[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M782K6FECHXJWSPDKB32JGJF":3,"skill-same:01M782K6FECHXJWSPDKB32JGJF":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M782K6FECHXJWSPDKB32JGJF","agno",null,"Agno AI agent framework. Use for building multi-agent systems, AgentOS runtime, MCP server integration, and agentic AI development.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fskills_sh\u002Fs\u002Fskills-sh_delorenj_skills_agno\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agno\ndescription: Agno AI agent framework. Use for building multi-agent systems, AgentOS runtime, MCP server integration, and agentic AI development.\n---\n\n# Agno Skill\n\nComprehensive assistance with Agno development - a modern AI agent framework for building production-ready multi-agent systems with MCP integration, workflow orchestration, and AgentOS runtime.\n\n## When to Use This Skill\n\nThis skill should be triggered when:\n- **Building AI agents** with tools, memory, and structured outputs\n- **Creating multi-agent teams** with role-based delegation and collaboration\n- **Implementing workflows** with conditional branching, loops, and async execution\n- **Integrating MCP servers** (stdio, SSE, or Streamable HTTP transports)\n- **Deploying AgentOS** with custom FastAPI apps, JWT middleware, or database backends\n- **Working with knowledge bases** for RAG and document processing\n- **Debugging agent behavior** with debug mode and telemetry\n- **Optimizing agent performance** with exponential backoff, retries, and rate limiting\n\n## Key Concepts\n\n### Core Architecture\n- **Agent**: Single autonomous AI unit with model, tools, instructions, and optional memory\u002Fknowledge\n- **Team**: Collection of agents that collaborate on tasks with role-based delegation\n- **Workflow**: Multi-step orchestration with conditional branching, loops, and parallel execution\n- **AgentOS**: FastAPI-based runtime for deploying agents as production APIs\n\n### MCP Integration\n- **MCPTools**: Connect to single MCP server via stdio, SSE, or Streamable HTTP\n- **MultiMCPTools**: Connect to multiple MCP servers simultaneously\n- **Transport Types**: stdio (local processes), SSE (server-sent events), Streamable HTTP (production)\n\n### Memory & Knowledge\n- **Session Memory**: Conversation state stored in PostgreSQL, SQLite, or cloud storage (GCS)\n- **Knowledge Base**: RAG-powered document retrieval with vector embeddings\n- **User Memory**: Persistent user-specific memories across sessions\n\n## Quick Reference\n\n### 1. Basic Agent with Tools\n\n```python\nfrom agno.agent import Agent\nfrom agno.tools.duckduckgo import DuckDuckGoTools\n\nagent = Agent(\n    tools=[DuckDuckGoTools()],\n    markdown=True,\n)\n\nagent.print_response(\"Search for the latest AI news\", stream=True)\n```\n\n### 2. Agent with Structured Output\n\n```python\nfrom agno.agent import Agent\nfrom pydantic import BaseModel, Field\n\nclass MovieScript(BaseModel):\n    name: str = Field(..., description=\"Movie title\")\n    genre: str = Field(..., description=\"Movie genre\")\n    storyline: str = Field(..., description=\"3 sentence storyline\")\n\nagent = Agent(\n    description=\"You help people write movie scripts.\",\n    output_schema=MovieScript,\n)\n\nresult = agent.run(\"Write a sci-fi thriller\")\nprint(result.content.name)  # Access structured output\n```\n\n### 3. MCP Server Integration (stdio)\n\n```python\nimport asyncio\nfrom agno.agent import Agent\nfrom agno.tools.mcp import MCPTools\n\nasync def run_agent(message: str) -> None:\n    mcp_tools = MCPTools(command=\"uvx mcp-server-git\")\n    await mcp_tools.connect()\n\n    try:\n        agent = Agent(tools=[mcp_tools])\n        await agent.aprint_response(message, stream=True)\n    finally:\n        await mcp_tools.close()\n\nasyncio.run(run_agent(\"What is the license for this project?