[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73FVG002K3BAW0GECPYXAYB":3,"skill-same:01M73FVG002K3BAW0GECPYXAYB":68},{"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":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M73FVG002K3BAW0GECPYXAYB","smolagents",null,"Build lightweight AI agents with HuggingFace Smolagents — use CodeAgent (writes Python to act) or ToolCallingAgent (JSON tool calls), add built-in or custom Tools, orchestrate multi-agent pipelines with ManagedAgent, and run locally or via HF Inference API.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fsmolagents\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: smolagents\ndescription: Build lightweight AI agents with HuggingFace Smolagents — use CodeAgent (writes Python to act) or ToolCallingAgent (JSON tool calls), add built-in or custom Tools, orchestrate multi-agent pipelines with ManagedAgent, and run locally or via HF Inference API.\ntriggers:\n  - \"smolagents\"\n  - \"smol agents\"\n  - \"huggingface agents\"\n  - \"code agent smolagents\"\n  - \"smolagents tool\"\n  - \"smolagents codeagent\"\n  - \"smolagents toolcallingagent\"\n  - \"smolagents managed agent\"\n  - \"smolagents multi agent\"\n  - \"hf agent framework\"\n  - \"smolagents web search\"\n  - \"transformers agents\"\ndo_not_use_for:\n  - Complex multi-agent crews with roles — use crewai instead\n  - State graph agents — use langgraph instead\n  - Workflow automation — use n8n-automation instead\nsee_also:\n  - crewai\n  - langgraph\n  - pydantic-ai\n---\n\n# Smolagents — Lightweight HuggingFace Agents\n\n**Source:** huggingface\u002Fsmolagents (Apache 2.0) — minimal, fast, code-first agent framework\n\n## Why Smolagents\n\n- **CodeAgent**: writes and executes Python code as actions (more flexible than JSON tool calls)\n- **Tiny footprint**: ~1K lines of core code, easy to understand and customize\n- **HF-native**: works with Transformers, Inference API, Hub models\n- **Multi-agent**: orchestrate agents calling other agents via `ManagedAgent`\n\n## Install\n\n```bash\npip install smolagents\n# Optional extras\npip install smolagents[transformers]  # local models\npip install smolagents[gradio]        # Gradio UI\npip install smolagents[vision]        # multimodal\npip install smolagents[toolkit]       # built-in tools\n```\n\n## Quick Start\n\n```python\nfrom smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel\n\nagent = CodeAgent(\n    tools=[DuckDuckGoSearchTool()],\n    model=HfApiModel(\"Qwen\u002FQwen2.5-72B-Instruct\"),\n)\n\nresult = agent.run(\"What are the top 3 AI news stories today?\")\nprint(result)\n```\n\n## Models\n\n```python\nfrom smolagents import (\n    HfApiModel,           # HuggingFace Inference API\n    LiteLLMModel,         # 100+ providers via LiteLLM\n    TransformersModel,    # local Transformers model\n    OpenAIServerModel,    # any OpenAI-compatible endpoint\n    AmazonBedrockServerModel,\n)\n\n# HuggingFace Inference API (free tier available)\nmodel = HfApiModel(\"Qwen\u002FQwen2.5-Coder-32B-Instruct\")\n\n# Claude via LiteLLM\nmodel = LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\", api_key=\"your-key\")\n\n# OpenAI\nmodel = LiteLLMModel(\"openai\u002Fgpt-4o\")\n\n# Local with Transformers\nmodel = TransformersModel(\n    model_id=\"Qwen\u002FQwen2.5-7B-Instruct\",\n    device_map=\"auto\",\n    torch_dtype=\"bfloat16\",\n)\n\n# Ollama (OpenAI-compatible)\nmodel = OpenAIServerModel(\n    model_id=\"llama3.2\",\n    api_base=\"http:\u002F\u002Flocalhost:11434\u002Fv1\",\n    api_key=\"ollama\",\n)\n```\n\n## Agent Types\n\n### CodeAgent (default — recommended)\n\nWrites Python code as actions. More flexible, can do multi-step computation.