[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72ZZJS0R3X3P6R19W72CTF9":3,"skill-same:01M72ZZJS0R3X3P6R19W72CTF9":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},"01M72ZZJS0R3X3P6R19W72CTF9","agno",null,"Build production AI agents with Agno (formerly Phidata) — define Agent with model\u002Ftools\u002Finstructions\u002Fmemory\u002Fknowledge, compose Agent Teams with coordinator routing, add Storage for persistence, and integrate RAG via built-in KnowledgeBase with PDF\u002FURL\u002Ftext sources.","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\u002Fagno\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: agno\ndescription: Build production AI agents with Agno (formerly Phidata) — define Agent with model\u002Ftools\u002Finstructions\u002Fmemory\u002Fknowledge, compose Agent Teams with coordinator routing, add Storage for persistence, and integrate RAG via built-in KnowledgeBase with PDF\u002FURL\u002Ftext sources.\ntriggers:\n  - \"agno\"\n  - \"phidata\"\n  - \"agno agent\"\n  - \"agno team\"\n  - \"agno knowledge\"\n  - \"agno storage\"\n  - \"agno memory\"\n  - \"phi agent\"\n  - \"agent team coordinator\"\n  - \"agent with knowledge base\"\n  - \"agno tools\"\n  - \"agno model\"\ndo_not_use_for:\n  - State graph agents — use langgraph instead\n  - Multi-agent role crews — use crewai instead\n  - LLM fine-tuning — use llamafactory instead\nsee_also:\n  - crewai\n  - langgraph\n  - mem0\n---\n\n# Agno — Production AI Agent Framework\n\n**Source:** agno-agi\u002Fagno (Mozilla PL) — formerly Phidata; full-stack agent framework\n\n## Why Agno\n\n- **One unified API** for agents, teams, memory, knowledge, storage, tools\n- **Agent Teams**: coordinator routes tasks to specialized sub-agents\n- **Built-in RAG**: KnowledgeBase with PDF, URL, text, database sources\n- **Persistent storage**: PostgreSQL, SQLite, MongoDB for long-term memory\n- **Playground UI**: `agent.serve()` launches a ready-made web UI\n\n## Install\n\n```bash\npip install agno\npip install agno[anthropic]   # Anthropic Claude\npip install agno[openai]      # OpenAI\npip install agno[all]         # everything\n```\n\n## Minimal Agent\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    instructions=\"You are a helpful assistant.\",\n    markdown=True,\n)\n\nagent.print_response(\"What is quantum computing?\")\n\n# Or get structured response\nresponse = agent.run(\"Explain RAG in 3 bullets\")\nprint(response.content)\n```\n\n## Agent with Tools\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.tools.duckduckgo import DuckDuckGoTools\nfrom agno.tools.yfinance import YFinanceTools\nfrom agno.tools.python import PythonTools\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    tools=[\n        DuckDuckGoTools(),\n        YFinanceTools(stock_price=True, analyst_recommendations=True),\n        PythonTools(),\n    ],\n    instructions=[\n        \"Use DuckDuckGo to search for recent news\",\n        \"Use YFinance for stock data\",\n        \"Always cite your sources\",\n    ],\n    show_tool_calls=True,\n    markdown=True,\n)\n\nagent.print_response(\"What is Apple's current stock price and recent news?\")\n```\n\n## Memory & Storage\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.memory.db.sqlite import SqliteMemoryDb\nfrom agno.storage.sqlite import SqliteStorage\n\n# Memory: stores facts about users across sessions\n# Storage: stores the full conversation history\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    # Persistent memory (facts extracted from conversations)\n    memory=SqliteMemoryDb(table_name=\"agent_memory\", db_file=\"agent.db\"),\n    enable_user_memories=True,\n    # Persistent storage (full chat history)\n    storage=SqliteStorage(table_name=\"agent_sessions\", db_file=\"agent.db\"),\n    add_history_to_messages=True,\n    num_history_runs=3,  # last 3 runs included in context\n)\n\n# First session\nagent.print_response(\"My name is Alice and I love hiking.\", user_id=\"alice\")\n\n# New session — memory persists\nagent.print_response(\"What do you know about me?