\"))\n```\n\n### 4. Multiple MCP Servers\n\n```python\nimport asyncio\nimport os\nfrom agno.agent import Agent\nfrom agno.tools.mcp import MultiMCPTools\n\nasync def run_agent(message: str) -> None:\n    env = {\n        **os.environ,\n        \"GOOGLE_MAPS_API_KEY\": os.getenv(\"GOOGLE_MAPS_API_KEY\"),\n    }\n\n    mcp_tools = MultiMCPTools(\n        commands=[\n            \"npx -y @openbnb\u002Fmcp-server-airbnb --ignore-robots-txt\",\n            \"npx -y @modelcontextprotocol\u002Fserver-google-maps\",\n        ],\n        env=env,\n    )\n    await mcp_tools.connect()\n\n    try:\n        agent = Agent(tools=[mcp_tools], markdown=True)\n        await agent.aprint_response(message, stream=True)\n    finally:\n        await mcp_tools.close()\n```\n\n### 5. Multi-Agent Team with Role Delegation\n\n```python\nfrom agno.agent import Agent\nfrom agno.team import Team\nfrom agno.tools.duckduckgo import DuckDuckGoTools\nfrom agno.tools.hackernews import HackerNewsTools\n\nresearch_agent = Agent(\n    name=\"Research Specialist\",\n    role=\"Gather information on topics\",\n    tools=[DuckDuckGoTools()],\n    instructions=[\"Find comprehensive information\", \"Cite sources\"],\n)\n\nnews_agent = Agent(\n    name=\"News Analyst\",\n    role=\"Analyze tech news\",\n    tools=[HackerNewsTools()],\n    instructions=[\"Focus on trending topics\", \"Summarize key points\"],\n)\n\nteam = Team(\n    members=[research_agent, news_agent],\n    instructions=[\"Delegate research tasks to appropriate agents\"],\n)\n\nteam.print_response(\"Research AI trends and latest HN discussions\", stream=True)\n```\n\n### 6. Workflow with Conditional Branching\n\n```python\nfrom agno.agent import Agent\nfrom agno.workflow.workflow import Workflow\nfrom agno.workflow.router import Router\nfrom agno.workflow.step import Step\nfrom agno.tools.duckduckgo import DuckDuckGoTools\nfrom agno.tools.hackernews import HackerNewsTools\n\nsimple_researcher = Agent(\n    name=\"Simple Researcher\",\n    tools=[DuckDuckGoTools()],\n)\n\ndeep_researcher = Agent(\n    name=\"Deep Researcher\",\n    tools=[HackerNewsTools()],\n)\n\nworkflow = Workflow(\n    steps=[\n        Router(\n            routes={\n                \"simple_topics\": Step(agent=simple_researcher),\n                \"complex_topics\": Step(agent=deep_researcher),\n            }\n        )\n    ]\n)\n\nworkflow.run(\"Research quantum computing\")\n```\n\n### 7. Agent with Database Session Storage\n\n```python\nfrom agno.agent import Agent\nfrom agno.db.postgres import PostgresDb\n\ndb = PostgresDb(\n    db_url=\"postgresql:\u002F\u002Fuser:pass@localhost:5432\u002Fagno\",\n    schema=\"agno_sessions\"\n)\n\nagent = Agent(\n    db=db,\n    session_id=\"user-123\",  # Persistent session\n    add_history_to_messages=True,\n)\n\n# Conversations are automatically saved and restored\nagent.print_response(\"Remember my favorite color is blue\")\nagent.print_response(\"What's my favorite color?