[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M730P9V5HSDM3NA1PYHAZ0VN":3,"skill-same:01M730P9V5HSDM3NA1PYHAZ0VN":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},"01M730P9V5HSDM3NA1PYHAZ0VN","autogen",null,"Build conversational multi-agent systems with AutoGen (AG2) — define AssistantAgent and UserProxyAgent, set up GroupChat with GroupChatManager for round-robin or auto routing, enable code execution, and compose nested chats or sequential pipelines.","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\u002F.claude\u002Fskills\u002Fautogen\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: autogen\ndescription: Build conversational multi-agent systems with AutoGen (AG2) — define AssistantAgent and UserProxyAgent, set up GroupChat with GroupChatManager for round-robin or auto routing, enable code execution, and compose nested chats or sequential pipelines.\ntriggers:\n  - \"autogen\"\n  - \"ag2\"\n  - \"pyautogen\"\n  - \"autogen agent\"\n  - \"autogen groupchat\"\n  - \"assistant agent user proxy\"\n  - \"groupchatmanager\"\n  - \"autogen code execution\"\n  - \"autogen conversable agent\"\n  - \"multi agent conversation autogen\"\n  - \"autogen nested chat\"\n  - \"autogen swarm\"\ndo_not_use_for:\n  - Role-playing agent crews — use crewai instead\n  - State graph agents — use langgraph instead\n  - Type-safe single agents — use pydantic-ai instead\nsee_also:\n  - crewai\n  - langgraph\n  - smolagents\n---\n\n# AutoGen (AG2) — Conversational Multi-Agent Framework\n\n**Source:** ag2ai\u002Fag2 (Apache 2.0) — formerly microsoft\u002Fautogen; conversational agent orchestration\n\n## Core Concepts\n\n| Component | Description |\n|-----------|-------------|\n| `ConversableAgent` | Base class — can send\u002Freceive messages, use LLM, execute code |\n| `AssistantAgent` | LLM-powered agent; generates replies using the model |\n| `UserProxyAgent` | Proxy for human input; can auto-execute code |\n| `GroupChat` | Manages conversation between multiple agents |\n| `GroupChatManager` | Routes messages in a GroupChat (round-robin or auto) |\n\n## Install\n\n```bash\npip install ag2\n# Optional: code execution support\npip install ag2[jupyter-executor]\n```\n\n## Two-Agent Conversation\n\n```python\nimport autogen\n\nconfig_list = [\n    {\n        \"model\": \"claude-sonnet-4-5\",\n        \"api_key\": \"your-anthropic-key\",\n        \"api_type\": \"anthropic\",\n    }\n]\n\nllm_config = {\"config_list\": config_list, \"cache_seed\": 42}\n\nassistant = autogen.AssistantAgent(\n    name=\"assistant\",\n    llm_config=llm_config,\n    system_message=\"You are a helpful AI assistant.\",\n)\n\nuser_proxy = autogen.UserProxyAgent(\n    name=\"user_proxy\",\n    human_input_mode=\"NEVER\",   # NEVER | ALWAYS | TERMINATE\n    max_consecutive_auto_reply=10,\n    is_termination_msg=lambda x: x.get(\"content\", \"\").rstrip().endswith(\"TERMINATE\"),\n    code_execution_config=False,  # no code execution\n)\n\n# Start conversation\nuser_proxy.initiate_chat(\n    assistant,\n    message=\"Write a Python function to calculate Fibonacci numbers.\",\n)\n```\n\n## Code Execution Agent\n\n```python\nimport autogen\n\nllm_config = {\"config_list\": [{\"model\": \"claude-sonnet-4-5\", \"api_key\": \"...\"}]}\n\nassistant = autogen.AssistantAgent(\n    name=\"coder\",\n    llm_config=llm_config,\n    system_message=\"Write Python code to solve tasks. Reply TERMINATE when done.