\", user_id=\"alice\")\n```\n\n## Knowledge Base (RAG)\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.knowledge.pdf import PDFKnowledgeBase\nfrom agno.knowledge.url import URLKnowledgeBase\nfrom agno.knowledge.text import TextKnowledgeBase\nfrom agno.vectordb.pgvector import PgVector\nfrom agno.embedder.openai import OpenAIEmbedder\n\n# Vector DB for knowledge\nvector_db = PgVector(\n    table_name=\"agent_knowledge\",\n    db_url=\"postgresql:\u002F\u002Fuser:pass@localhost\u002Fdb\",\n    embedder=OpenAIEmbedder(id=\"text-embedding-3-small\"),\n)\n\n# Load PDFs into knowledge base\nknowledge = PDFKnowledgeBase(\n    path=\"docs\u002F\",                   # directory of PDFs\n    vector_db=vector_db,\n)\nknowledge.load(recreate=False)      # recreate=True to reindex\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    knowledge=knowledge,\n    search_knowledge=True,          # auto-search on every query\n    instructions=\"Answer from the knowledge base. Cite sources.\",\n)\n\nagent.print_response(\"What does the document say about authentication?\")\n```\n\n## Agent Teams\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.team import Team\nfrom agno.tools.duckduckgo import DuckDuckGoTools\nfrom agno.tools.yfinance import YFinanceTools\n\nweb_agent = Agent(\n    name=\"Web Researcher\",\n    role=\"Search the web for information\",\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    tools=[DuckDuckGoTools()],\n    instructions=\"Always include sources\",\n)\n\nfinance_agent = Agent(\n    name=\"Finance Analyst\",\n    role=\"Analyze financial data and markets\",\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    tools=[YFinanceTools(stock_price=True, analyst_recommendations=True)],\n    instructions=\"Provide data-backed analysis\",\n)\n\n# Team with coordinator routing\nteam = Team(\n    name=\"Research Team\",\n    mode=\"coordinate\",              # coordinator decides which agent to use\n    model=Claude(id=\"claude-opus-4-5\"),  # coordinator model\n    members=[web_agent, finance_agent],\n    instructions=\"Coordinate agents to provide comprehensive research\",\n)\n\nteam.print_response(\"What are the latest AI trends and their market impact?\")\n```\n\n## Structured Output\n\n```python\nfrom pydantic import BaseModel\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\n\nclass MovieSummary(BaseModel):\n    title: str\n    director: str\n    year: int\n    genre: list[str]\n    summary: str\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    response_model=MovieSummary,\n)\n\nmovie: MovieSummary = agent.run(\"Tell me about Inception\").content\nprint(movie.title, movie.director, movie.year)\n```\n\n## Async Agent\n\n```python\nimport asyncio\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\n\nagent = Agent(model=Claude(id=\"claude-sonnet-4-5\"))\n\nasync def main():\n    response = await agent.arun(\"Explain neural networks\")\n    print(response.content)\n\n    async for chunk in await agent.astream(\"Write a poem\"):\n        print(chunk.content, end=\"\", flush=True)\n\nasyncio.run(main())\n```\n\n## Playground (Web UI)\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.playground import Playground, serve_playground_app\n\nagent = Agent(\n    name=\"My Assistant\",\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    markdown=True,\n)\n\n# Launch web UI at http:\u002F\u002Flocalhost:7777\napp = Playground(agents=[agent]).get_app()\nserve_playground_app(\"main:app\", reload=True)\n```\n\n## Built-in Tools\n\n```python\nfrom agno.tools.duckduckgo import DuckDuckGoTools       # web search\nfrom agno.tools.yfinance import YFinanceTools           # stock data\nfrom agno.tools.python import PythonTools               # run Python code\nfrom agno.tools.shell import ShellTools                 # shell commands\nfrom agno.tools.file import FileTools                   # file operations\nfrom agno.tools.github import GitHubTools               # GitHub API\nfrom agno.tools.slack import SlackTools                 # Slack messages\nfrom agno.tools.newspaper import NewspaperTools         # article extraction\nfrom agno.tools.arxiv import ArxivTools                 # arXiv papers\nfrom agno.tools.calculator import CalculatorTools       # math\nfrom agno.tools.email import EmailTools                 # send email\nfrom agno.tools.sql import SQLTools                     # SQL queries\nfrom agno.tools.docker import DockerTools               # Docker ops\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `agent.run()` returns `RunResponse` — content at `.content`, not `.text` or `.data`\n- [ ] `enable_user_memories=True` requires both `memory` AND `user_id` at run time\n- [ ] `knowledge.load()` must be called before first query — not lazy-loaded automatically\n- [ ] Team `mode=\"coordinate\"` uses