\")  # Will remember\n```\n\n### 8. AgentOS with Custom FastAPI App\n\n```python\nfrom fastapi import FastAPI\nfrom agno.agent import Agent\nfrom agno.models.openai import OpenAIChat\nfrom agno.os import AgentOS\n\n# Custom FastAPI app\napp = FastAPI(title=\"Custom App\")\n\n@app.get(\"\u002Fhealth\")\ndef health_check():\n    return {\"status\": \"healthy\"}\n\n# Add AgentOS routes\nagent_os = AgentOS(\n    agents=[Agent(id=\"assistant\", model=OpenAIChat(id=\"gpt-5-mini\"))],\n    base_app=app  # Merge with custom app\n)\n\nif __name__ == \"__main__\":\n    agent_os.serve(app=\"custom_app:app\", reload=True)\n```\n\n### 9. Agent with Debug Mode\n\n```python\nfrom agno.agent import Agent\nfrom agno.tools.hackernews import HackerNewsTools\n\nagent = Agent(\n    tools=[HackerNewsTools()],\n    debug_mode=True,  # Enable detailed logging\n    # debug_level=2,  # More verbose output\n)\n\n# See detailed logs of:\n# - Messages sent to model\n# - Tool calls and results\n# - Token usage and timing\nagent.print_response(\"Get top HN stories\")\n```\n\n### 10. Workflow with Input Schema Validation\n\n```python\nfrom typing import List\nfrom agno.agent import Agent\nfrom agno.workflow.workflow import Workflow\nfrom agno.workflow.step import Step\nfrom pydantic import BaseModel, Field\n\nclass ResearchTopic(BaseModel):\n    \"\"\"Structured research topic with specific requirements\"\"\"\n    topic: str\n    focus_areas: List[str] = Field(description=\"Specific areas to focus on\")\n    target_audience: str = Field(description=\"Who this research is for\")\n    sources_required: int = Field(description=\"Number of sources needed\", default=5)\n\nworkflow = Workflow(\n    input_schema=ResearchTopic,  # Validate inputs\n    steps=[\n        Step(agent=Agent(instructions=[\"Research based on focus areas\"]))\n    ]\n)\n\n# This will validate the input structure\nworkflow.run({\n    \"topic\": \"AI Safety\",\n    \"focus_areas\": [\"alignment\", \"interpretability\"],\n    \"target_audience\": \"researchers\",\n    \"sources_required\": 10\n})\n```\n\n## Reference Files\n\nThis skill includes comprehensive documentation in `references\u002F`:\n\n### **agentos.md** (22 pages)\n- MCP server integration (stdio, SSE, Streamable HTTP)\n- Multiple MCP server connections\n- Custom FastAPI app integration\n- JWT middleware and authentication\n- AgentOS lifespan management\n- Telemetry and monitoring\n\n### **agents.md** (834 pages)\n- Agent creation and configuration\n- Tools integration (DuckDuckGo, HackerNews, Pandas, PostgreSQL, Wikipedia)\n- Structured outputs with Pydantic\n- Memory management (session, user, knowledge)\n- Debugging with debug mode\n- Human-in-the-loop patterns\n- Multimodal agents (audio, video, images)\n- Database backends (PostgreSQL, SQLite, GCS)\n- State management and session persistence\n\n### **examples.md** (188 pages)\n- Workflow patterns (conditional branching, loops, routers)\n- Team collaboration examples\n- Async streaming workflows\n- Audio\u002Fvideo processing teams\n- Image generation pipelines\n- Multi-step orchestration\n- Input schema validation\n\n### **getting_started.md**\n- Installation and setup\n- First agent examples\n- MCP server quickstarts\n- Common patterns and best practices\n\n### **integration.md**\n- Third-party integrations\n- API connections\n- Custom tool creation\n- Database setup\n\n### **migration.md**\n- Upgrading between versions\n- Breaking changes and migration guides\n- Deprecated features\n\n### **other.md**\n- Advanced topics\n- Performance optimization\n- Production deployment\n\n## Working with This Skill\n\n### For Beginners\nStart with **getting_started.md** to understand:\n- Basic agent creation with `Agent()`\n- Adding tools for web search, databases, etc.