\n\n```python\nfrom smolagents import CodeAgent, LiteLLMModel\n\nagent = CodeAgent(\n    tools=[],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n    max_steps=10,\n    verbosity_level=2,  # 0=silent, 1=steps, 2=full\n)\n\n# Agent writes and executes Python code to answer\nresult = agent.run(\"Calculate the compound interest on $10,000 at 5% for 10 years\")\nprint(result)\n```\n\n### ToolCallingAgent (JSON tool calls)\n\nUses standard function-calling API. More predictable, less flexible.\n\n```python\nfrom smolagents import ToolCallingAgent, DuckDuckGoSearchTool, LiteLLMModel\n\nagent = ToolCallingAgent(\n    tools=[DuckDuckGoSearchTool()],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n)\n\nresult = agent.run(\"Search for the latest news about LLMs\")\n```\n\n## Built-in Tools\n\n```python\nfrom smolagents import (\n    DuckDuckGoSearchTool,     # web search\n    WikipediaSearchTool,      # Wikipedia\n    VisitWebpageTool,         # fetch web page content\n    PythonInterpreterTool,    # run Python code (for ToolCallingAgent)\n    FinalAnswerTool,          # explicit answer tool\n    UserInputTool,            # ask user for input\n    SpeechToTextTool,         # transcribe audio\n    TextToImageTool,          # generate image\n)\n\n# Combine tools\nagent = CodeAgent(\n    tools=[\n        DuckDuckGoSearchTool(),\n        VisitWebpageTool(),\n        WikipediaSearchTool(),\n    ],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n)\n```\n\n## Custom Tools\n\n### Decorator style (simplest)\n\n```python\nfrom smolagents import tool\n\n@tool\ndef get_stock_price(ticker: str) -> str:\n    \"\"\"\n    Get the current stock price for a ticker symbol.\n\n    Args:\n        ticker: Stock ticker symbol (e.g., 'AAPL', 'GOOGL')\n    \"\"\"\n    # your implementation\n    price = fetch_price(ticker)\n    return f\"{ticker}: ${price:.2f}\"\n\nagent = CodeAgent(tools=[get_stock_price], model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"))\nresult = agent.run(\"What is Apple's current stock price?\")\n```\n\n### Class style (for complex tools)\n\n```python\nfrom smolagents import Tool\n\nclass DatabaseQueryTool(Tool):\n    name = \"database_query\"\n    description = \"Execute a SQL query against the company database\"\n    inputs = {\n        \"query\": {\n            \"type\": \"string\",\n            \"description\": \"SQL query to execute (SELECT only)\",\n        }\n    }\n    output_type = \"string\"\n\n    def __init__(self, connection_string: str):\n        super().__init__()\n        self.conn = connect(connection_string)\n\n    def forward(self, query: str) -> str:\n        if not query.strip().upper().startswith(\"SELECT\"):\n            raise ValueError(\"Only SELECT queries allowed\")\n        results = self.conn.execute(query).fetchall()\n        return str(results)\n\ndb_tool = DatabaseQueryTool(\"postgresql:\u002F\u002Flocalhost\u002Fmydb\")\nagent = CodeAgent(tools=[db_tool], model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"))\n```\n\n## Multi-Agent Orchestration\n\n```python\nfrom smolagents import CodeAgent, ManagedAgent, DuckDuckGoSearchTool, LiteLLMModel\n\nmodel = LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\")\n\n# Specialized web research agent\nweb_agent = CodeAgent(\n    tools=[DuckDuckGoSearchTool(), VisitWebpageTool()],\n    model=model,\n    name=\"web_researcher\",\n    description=\"Expert at finding information on the web\",\n)\n\n# Wrap it as a managed agent (callable by orchestrator)\nmanaged_web = ManagedAgent(\n    agent=web_agent,\n    name=\"web_researcher\",\n    description=\"Use this agent to search the web for information\",\n)\n\n# Orchestrator calls managed agents as tools\norchestrator = CodeAgent(\n    tools=[managed_web],\n    model=model,\n)\n\nresult = orchestrator.run(\n    \"Research AI trends in 2025 and write a comprehensive report\"\n)\n```\n\n## Vision \u002F Multimodal\n\n```python\nfrom smolagents import CodeAgent, LiteLLMModel\nfrom PIL import Image\n\nmodel = LiteLLMModel(\"anthropic\u002Fclaude-opus-4-5\")\n\nagent = CodeAgent(tools=[], model=model)\n\n# Pass image as input\nimage = Image.open(\"chart.png\")\nresult = agent.run(\n    \"Analyze this chart and extract the key data points\",\n    images=[image],\n)\n```\n\n## Memory \u002F Context\n\n```python\nfrom smolagents import CodeAgent, LiteLLMModel\n\nagent = CodeAgent(tools=[], model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"))\n\n# First run\nagent.run(\"My name is Alice and I work in AI\")\n\n# Continue — agent has memory of previous run\nresult = agent.run(\"What do you know about me?\")\n\n# Reset memory\nagent.memory.reset()\n```\n\n## Gradio UI\n\n```python\nfrom smolagents import CodeAgent, DuckDuckGoSearchTool, LiteLLMModel, GradioUI\n\nagent = CodeAgent(\n    tools=[DuckDuckGoSearchTool()],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n)\n\nGradioUI(agent).launch()\n```\n\n## Sandbox Safety (Docker\u002FE2B)\n\n```python\nfrom smolagents import CodeAgent, LiteLLMModel, E2BSandbox\n\n# Run code in isolated E2B sandbox\nagent = CodeAgent(\n    tools=[],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n    executor_type=\"e2b\",  # requires e2b API key\n)\n\n# Or local Docker sandbox\nfrom smolagents import LocalPythonInterpreter\nagent = CodeAgent(\n    tools=[],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n    executor_type=\"local\",\n    additional_authorized_imports=[\"pandas\", \"numpy\", \"matplotlib\"],\n)\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `CodeAgent` writes + executes Python — different from `ToolCallingAgent` which uses JSON\n- [ ] `@tool` docstring format matters: first line = description, then `Args:` block\n- [ ] `ManagedAgent` wraps an agent to make it callable as a tool by the orchestrator\n- [ ] `additional_authorized_imports` needed for non-stdlib packages in local executor\n- [ ] `agent.run()` returns the final answer string, not a structured object\n- [ ] `verbosity_level=2` shows intermediate code steps — useful for debugging\n- [ ] Memory is per-agent-instance; create new instance or call `.memory.reset()` to clear\n","# Smolagents — Lightweight HuggingFace Agents\n\n**Source:** huggingface\u002Fsmolagents (Apache 2.0) — minimal, fast, code-first agent framework\n\n## Why Smolagents\n\n- **CodeAgent**: writes and executes Python code as actions (more flexible than JSON tool calls)\n- **Tiny footprint**: ~1K lines of core code, easy to understand and customize\n- **HF-native**: works with Transformers, Inference API, Hub models\n- **Multi-agent**: orchestrate agents calling other agents via `ManagedAgent`\n\n## Install\n\n```bash\npip install smolagents\n# Optional extras\npip install smolagents[transformers]  # local models\npip install smolagents[gradio]        # Gradio UI\npip install smolagents[vision]        # multimodal\npip install smolagents[toolkit]       # built-in tools\n```\n\n## Quick Start\n\n```python\nfrom smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel\n\nagent = CodeAgent(\n    tools=[DuckDuckGoSearchTool()],\n    model=HfApiModel(\"Qwen\u002FQwen2.5-72B-Instruct\"),\n)\n\nresult = agent.run(\"What are the top 3 AI news stories today?\")\nprint(result)\n```\n\n## Models\n\n```python\nfrom smolagents import (\n    HfApiModel,           # HuggingFace Inference API\n    LiteLLMModel,         # 100+ providers via LiteLLM\n    TransformersModel,    # local Transformers model\n    OpenAIServerModel,    # any OpenAI-compatible endpoint\n    AmazonBedrockServerModel,\n)\n\n# HuggingFace Inference API (free tier available)\nmodel = HfApiModel(\"Qwen\u002FQwen2.5-Coder-32B-Instruct\")\n\n# Claude via LiteLLM\nmodel = LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\", api_key=\"your-key\")\n\n# OpenAI\nmodel = LiteLLMModel(\"openai\u002Fgpt-4o\")\n\n# Local with Transformers\nmodel = TransformersModel(\n    model_id=\"Qwen\u002FQwen2.5-7B-Instruct\",\n    device_map=\"auto\",\n    torch_dtype=\"bfloat16\",\n)\n\n# Ollama (OpenAI-compatible)\nmodel = OpenAIServerModel(\n    model_id=\"llama3.2\",\n    api_base=\"http:\u002F\u002Flocalhost:11434\u002Fv1\",\n    api_key=\"ollama\",\n)\n```\n\n## Agent Types\n\n### CodeAgent (default — recommended)\n\nWrites Python code as actions. More flexible, can do multi-step computation.