\",\n)\n\nuser_proxy = autogen.UserProxyAgent(\n    name=\"executor\",\n    human_input_mode=\"NEVER\",\n    code_execution_config={\n        \"work_dir\": \"coding\",\n        \"use_docker\": False,  # True for Docker isolation (recommended)\n    },\n    is_termination_msg=lambda x: \"TERMINATE\" in x.get(\"content\", \"\"),\n)\n\nuser_proxy.initiate_chat(\n    assistant,\n    message=\"Create and run a script that plots a sine wave using matplotlib.\",\n)\n```\n\n## GroupChat (Multiple Agents)\n\n```python\nimport autogen\n\nllm_config = {\"config_list\": [{\"model\": \"claude-sonnet-4-5\", \"api_key\": \"...\"}]}\n\nplanner = autogen.AssistantAgent(\n    name=\"Planner\",\n    system_message=\"You break down tasks into steps and create a plan.\",\n    llm_config=llm_config,\n)\n\ncoder = autogen.AssistantAgent(\n    name=\"Coder\",\n    system_message=\"You implement the code based on the plan.\",\n    llm_config=llm_config,\n)\n\nreviewer = autogen.AssistantAgent(\n    name=\"Reviewer\",\n    system_message=\"You review code for bugs and suggest improvements.\",\n    llm_config=llm_config,\n)\n\nuser_proxy = autogen.UserProxyAgent(\n    name=\"User\",\n    human_input_mode=\"NEVER\",\n    code_execution_config={\"work_dir\": \"coding\", \"use_docker\": False},\n    is_termination_msg=lambda x: \"TERMINATE\" in x.get(\"content\", \"\"),\n)\n\ngroupchat = autogen.GroupChat(\n    agents=[user_proxy, planner, coder, reviewer],\n    messages=[],\n    max_round=12,\n    speaker_selection_method=\"auto\",  # LLM selects next speaker\n    # or: \"round_robin\" | custom function\n)\n\nmanager = autogen.GroupChatManager(\n    groupchat=groupchat,\n    llm_config=llm_config,\n)\n\nuser_proxy.initiate_chat(\n    manager,\n    message=\"Build a REST API endpoint for user authentication.\",\n)\n```\n\n## Custom Speaker Selection\n\n```python\ndef custom_speaker_selection(last_speaker, groupchat):\n    \"\"\"Custom logic to select next speaker.\"\"\"\n    messages = groupchat.messages\n    if last_speaker.name == \"Planner\":\n        return groupchat.agent_by_name(\"Coder\")\n    elif last_speaker.name == \"Coder\":\n        return groupchat.agent_by_name(\"Reviewer\")\n    else:\n        return groupchat.agent_by_name(\"Planner\")\n\ngroupchat = autogen.GroupChat(\n    agents=[planner, coder, reviewer],\n    messages=[],\n    speaker_selection_method=custom_speaker_selection,\n)\n```\n\n## Nested Chat (Subpipeline)\n\n```python\nimport autogen\n\nllm_config = {\"config_list\": [{\"model\": \"claude-sonnet-4-5\", \"api_key\": \"...\"}]}\n\n# Inner pipeline: writer + reviewer\ninner_writer = autogen.AssistantAgent(\"inner_writer\", llm_config=llm_config)\ninner_reviewer = autogen.AssistantAgent(\"inner_reviewer\", llm_config=llm_config)\ninner_proxy = autogen.UserProxyAgent(\"inner_proxy\", human_input_mode=\"NEVER\",\n                                      max_consecutive_auto_reply=3)\n\n# Outer agent triggers nested chat\nouter_assistant = autogen.AssistantAgent(\"outer_assistant\", llm_config=llm_config)\nouter_proxy = autogen.UserProxyAgent(\n    \"outer_proxy\",\n    human_input_mode=\"NEVER\",\n    is_termination_msg=lambda x: \"TERMINATE\" in x.get(\"content\", \"\"),\n)\n\n# Register nested chat — runs when outer_assistant replies to outer_proxy\nouter_proxy.register_nested_chats(\n    [{\"sender\": inner_proxy, \"recipient\": inner_writer, \"max_turns\": 3}],\n    trigger=outer_assistant,\n)\n\nouter_proxy.initiate_chat(outer_assistant, message=\"Write and review a blog post on AI.\")\n```\n\n## Swarm (Handoff Pattern)\n\n```python\nfrom autogen import SwarmAgent, initiate_swarm_chat, ON_CONDITION, AFTER_WORK, SwarmResult\n\ndef check_order(product: str, order_id: str) -> SwarmResult:\n    \"\"\"Check order status.