\n- Running agents with `.print_response()` or `.run()`\n- Understanding the difference between Agent, Team, and Workflow\n\n**Quick Start Pattern:**\n```python\nfrom agno.agent import Agent\nfrom agno.tools.duckduckgo import DuckDuckGoTools\n\nagent = Agent(tools=[DuckDuckGoTools()])\nagent.print_response(\"Your question here\")\n```\n\n### For Intermediate Users\nExplore **agents.md** and **examples.md** for:\n- Multi-agent teams with role delegation\n- MCP server integration (local tools via stdio)\n- Workflow orchestration with conditional logic\n- Session persistence with databases\n- Structured outputs with Pydantic models\n\n**Team Pattern:**\n```python\nfrom agno.team import Team\n\nteam = Team(\n    members=[researcher, analyst, writer],\n    instructions=[\"Delegate tasks based on agent roles\"]\n)\n```\n\n### For Advanced Users\nDeep dive into **agentos.md** for:\n- AgentOS deployment with custom FastAPI apps\n- Multiple MCP server orchestration\n- Production authentication with JWT middleware\n- Custom lifespan management\n- Performance tuning with exponential backoff\n- Telemetry and monitoring integration\n\n**AgentOS Pattern:**\n```python\nfrom agno.os import AgentOS\n\nagent_os = AgentOS(\n    agents=[agent1, agent2],\n    db=PostgresDb(...),\n    base_app=custom_fastapi_app\n)\nagent_os.serve()\n```\n\n### Navigation Tips\n1. **Looking for examples?** → Check `examples.md` first for real-world patterns\n2. **Need API details?** → Search `agents.md` for class references and parameters\n3. **Deploying to production?** → Read `agentos.md` for AgentOS setup\n4. **Integrating external tools?** → See `integration.md` for MCP and custom tools\n5. **Debugging issues?** → Enable `debug_mode=True` and check logs\n\n## Common Patterns\n\n### Pattern: MCP Server Connection Lifecycle\n```python\nasync def run_with_mcp():\n    mcp_tools = MCPTools(command=\"uvx mcp-server-git\")\n    await mcp_tools.connect()  # Always connect before use\n\n    try:\n        agent = Agent(tools=[mcp_tools])\n        await agent.aprint_response(\"Your query\")\n    finally:\n        await mcp_tools.close()  # Always close when done\n```\n\n### Pattern: Persistent Sessions with Database\n```python\nfrom agno.agent import Agent\nfrom agno.db.postgres import PostgresDb\n\ndb = PostgresDb(db_url=\"postgresql:\u002F\u002F...\")\n\nagent = Agent(\n    db=db,\n    session_id=\"unique-user-id\",\n    add_history_to_messages=True,  # Include conversation history\n)\n```\n\n### Pattern: Conditional Workflow Routing\n```python\nfrom agno.workflow.router import Router\n\nworkflow = Workflow(\n    steps=[\n        Router(\n            routes={\n                \"route_a\": Step(agent=agent_a),\n                \"route_b\": Step(agent=b),\n            }\n        )\n    ]\n)\n```\n\n## Resources\n\n### Official Links\n- **Documentation**: https:\u002F\u002Fdocs.agno.com\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fagno-agi\u002Fagno\n- **Examples**: https:\u002F\u002Fgithub.com\u002Fagno-agi\u002Fagno\u002Ftree\u002Fmain\u002Fcookbook\n\n### Key Concepts to Remember\n- **Always close MCP connections**: Use try\u002Ffinally blocks or async context managers\n- **Enable debug mode for troubleshooting**: `debug_mode=True` shows detailed execution logs\n- **Use structured outputs for reliability**: Define Pydantic schemas with `output_schema=`\n- **Persist sessions with databases**: PostgreSQL or SQLite for production agents\n- **Disable telemetry if needed**: Set `AGNO_TELEMETRY=false` or `telemetry=False`\n\n## scripts\u002F\nAdd helper scripts here for common automation tasks.\n\n## assets\u002F\nAdd templates, boilerplate, or example projects here.\n\n## Notes\n\n- This skill was automatically generated from official Agno documentation\n- Reference files preserve structure and examples from source docs\n- Code examples include language detection for better syntax highlighting\n- Quick reference patterns are extracted from real-world usage in the docs\n- All examples are tested and production-ready\n\n## Updating\n\nTo refresh this skill with updated documentation:\n1. Re-run the scraper with the same configuration\n2. The skill will be rebuilt with the latest information from docs.agno.com\n","# Agno Skill\n\nComprehensive assistance with Agno development - a modern AI agent framework for building production-ready multi-agent systems with MCP integration, workflow orchestration, and AgentOS runtime.