\n\n```python\nfrom smolagents import CodeAgent, LiteLLMModel\n\nagent = CodeAgent(\n    tools=[],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n    max_steps=10,\n    verbosity_level=2,  # 0=silent, 1=steps, 2=full\n)\n\n# Agent writes and executes Python code to answer\nresult = agent.run(\"Calculate the compound interest on $10,000 at 5% for 10 years\")\nprint(result)\n```\n\n### ToolCallingAgent (JSON tool calls)\n\nUses standard function-calling API. More predictable, less flexible.\n\n```python\nfrom smolagents import ToolCallingAgent, DuckDuckGoSearchTool, LiteLLMModel\n\nagent = ToolCallingAgent(\n    tools=[DuckDuckGoSearchTool()],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n)\n\nresult = agent.run(\"Search for the latest news about LLMs\")\n```\n\n## Built-in Tools\n\n```python\nfrom smolagents import (\n    DuckDuckGoSearchTool,     # web search\n    WikipediaSearchTool,      # Wikipedia\n    VisitWebpageTool,         # fetch web page content\n    PythonInterpreterTool,    # run Python code (for ToolCallingAgent)\n    FinalAnswerTool,          # explicit answer tool\n    UserInputTool,            # ask user for input\n    SpeechToTextTool,         # transcribe audio\n    TextToImageTool,          # generate image\n)\n\n# Combine tools\nagent = CodeAgent(\n    tools=[\n        DuckDuckGoSearchTool(),\n        VisitWebpageTool(),\n        WikipediaSearchTool(),\n    ],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n)\n```\n\n## Custom Tools\n\n### Decorator style (simplest)\n\n```python\nfrom smolagents import tool\n\n@tool\ndef get_stock_price(ticker: str) -> str:\n    \"\"\"\n    Get the current stock price for a ticker symbol.\n\n    Args:\n        ticker: Stock ticker symbol (e.g., 'AAPL', 'GOOGL')\n    \"\"\"\n    # your implementation\n    price = fetch_price(ticker)\n    return f\"{ticker}: ${price:.2f}\"\n\nagent = CodeAgent(tools=[get_stock_price], model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"))\nresult = agent.run(\"What is Apple's current stock price?\")\n```\n\n### Class style (for complex tools)\n\n```python\nfrom smolagents import Tool\n\nclass DatabaseQueryTool(Tool):\n    name = \"database_query\"\n    description = \"Execute a SQL query against the company database\"\n    inputs = {\n        \"query\": {\n            \"type\": \"string\",\n            \"description\": \"SQL query to execute (SELECT only)\",\n        }\n    }\n    output_type = \"string\"\n\n    def __init__(self, connection_string: str):\n        super().__init__()\n        self.conn = connect(connection_string)\n\n    def forward(self, query: str) -> str:\n        if not query.strip().upper().startswith(\"SELECT\"):\n            raise ValueError(\"Only SELECT queries allowed\")\n        results = self.conn.execute(query).fetchall()\n        return str(results)\n\ndb_tool = DatabaseQueryTool(\"postgresql:\u002F\u002Flocalhost\u002Fmydb\")\nagent = CodeAgent(tools=[db_tool], model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"))\n```\n\n## Multi-Agent Orchestration\n\n```python\nfrom smolagents import CodeAgent, ManagedAgent, DuckDuckGoSearchTool, LiteLLMModel\n\nmodel = LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\")\n\n# Specialized web research agent\nweb_agent = CodeAgent(\n    tools=[DuckDuckGoSearchTool(), VisitWebpageTool()],\n    model=model,\n    name=\"web_researcher\",\n    description=\"Expert at finding information on the web\",\n)\n\n# Wrap it as a managed