlamaIndex', 'CrewAI', 'AutoGen', 'Claude agent', 'agent SDK', 'Letta', 'MemGPT', 'agent memory', 'context window management', 'prompt engineering', 'system prompt', 'guardrails', 'agent evaluation', 'LLM evaluation', 'hallucination', 'grounding', 'citation', 'agent orchestration', 'planning agent', 'coding agent', 'research agent', 'agent loop', 'agent tools', 'MCP tools', 'structured output', 'JSON mode', 'streaming', 'agent observability', 'agent testing', or any request to build an AI-powered application, design agent workflows, implement RAG, evaluate LLM outputs, or architect systems where LLMs make decisions and take actions. Also use when the user asks 'how do I build an AI agent?', 'how should I chunk my documents?', 'why is my RAG returning bad results?', or wants to connect an LLM to external tools and data. If someone is building anything where an LLM reasons and acts, use this skill.
Create agent company packages conforming to the Agent Companies specification (agentcompanies/v1). Use when a user wants to create a new agent company from scratch, build a company around an existing git repo or skills collection, or scaffold a team/department of agents. Triggers on: "create a company", "make me a company", "build a company from this repo", "set up an agent company", "create a team of agents", "hire some agents", or when given a repo URL and asked to turn it into a company. Do NOT use for importing an existing company package (use the CLI import command instead) or for modifying a company that is already running in Paperclip. --- # Company Creator Create agent company packages that conform to the Agent Companies specification.
- 📁 assets/
- 📁 references/
- 📁 scripts/
- 📄 .gitignore
- 📄 _meta.json
- 📄 bridge_simple.py
IMClaw 跨网通信能力 — 让 AI Agent 具备实时聊天能力。用于：(1) Agent 需要与其他 Agent 实时通信，(2) 管理群聊，(3) 订阅和接收群聊消息，(4) 构建聊天机器人或协作 Agent。触发词：imclaw、跨网通信、agent 聊天、群聊、实时消息、龙虾。
Register this AI agent on-chain via ERC-8004 Identity Registry on Base, link to the Augmi marketplace, check reputation. Use this skill when setting up a new agent or checking registration status.
- 📁 examples/
- 📁 references/
- 📄 SKILL.md
This skill should be used when the user asks to "configure agents", "create a custom agent", "set up agent permissions", "customize agent behavior", "switch agents", or needs guidance on OpenCode agent system.
- 📁 references/
- 📄 .gitignore
- 📄 README.md
- 📄 README_EN.md
Production-grade Agent development methodology extracted from Claude Code. 7-dimension framework covering tool design, system prompts, permission & safety, multi-agent orchestration, token economy, memory/state, and extensibility. Supports architecture design, implementation guidance, and agent review. Trigger on "Agent design", "build an agent", "AI agent", "tool design", "system prompt architecture", "agent review", "multi-agent", or any agent development concern.
- 📁 .github/
- 📁 .vscode/
- 📁 docs/
- 📄 .env.example
- 📄 .gitattributes
- 📄 .gitignore
Build AI agents using ya-agent-sdk with Pydantic AI. Covers agent creation via create_agent(), toolset configuration, session persistence with ResumableState, subagent hierarchies, and browser automation. Use when creating agent applications, configuring custom tools, managing multi-turn sessions, setting up hierarchical agents, or implementing HITL approval flows.
Advanced Boss orchestration patterns — Agent Teams leadership, 6-section delegation template, Skill vs Agent conflict resolution, Guardian pattern, and AI-slop detection.
Use when the user asks about Agent SDK permissions, canUseTool callback, permission modes, hooks system, PreToolUse/PostToolUse, custom subagents, agent definitions, structured output, outputFormat, sandbox configuration, budget controls, maxTurns, file checkpointing, or thinking/effort configuration.
- 📁 references/
- 📄 .gitignore
- 📄 README.md
- 📄 SKILL.md
Hardware-secured Solana wallet, trading terminal, and agent identity layer. Trade on Jupiter DEX, earn DeFi yield, snipe meme coins with rug-pull detection, build trading bots — plus agent identity, encrypted agent-to-agent messaging, and service discovery for autonomous agent commerce. All signed by Apple Secure Enclave (no .env private keys). TRIGGER when: user mentions Solana, SOL, USDC, SPL tokens, Jupiter, Raydium, swap, DEX, meme coin, token price, DeFi yield, lending, on-chain balance, crypto wallet, send crypto, pay crypto, sign message, agent identity, agent messaging, agent commerce, agent discovery, copy trading, whale tracking, trading bot, or any Solana token symbol/mint address. Also trigger when: user asks to check a token, buy/sell tokens, transfer funds on Solana, earn yield, or interact with other AI agents economically.
Review Agent Skill directories and SKILL.md files against best practices. Use this skill when the user wants to review, validate, or check an Agent Skill implementation.
- 📁 reference/
- 📄 config.json
- 📄 SKILL.md
Map task types to the best agent, skill, model, and fallback. Route any task to the right tool. Use when: which agent, route task, agent for this, best agent, capability matrix.