\n\n## When to Use This Skill\n\nThis skill should be triggered when:\n- **Building AI agents** with tools, memory, and structured outputs\n- **Creating multi-agent teams** with role-based delegation and collaboration\n- **Implementing workflows** with conditional branching, loops, and async execution\n- **Integrating MCP servers** (stdio, SSE, or Streamable HTTP transports)\n- **Deploying AgentOS** with custom FastAPI apps, JWT middleware, or database backends\n- **Working with knowledge bases** for RAG and document processing\n- **Debugging agent behavior** with debug mode and telemetry\n- **Optimizing agent performance** with exponential backoff, retries, and rate limiting\n\n## Key Concepts\n\n### Core Architecture\n- **Agent**: Single autonomous AI unit with model, tools, instructions, and optional memory\u002Fknowledge\n- **Team**: Collection of agents that collaborate on tasks with role-based delegation\n- **Workflow**: Multi-step orchestration with conditional branching, loops, and parallel execution\n- **AgentOS**: FastAPI-based runtime for deploying agents as production APIs\n\n### MCP Integration\n- **MCPTools**: Connect to single MCP server via stdio, SSE, or Streamable HTTP\n- **MultiMCPTools**: Connect to multiple MCP servers simultaneously\n- **Transport Types**: stdio (local processes), SSE (server-sent events), Streamable HTTP (production)\n\n### Memory & Knowledge\n- **Session Memory**: Conversation state stored in PostgreSQL, SQLite, or cloud storage (GCS)\n- **Knowledge Base**: RAG-powered document retrieval with vector embeddings\n- **User Memory**: Persistent user-specific memories across sessions\n\n## Quick Reference\n\n### 1. Basic Agent with Tools\n\n```python\nfrom agno.agent import Agent\nfrom agno.tools.duckduckgo import DuckDuckGoTools\n\nagent = Agent(\n    tools=[DuckDuckGoTools()],\n    markdown=True,\n)\n\nagent.print_response(\"Search for the latest AI news\", stream=True)\n```\n\n### 2. Agent with Structured Output\n\n```python\nfrom agno.agent import Agent\nfrom pydantic import BaseModel, Field\n\nclass MovieScript(BaseModel):\n    name: str = Field(..., description=\"Movie title\")\n    genre: str = Field(..., description=\"Movie genre\")\n    storyline: str = Field(..., description=\"3 sentence storyline\")\n\nagent = Agent(\n    description=\"You help people write movie scripts.\",\n    output_schema=MovieScript,\n)\n\nresult = agent.run(\"Write a sci-fi thriller\")\nprint(result.content.name)  # Access structured output\n```\n\n### 3. MCP Server Integration (stdio)\n\n```python\nimport asyncio\nfrom agno.agent import Agent\nfrom agno.tools.mcp import MCPTools\n\nasync def run_agent(message: str) -> None:\n    mcp_tools = MCPTools(command=\"uvx mcp-server-git\")\n    await mcp_tools.connect()\n\n    try:\n        agent = Agent(tools=[mcp_tools])\n        await agent.aprint_response(message, stream=True)\n    finally:\n        await mcp_tools.close()\n\nasyncio.run(run_agent(\"What is the license for this project?