a coordinator LLM — requires `model` on Team, not just members\n- [ ] `search_knowledge=True` makes agent automatically search; `knowledge.search()` is manual\n- [ ] `add_history_to_messages=True` requires `storage` to be set\n","# Agno — Production AI Agent Framework\n\n**Source:** agno-agi\u002Fagno (Mozilla PL) — formerly Phidata; full-stack agent framework\n\n## Why Agno\n\n- **One unified API** for agents, teams, memory, knowledge, storage, tools\n- **Agent Teams**: coordinator routes tasks to specialized sub-agents\n- **Built-in RAG**: KnowledgeBase with PDF, URL, text, database sources\n- **Persistent storage**: PostgreSQL, SQLite, MongoDB for long-term memory\n- **Playground UI**: `agent.serve()` launches a ready-made web UI\n\n## Install\n\n```bash\npip install agno\npip install agno[anthropic]   # Anthropic Claude\npip install agno[openai]      # OpenAI\npip install agno[all]         # everything\n```\n\n## Minimal Agent\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    instructions=\"You are a helpful assistant.\",\n    markdown=True,\n)\n\nagent.print_response(\"What is quantum computing?\")\n\n# Or get structured response\nresponse = agent.run(\"Explain RAG in 3 bullets\")\nprint(response.content)\n```\n\n## Agent with Tools\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.tools.duckduckgo import DuckDuckGoTools\nfrom agno.tools.yfinance import YFinanceTools\nfrom agno.tools.python import PythonTools\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    tools=[\n        DuckDuckGoTools(),\n        YFinanceTools(stock_price=True, analyst_recommendations=True),\n        PythonTools(),\n    ],\n    instructions=[\n        \"Use DuckDuckGo to search for recent news\",\n        \"Use YFinance for stock data\",\n        \"Always cite your sources\",\n    ],\n    show_tool_calls=True,\n    markdown=True,\n)\n\nagent.print_response(\"What is Apple's current stock price and recent news?\")\n```\n\n## Memory & Storage\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.memory.db.sqlite import SqliteMemoryDb\nfrom agno.storage.sqlite import SqliteStorage\n\n# Memory: stores facts about users across sessions\n# Storage: stores the full conversation history\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    # Persistent memory (facts extracted from conversations)\n    memory=SqliteMemoryDb(table_name=\"agent_memory\", db_file=\"agent.db\"),\n    enable_user_memories=True,\n    # Persistent storage (full chat history)\n    storage=SqliteStorage(table_name=\"agent_sessions\", db_file=\"agent.db\"),\n    add_history_to_messages=True,\n    num_history_runs=3,  # last 3 runs included in context\n)\n\n# First session\nagent.print_response(\"My name is Alice and I love hiking.\", user_id=\"alice\")\n\n# New session — memory persists\nagent.print_response(\"What do you know about me?\", user_id=\"alice\")\n```\n\n## Knowledge Base (RAG)\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.knowledge.pdf import PDFKnowledgeBase\nfrom agno.knowledge.url import URLKnowledgeBase\nfrom agno.knowledge.text import TextKnowledgeBase\nfrom agno.vectordb.pgvector import PgVector\nfrom agno.embedder.openai import OpenAIEmbedder\n\n# Vector DB for knowledge\nvector_db = PgVector(\n    table_name=\"agent_knowledge\",\n    db_url=\"postgresql:\u002F\u002Fuser:pass@localhost\u002Fdb\",\n    embedder=OpenAIEmbedder(id=\"text-embedding-3-small\"),\n)\n\n# Load PDFs into knowledge base\nknowledge = PDFKnowledgeBase(\n    path=\"docs\u002F\",                   # directory of PDFs\n    vector_db=vector_db,\n)\nknowledge.load(recreate=False)      # recreate=True to reindex\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    knowledge=knowledge,\n    search_knowledge=True,          # auto-search on every query\n    instructions=\"Answer from the knowledge base. Cite sources.\",\n)\n\nagent.print_response(\"What does the document say about authentication?