agent (callable by orchestrator)\nmanaged_web = ManagedAgent(\n    agent=web_agent,\n    name=\"web_researcher\",\n    description=\"Use this agent to search the web for information\",\n)\n\n# Orchestrator calls managed agents as tools\norchestrator = CodeAgent(\n    tools=[managed_web],\n    model=model,\n)\n\nresult = orchestrator.run(\n    \"Research AI trends in 2025 and write a comprehensive report\"\n)\n```\n\n## Vision \u002F Multimodal\n\n```python\nfrom smolagents import CodeAgent, LiteLLMModel\nfrom PIL import Image\n\nmodel = LiteLLMModel(\"anthropic\u002Fclaude-opus-4-5\")\n\nagent = CodeAgent(tools=[], model=model)\n\n# Pass image as input\nimage = Image.open(\"chart.png\")\nresult = agent.run(\n    \"Analyze this chart and extract the key data points\",\n    images=[image],\n)\n```\n\n## Memory \u002F Context\n\n```python\nfrom smolagents import CodeAgent, LiteLLMModel\n\nagent = CodeAgent(tools=[], model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"))\n\n# First run\nagent.run(\"My name is Alice and I work in AI\")\n\n# Continue — agent has memory of previous run\nresult = agent.run(\"What do you know about me?\")\n\n# Reset memory\nagent.memory.reset()\n```\n\n## Gradio UI\n\n```python\nfrom smolagents import CodeAgent, DuckDuckGoSearchTool, LiteLLMModel, GradioUI\n\nagent = CodeAgent(\n    tools=[DuckDuckGoSearchTool()],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n)\n\nGradioUI(agent).launch()\n```\n\n## Sandbox Safety (Docker\u002FE2B)\n\n```python\nfrom smolagents import CodeAgent, LiteLLMModel, E2BSandbox\n\n# Run code in isolated E2B sandbox\nagent = CodeAgent(\n    tools=[],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n    executor_type=\"e2b\",  # requires e2b API key\n)\n\n# Or local Docker sandbox\nfrom smolagents import LocalPythonInterpreter\nagent = CodeAgent(\n    tools=[],\n    model=LiteLLMModel(\"anthropic\u002Fclaude-sonnet-4-5\"),\n    executor_type=\"local\",\n    additional_authorized_imports=[\"pandas\", \"numpy\", \"matplotlib\"],\n)\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `CodeAgent` writes + executes Python — different from `ToolCallingAgent` which uses JSON\n- [ ] `@tool` docstring format matters: first line = description, then `Args:` block\n- [ ] `ManagedAgent` wraps an agent to make it callable as a tool by the orchestrator\n- [ ] `additional_authorized_imports` needed for non-stdlib packages in local executor\n- [ ] `agent.run()` returns the final answer string, not a structured object\n- [ ] `verbosity_level=2` shows intermediate code steps — useful for debugging\n- [ ] Memory is per-agent-instance; create new instance or call `.memory.reset()` to clear\n",{"name":5,"see_also":24,"triggers":28,"description":7,"do_not_use_for":40},[25,26,27],"crewai","langgraph","pydantic-ai",[5,29,30,31,32,33,34,35,36,37,38,39],"smol agents","huggingface agents","code agent smolagents","smolagents tool","smolagents codeagent","smolagents toolcallingagent","smolagents managed agent","smolagents multi agent","hf agent framework","smolagents web search","transformers agents",[41,42,43],"Complex multi-agent crews with roles — use crewai instead","State graph agents — use langgraph instead","Workflow automation — use n8n-automation instead","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fsmolagents",1,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-11 23:56:26",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill smolagents",{"tool":60,"command":61},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill smolagents",{"tool":63,"command":64},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill smolagents","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fsmolagents\u002FSKILL.md",true,[],[69,77,84,92,100,108],{"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":73,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]