\"))\n```\n\n### 4. Multiple MCP Servers\n\n```python\nimport asyncio\nimport os\nfrom agno.agent import Agent\nfrom agno.tools.mcp import MultiMCPTools\n\nasync def run_agent(message: str) -> None:\n    env = {\n        **os.environ,\n        \"GOOGLE_MAPS_API_KEY\": os.getenv(\"GOOGLE_MAPS_API_KEY\"),\n    }\n\n    mcp_tools = MultiMCPTools(\n        commands=[\n            \"npx -y @openbnb\u002Fmcp-server-airbnb --ignore-robots-txt\",\n            \"npx -y @modelcontextprotocol\u002Fserver-google-maps\",\n        ],\n        env=env,\n    )\n    await mcp_tools.connect()\n\n    try:\n        agent = Agent(tools=[mcp_tools], markdown=True)\n        await agent.aprint_response(message, stream=True)\n    finally:\n        await mcp_tools.close()\n```\n\n### 5. Multi-Agent Team with Role Delegation\n\n```python\nfrom agno.agent import Agent\nfrom agno.team import Team\nfrom agno.tools.duckduckgo import DuckDuckGoTools\nfrom agno.tools.hackernews import HackerNewsTools\n\nresearch_agent = Agent(\n    name=\"Research Specialist\",\n    role=\"Gather information on topics\",\n    tools=[DuckDuckGoTools()],\n    instructions=[\"Find comprehensive information\", \"Cite sources\"],\n)\n\nnews_agent = Agent(\n    name=\"News Analyst\",\n    role=\"Analyze tech news\",\n    tools=[HackerNewsTools()],\n    instructions=[\"Focus on trending topics\", \"Summarize key points\"],\n)\n\nteam = Team(\n    members=[research_agent, news_agent],\n    instructions=[\"Delegate research tasks to appropriate agents\"],\n)\n\nteam.print_response(\"Research AI trends and latest HN discussions\", stream=True)\n```\n\n### 6. Workflow with Conditional Branching\n\n```python\nfrom agno.agent import Agent\nfrom agno.workflow.workflow import Workflow\nfrom agno.workflow.router import Router\nfrom agno.workflow.step import Step\nfrom agno.tools.duckduckgo import DuckDuckGoTools\nfrom agno.tools.hackernews import HackerNewsTools\n\nsimple_researcher = Agent(\n    name=\"Simple Researcher\",\n    tools=[DuckDuckGoTools()],\n)\n\ndeep_researcher = Agent(\n    name=\"Deep Researcher\",\n    tools=[HackerNewsTools()],\n)\n\nworkflow = Workflow(\n    steps=[\n        Router(\n            routes={\n                \"simple_topics\": Step(agent=simple_researcher),\n                \"complex_topics\": Step(agent=deep_researcher),\n            }\n        )\n    ]\n)\n\nworkflow.run(\"Research quantum computing\")\n```\n\n### 7. Agent with Database Session Storage\n\n```python\nfrom agno.agent import Agent\nfrom agno.db.postgres import PostgresDb\n\ndb = PostgresDb(\n    db_url=\"postgresql:\u002F\u002Fuser:pass@localhost:5432\u002Fagno\",\n    schema=\"agno_sessions\"\n)\n\nagent = Agent(\n    db=db,\n    session_id=\"user-123\",  # Persistent session\n    add_history_to_messages=True,\n)\n\n# Conversations are automatically saved and restored\nagent.print_response(\"Remember my favorite color is blue\")\nagent.print_response(\"What's my favorite color?\")  # Will remember\n```\n\n### 8. AgentOS with Custom FastAPI App\n\n```python\nfrom fastapi import FastAPI\nfrom agno.agent import Agent\nfrom agno.models.openai import OpenAIChat\nfrom agno.os import AgentOS\n\n# Custom FastAPI app\napp = FastAPI(title=\"Custom App\")\n\n@app.get(\"\u002Fhealth\")\ndef health_check():\n    return {\"status\": \"healthy\"}\n\n# Add AgentOS routes\nagent_os = AgentOS(\n    agents=[Agent(id=\"assistant\", model=OpenAIChat(id=\"gpt-5-mini\"))],\n    base_app=app  # Merge with custom app\n)\n\nif __name__ == \"__main__\":\n    agent_os.serve(app=\"custom_app:app\", reload=True)\n```\n\n### 9. Agent with Debug Mode\n\n```python\nfrom agno.agent import Agent\nfrom agno.tools.hackernews import HackerNewsTools\n\nagent = Agent(\n    tools=[HackerNewsTools()],\n    debug_mode=True,  # Enable detailed logging\n    # debug_level=2,  # More verbose output\n)\n\n# See detailed logs of:\n# - Messages sent to model\n# - Tool calls and results\n# - Token usage and timing\nagent.print_response(\"Get top HN stories\")\n```\n\n### 10. Workflow with Input Schema