\"\"\"\n    status = lookup_order(order_id)  # your implementation\n    return SwarmResult(values=f\"Order {order_id}: {status}\", agent=billing_agent)\n\ndef process_refund(order_id: str, reason: str) -> str:\n    \"\"\"Process a refund request.\"\"\"\n    execute_refund(order_id)\n    return \"Refund processed successfully.\"\n\ntriage_agent = SwarmAgent(\n    name=\"Triage\",\n    system_message=\"Determine if user needs order status or refund.\",\n    llm_config=llm_config,\n    functions=[check_order],\n)\n\nbilling_agent = SwarmAgent(\n    name=\"Billing\",\n    system_message=\"Handle refunds and billing questions.\",\n    llm_config=llm_config,\n    functions=[process_refund],\n    after_work=AFTER_WORK.TERMINATE,\n)\n\n# Handoff: triage → billing based on function result\nchat_result, context, last_agent = initiate_swarm_chat(\n    initial_agent=triage_agent,\n    agents=[triage_agent, billing_agent],\n    messages=\"I want to return my order #12345\",\n    max_rounds=10,\n)\n```\n\n## Structured Output\n\n```python\nfrom pydantic import BaseModel\nimport autogen\n\nclass CodeReview(BaseModel):\n    has_bugs: bool\n    severity: str\n    suggestions: list[str]\n\nllm_config = {\n    \"config_list\": [{\"model\": \"claude-sonnet-4-5\", \"api_key\": \"...\"}],\n    \"response_format\": CodeReview,  # enforces Pydantic schema\n}\n\nreviewer = autogen.AssistantAgent(\"reviewer\", llm_config=llm_config)\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `human_input_mode=\"NEVER\"` needed for fully automated runs — default is \"ALWAYS\"\n- [ ] `is_termination_msg` must be set or conversation runs until `max_consecutive_auto_reply`\n- [ ] `code_execution_config` on `UserProxyAgent`, NOT on `AssistantAgent`\n- [ ] `GroupChatManager` requires `llm_config` to select speakers with `\"auto\"` mode\n- [ ] Nested chats trigger on reply FROM the specified `trigger` agent — not on any message\n- [ ] `SwarmResult(agent=next_agent)` is how swarm handoffs are declared — return from function\n- [ ] `speaker_selection_method=\"auto\"` costs extra LLM calls per round to pick next speaker\n","# AutoGen (AG2) — Conversational Multi-Agent Framework\n\n**Source:** ag2ai\u002Fag2 (Apache 2.0) — formerly microsoft\u002Fautogen; conversational agent orchestration\n\n## Core Concepts\n\n| Component | Description |\n|-----------|-------------|\n| `ConversableAgent` | Base class — can send\u002Freceive messages, use LLM, execute code |\n| `AssistantAgent` | LLM-powered agent; generates replies using the model |\n| `UserProxyAgent` | Proxy for human input; can auto-execute code |\n| `GroupChat` | Manages conversation between multiple agents |\n| `GroupChatManager` | Routes messages in a GroupChat (round-robin or auto) |\n\n## Install\n\n```bash\npip install ag2\n# Optional: code execution support\npip install ag2[jupyter-executor]\n```\n\n## Two-Agent Conversation\n\n```python\nimport autogen\n\nconfig_list = [\n    {\n        \"model\": \"claude-sonnet-4-5\",\n        \"api_key\": \"your-anthropic-key\",\n        \"api_type\": \"anthropic\",\n    }\n]\n\nllm_config = {\"config_list\": config_list, \"cache_seed\": 42}\n\nassistant = autogen.AssistantAgent(\n    name=\"assistant\",\n    llm_config=llm_config,\n    system_message=\"You are a helpful AI assistant.\",\n)\n\nuser_proxy = autogen.UserProxyAgent(\n    name=\"user_proxy\",\n    human_input_mode=\"NEVER\",   # NEVER | ALWAYS | TERMINATE\n    max_consecutive_auto_reply=10,\n    is_termination_msg=lambda x: x.get(\"content\", \"\").rstrip().endswith(\"TERMINATE\"),\n    code_execution_config=False,  # no code execution\n)\n\n# Start conversation\nuser_proxy.initiate_chat(\n    assistant,\n    message=\"Write a Python function to calculate Fibonacci numbers.