\")\n```\n\n## Agent Teams\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.team import Team\nfrom agno.tools.duckduckgo import DuckDuckGoTools\nfrom agno.tools.yfinance import YFinanceTools\n\nweb_agent = Agent(\n    name=\"Web Researcher\",\n    role=\"Search the web for information\",\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    tools=[DuckDuckGoTools()],\n    instructions=\"Always include sources\",\n)\n\nfinance_agent = Agent(\n    name=\"Finance Analyst\",\n    role=\"Analyze financial data and markets\",\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    tools=[YFinanceTools(stock_price=True, analyst_recommendations=True)],\n    instructions=\"Provide data-backed analysis\",\n)\n\n# Team with coordinator routing\nteam = Team(\n    name=\"Research Team\",\n    mode=\"coordinate\",              # coordinator decides which agent to use\n    model=Claude(id=\"claude-opus-4-5\"),  # coordinator model\n    members=[web_agent, finance_agent],\n    instructions=\"Coordinate agents to provide comprehensive research\",\n)\n\nteam.print_response(\"What are the latest AI trends and their market impact?\")\n```\n\n## Structured Output\n\n```python\nfrom pydantic import BaseModel\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\n\nclass MovieSummary(BaseModel):\n    title: str\n    director: str\n    year: int\n    genre: list[str]\n    summary: str\n\nagent = Agent(\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    response_model=MovieSummary,\n)\n\nmovie: MovieSummary = agent.run(\"Tell me about Inception\").content\nprint(movie.title, movie.director, movie.year)\n```\n\n## Async Agent\n\n```python\nimport asyncio\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\n\nagent = Agent(model=Claude(id=\"claude-sonnet-4-5\"))\n\nasync def main():\n    response = await agent.arun(\"Explain neural networks\")\n    print(response.content)\n\n    async for chunk in await agent.astream(\"Write a poem\"):\n        print(chunk.content, end=\"\", flush=True)\n\nasyncio.run(main())\n```\n\n## Playground (Web UI)\n\n```python\nfrom agno.agent import Agent\nfrom agno.models.anthropic import Claude\nfrom agno.playground import Playground, serve_playground_app\n\nagent = Agent(\n    name=\"My Assistant\",\n    model=Claude(id=\"claude-sonnet-4-5\"),\n    markdown=True,\n)\n\n# Launch web UI at http:\u002F\u002Flocalhost:7777\napp = Playground(agents=[agent]).get_app()\nserve_playground_app(\"main:app\", reload=True)\n```\n\n## Built-in Tools\n\n```python\nfrom agno.tools.duckduckgo import DuckDuckGoTools       # web search\nfrom agno.tools.yfinance import YFinanceTools           # stock data\nfrom agno.tools.python import PythonTools               # run Python code\nfrom agno.tools.shell import ShellTools                 # shell commands\nfrom agno.tools.file import FileTools                   # file operations\nfrom agno.tools.github import GitHubTools               # GitHub API\nfrom agno.tools.slack import SlackTools                 # Slack messages\nfrom agno.tools.newspaper import NewspaperTools         # article extraction\nfrom agno.tools.arxiv import ArxivTools                 # arXiv papers\nfrom agno.tools.calculator import CalculatorTools       # math\nfrom agno.tools.email import EmailTools                 # send email\nfrom agno.tools.sql import SQLTools                     # SQL queries\nfrom agno.tools.docker import DockerTools               # Docker ops\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `agent.run()` returns `RunResponse` — content at `.content`, not `.text` or `.data`\n- [ ] `enable_user_memories=True` requires both `memory` AND `user_id` at run time\n- [ ] `knowledge.load()` must be called before first query — not lazy-loaded automatically\n- [ ] Team `mode=\"coordinate\"` uses a coordinator LLM — requires `model` on Team, not just members\n- [ ] `search_knowledge=True` makes agent automatically search; `knowledge.search()` is manual\n- [ ] `add_history_to_messages=True` requires `storage` to be set\n",{"name":5,"see_also":24,"triggers":28,"description":7,"do_not_use_for":40},[25,26,27],"crewai","langgraph","mem0",[5,29,30,31,32,33,34,35,36,37,38,39],"phidata","agno agent","agno team","agno knowledge","agno storage","agno memory","phi agent","agent team coordinator","agent with knowledge base","agno tools","agno model",[41,42,43],"State graph agents — use langgraph instead","Multi-agent role crews — use crewai instead","LLM fine-tuning — use llamafactory instead","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa",".claude\u002Fskills\u002Fagno",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 agno",{"tool":60,"command":61},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill agno",{"tool":63,"command":64},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill agno","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fagno\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",[],[]]