Validation\n\n```python\nfrom typing import List\nfrom agno.agent import Agent\nfrom agno.workflow.workflow import Workflow\nfrom agno.workflow.step import Step\nfrom pydantic import BaseModel, Field\n\nclass ResearchTopic(BaseModel):\n    \"\"\"Structured research topic with specific requirements\"\"\"\n    topic: str\n    focus_areas: List[str] = Field(description=\"Specific areas to focus on\")\n    target_audience: str = Field(description=\"Who this research is for\")\n    sources_required: int = Field(description=\"Number of sources needed\", default=5)\n\nworkflow = Workflow(\n    input_schema=ResearchTopic,  # Validate inputs\n    steps=[\n        Step(agent=Agent(instructions=[\"Research based on focus areas\"]))\n    ]\n)\n\n# This will validate the input structure\nworkflow.run({\n    \"topic\": \"AI Safety\",\n    \"focus_areas\": [\"alignment\", \"interpretability\"],\n    \"target_audience\": \"researchers\",\n    \"sources_required\": 10\n})\n```\n\n## Reference Files\n\nThis skill includes comprehensive documentation in `references\u002F`:\n\n### **agentos.md** (22 pages)\n- MCP server integration (stdio, SSE, Streamable HTTP)\n- Multiple MCP server connections\n- Custom FastAPI app integration\n- JWT middleware and authentication\n- AgentOS lifespan management\n- Telemetry and monitoring\n\n### **agents.md** (834 pages)\n- Agent creation and configuration\n- Tools integration (DuckDuckGo, HackerNews, Pandas, PostgreSQL, Wikipedia)\n- Structured outputs with Pydantic\n- Memory management (session, user, knowledge)\n- Debugging with debug mode\n- Human-in-the-loop patterns\n- Multimodal agents (audio, video, images)\n- Database backends (PostgreSQL, SQLite, GCS)\n- State management and session persistence\n\n### **examples.md** (188 pages)\n- Workflow patterns (conditional branching, loops, routers)\n- Team collaboration examples\n- Async streaming workflows\n- Audio\u002Fvideo processing teams\n- Image generation pipelines\n- Multi-step orchestration\n- Input schema validation\n\n### **getting_started.md**\n- Installation and setup\n- First agent examples\n- MCP server quickstarts\n- Common patterns and best practices\n\n### **integration.md**\n- Third-party integrations\n- API connections\n- Custom tool creation\n- Database setup\n\n### **migration.md**\n- Upgrading between versions\n- Breaking changes and migration guides\n- Deprecated features\n\n### **other.md**\n- Advanced topics\n- Performance optimization\n- Production deployment\n\n## Working with This Skill\n\n### For Beginners\nStart with **getting_started.md** to understand:\n- Basic agent creation with `Agent()`\n- Adding tools for web search, databases, etc.\n- Running agents with `.print_response()` or `.run()`\n- Understanding the difference between Agent, Team, and Workflow\n\n**Quick Start Pattern:**\n```python\nfrom agno.agent import Agent\nfrom agno.tools.duckduckgo import DuckDuckGoTools\n\nagent = Agent(tools=[DuckDuckGoTools()])\nagent.print_response(\"Your question here\")\n```\n\n### For Intermediate Users\nExplore **agents.md** and **examples.md** for:\n- Multi-agent teams with role delegation\n- MCP server integration (local tools via stdio)\n- Workflow orchestration with conditional logic\n- Session persistence with databases\n- Structured outputs with Pydantic models\n\n**Team Pattern:**\n```python\nfrom agno.team import Team\n\nteam = Team(\n    members=[researcher, analyst, writer],\n    instructions=[\"Delegate tasks based on agent roles\"]\n)\n```\n\n### For Advanced Users\nDeep dive into **agentos.md** for:\n- AgentOS deployment with custom FastAPI apps\n- Multiple MCP server orchestration\n- Production authentication with JWT middleware\n- Custom lifespan management\n- Performance tuning with exponential backoff\n- Telemetry and monitoring integration\n\n**AgentOS Pattern:**\n```python\nfrom agno.os import AgentOS\n\nagent_os = AgentOS(\n    agents=[agent1, agent2],\n    db=PostgresDb(...),\n    base_app=custom_fastapi_app\n)\nagent_os.serve()\n```\n\n### Navigation Tips\n1. **Looking for examples?