\",\n)\n```\n\n## Code Execution Agent\n\n```python\nimport autogen\n\nllm_config = {\"config_list\": [{\"model\": \"claude-sonnet-4-5\", \"api_key\": \"...\"}]}\n\nassistant = autogen.AssistantAgent(\n    name=\"coder\",\n    llm_config=llm_config,\n    system_message=\"Write Python code to solve tasks. Reply TERMINATE when done.\",\n)\n\nuser_proxy = autogen.UserProxyAgent(\n    name=\"executor\",\n    human_input_mode=\"NEVER\",\n    code_execution_config={\n        \"work_dir\": \"coding\",\n        \"use_docker\": False,  # True for Docker isolation (recommended)\n    },\n    is_termination_msg=lambda x: \"TERMINATE\" in x.get(\"content\", \"\"),\n)\n\nuser_proxy.initiate_chat(\n    assistant,\n    message=\"Create and run a script that plots a sine wave using matplotlib.\",\n)\n```\n\n## GroupChat (Multiple Agents)\n\n```python\nimport autogen\n\nllm_config = {\"config_list\": [{\"model\": \"claude-sonnet-4-5\", \"api_key\": \"...\"}]}\n\nplanner = autogen.AssistantAgent(\n    name=\"Planner\",\n    system_message=\"You break down tasks into steps and create a plan.\",\n    llm_config=llm_config,\n)\n\ncoder = autogen.AssistantAgent(\n    name=\"Coder\",\n    system_message=\"You implement the code based on the plan.\",\n    llm_config=llm_config,\n)\n\nreviewer = autogen.AssistantAgent(\n    name=\"Reviewer\",\n    system_message=\"You review code for bugs and suggest improvements.\",\n    llm_config=llm_config,\n)\n\nuser_proxy = autogen.UserProxyAgent(\n    name=\"User\",\n    human_input_mode=\"NEVER\",\n    code_execution_config={\"work_dir\": \"coding\", \"use_docker\": False},\n    is_termination_msg=lambda x: \"TERMINATE\" in x.get(\"content\", \"\"),\n)\n\ngroupchat = autogen.GroupChat(\n    agents=[user_proxy, planner, coder, reviewer],\n    messages=[],\n    max_round=12,\n    speaker_selection_method=\"auto\",  # LLM selects next speaker\n    # or: \"round_robin\" | custom function\n)\n\nmanager = autogen.GroupChatManager(\n    groupchat=groupchat,\n    llm_config=llm_config,\n)\n\nuser_proxy.initiate_chat(\n    manager,\n    message=\"Build a REST API endpoint for user authentication.\",\n)\n```\n\n## Custom Speaker Selection\n\n```python\ndef custom_speaker_selection(last_speaker, groupchat):\n    \"\"\"Custom logic to select next speaker.\"\"\"\n    messages = groupchat.messages\n    if last_speaker.name == \"Planner\":\n        return groupchat.agent_by_name(\"Coder\")\n    elif last_speaker.name == \"Coder\":\n        return groupchat.agent_by_name(\"Reviewer\")\n    else:\n        return groupchat.agent_by_name(\"Planner\")\n\ngroupchat = autogen.GroupChat(\n    agents=[planner, coder, reviewer],\n    messages=[],\n    speaker_selection_method=custom_speaker_selection,\n)\n```\n\n## Nested Chat (Subpipeline)\n\n```python\nimport autogen\n\nllm_config = {\"config_list\": [{\"model\": \"claude-sonnet-4-5\", \"api_key\": \"...\"}]}\n\n# Inner pipeline: writer + reviewer\ninner_writer = autogen.AssistantAgent(\"inner_writer\", llm_config=llm_config)\ninner_reviewer = autogen.AssistantAgent(\"inner_reviewer\", llm_config=llm_config)\ninner_proxy = autogen.UserProxyAgent(\"inner_proxy\", human_input_mode=\"NEVER\",\n                                      max_consecutive_auto_reply=3)\n\n# Outer agent triggers nested chat\nouter_assistant = autogen.AssistantAgent(\"outer_assistant\", llm_config=llm_config)\nouter_proxy = autogen.UserProxyAgent(\n    \"outer_proxy\",\n    human_input_mode=\"NEVER\",\n    is_termination_msg=lambda x: \"TERMINATE\" in x.get(\"content\", \"\"),\n)\n\n# Register nested chat — runs when outer_assistant replies to outer_proxy\nouter_proxy.register_nested_chats(\n    [{\"sender\": inner_proxy, \"recipient\": inner_writer, \"max_turns\": 3}],\n    trigger=outer_assistant,\n)\n\nouter_proxy.initiate_chat(outer_assistant, message=\"Write and review a blog post on AI.\")\n```\n\n## Swarm (Handoff Pattern)\n\n```python\nfrom autogen import SwarmAgent, initiate_swarm_chat, ON_CONDITION, AFTER_WORK, SwarmResult\n\ndef check_order(product: str, order_id: str) -> SwarmResult:\n    \"\"\"Check order status.\"\"\"\n    status = lookup_order(order_id)  # your implementation\n    return SwarmResult(values=f\"Order {order_id}: {status}\", agent=billing_agent)\n\ndef process_refund(order_id: str, reason: str) -> str:\n    \"\"\"Process a refund request.\"\"\"\n    execute_refund(order_id)\n    return \"Refund processed successfully.\"\n\ntriage_agent = SwarmAgent(\n    name=\"Triage\",\n    system_message=\"Determine if user needs order status or refund.\",\n    llm_config=llm_config,\n    functions=[check_order],\n)\n\nbilling_agent = SwarmAgent(\n    name=\"Billing\",\n    system_message=\"Handle refunds and billing questions.\",\n    llm_config=llm_config,\n    functions=[process_refund],\n    after_work=AFTER_WORK.TERMINATE,\n)\n\n# Handoff: triage → billing based on function result\nchat_result, context, last_agent = initiate_swarm_chat(\n    initial_agent=triage_agent,\n    agents=[triage_agent, billing_agent],\n    messages=\"I want to return my order #12345\",\n    max_rounds=10,\n)\n```\n\n## Structured Output\n\n```python\nfrom pydantic import BaseModel\nimport autogen\n\nclass CodeReview(BaseModel):\n    has_bugs: bool\n    severity: str\n    suggestions: list[str]\n\nllm_config = {\n    \"config_list\": [{\"model\": \"claude-sonnet-4-5\", \"api_key\": \"...\"}],\n    \"response_format\": CodeReview,  # enforces Pydantic schema\n}\n\nreviewer = autogen.AssistantAgent(\"reviewer\", llm_config=llm_config)\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `human_input_mode=\"NEVER\"` needed for fully automated runs — default is \"ALWAYS\"\n- [ ] `is_termination_msg` must be set or conversation runs until `max_consecutive_auto_reply`\n- [ ] `code_execution_config` on `UserProxyAgent`, NOT on `AssistantAgent`\n- [ ] `GroupChatManager` requires `llm_config` to select speakers with `\"auto\"` mode\n- [ ] Nested chats trigger on reply FROM the specified `trigger` agent — not on any message\n- [ ] `SwarmResult(agent=next_agent)` is how swarm handoffs are declared — return from function\n- [ ] `speaker_selection_method=\"auto\"` costs extra LLM calls per round to pick next speaker\n",{"name":5,"see_also":24,"triggers":28,"description":7,"do_not_use_for":40},[25,26,27],"crewai","langgraph","smolagents",[5,29,30,31,32,33,34,35,36,37,38,39],"ag2","pyautogen","autogen agent","autogen groupchat","assistant agent user proxy","groupchatmanager","autogen code execution","autogen conversable agent","multi agent conversation autogen","autogen nested chat","autogen swarm",[41,42,43],"Role-playing agent crews — use crewai instead","State graph agents — use langgraph instead","Type-safe single agents — use pydantic-ai instead","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa",".claude\u002Fskills\u002Fautogen",2,"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.","2026-11-14 13:24:09",{"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 autogen",{"tool":60,"command":61},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill autogen",{"tool":63,"command":64},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill autogen","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fautogen\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",[],[]]