** → Check `examples.md` first for real-world patterns\n2. **Need API details?** → Search `agents.md` for class references and parameters\n3. **Deploying to production?** → Read `agentos.md` for AgentOS setup\n4. **Integrating external tools?** → See `integration.md` for MCP and custom tools\n5. **Debugging issues?** → Enable `debug_mode=True` and check logs\n\n## Common Patterns\n\n### Pattern: MCP Server Connection Lifecycle\n```python\nasync def run_with_mcp():\n    mcp_tools = MCPTools(command=\"uvx mcp-server-git\")\n    await mcp_tools.connect()  # Always connect before use\n\n    try:\n        agent = Agent(tools=[mcp_tools])\n        await agent.aprint_response(\"Your query\")\n    finally:\n        await mcp_tools.close()  # Always close when done\n```\n\n### Pattern: Persistent Sessions with Database\n```python\nfrom agno.agent import Agent\nfrom agno.db.postgres import PostgresDb\n\ndb = PostgresDb(db_url=\"postgresql:\u002F\u002F...\")\n\nagent = Agent(\n    db=db,\n    session_id=\"unique-user-id\",\n    add_history_to_messages=True,  # Include conversation history\n)\n```\n\n### Pattern: Conditional Workflow Routing\n```python\nfrom agno.workflow.router import Router\n\nworkflow = Workflow(\n    steps=[\n        Router(\n            routes={\n                \"route_a\": Step(agent=agent_a),\n                \"route_b\": Step(agent=b),\n            }\n        )\n    ]\n)\n```\n\n## Resources\n\n### Official Links\n- **Documentation**: https:\u002F\u002Fdocs.agno.com\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fagno-agi\u002Fagno\n- **Examples**: https:\u002F\u002Fgithub.com\u002Fagno-agi\u002Fagno\u002Ftree\u002Fmain\u002Fcookbook\n\n### Key Concepts to Remember\n- **Always close MCP connections**: Use try\u002Ffinally blocks or async context managers\n- **Enable debug mode for troubleshooting**: `debug_mode=True` shows detailed execution logs\n- **Use structured outputs for reliability**: Define Pydantic schemas with `output_schema=`\n- **Persist sessions with databases**: PostgreSQL or SQLite for production agents\n- **Disable telemetry if needed**: Set `AGNO_TELEMETRY=false` or `telemetry=False`\n\n## scripts\u002F\nAdd helper scripts here for common automation tasks.\n\n## assets\u002F\nAdd templates, boilerplate, or example projects here.\n\n## Notes\n\n- This skill was automatically generated from official Agno documentation\n- Reference files preserve structure and examples from source docs\n- Code examples include language detection for better syntax highlighting\n- Quick reference patterns are extracted from real-world usage in the docs\n- All examples are tested and production-ready\n\n## Updating\n\nTo refresh this skill with updated documentation:\n1. Re-run the scraper with the same configuration\n2. The skill will be rebuilt with the latest information from docs.agno.com\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fskills_sh\u002Fs\u002Fskills-sh_delorenj_skills_agno",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill agno",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill agno",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill agno","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fskills_sh\u002Fs\u002Fskills-sh_delorenj_skills_agno\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]