[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73DR8MT72YMBFATZEZBA5RG":3,"skill-same:01M73DR8MT72YMBFATZEZBA5RG":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},"01M73DR8MT72YMBFATZEZBA5RG","mem0",null,"Add persistent, intelligent memory to AI agents with Mem0 — add\u002Fsearch\u002Fupdate\u002Fdelete memories per user\u002Fagent\u002Fsession, supports vector + graph + key-value storage, integrates with LangChain, CrewAI, OpenAI Assistants, and any LLM.","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\u002Fmem0\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: mem0\ndescription: Add persistent, intelligent memory to AI agents with Mem0 — add\u002Fsearch\u002Fupdate\u002Fdelete memories per user\u002Fagent\u002Fsession, supports vector + graph + key-value storage, integrates with LangChain, CrewAI, OpenAI Assistants, and any LLM.\ntriggers:\n  - \"mem0\"\n  - \"mem0ai\"\n  - \"memory layer ai agent\"\n  - \"persistent agent memory\"\n  - \"user memory ai\"\n  - \"add memory agent\"\n  - \"search memory\"\n  - \"memory.add\"\n  - \"memory.search\"\n  - \"agent long term memory\"\n  - \"personalized ai memory\"\n  - \"cross session memory\"\ndo_not_use_for:\n  - Short-term conversation history — use LangChain ConversationBufferMemory instead\n  - Vector search only — use pgvector or qdrant directly\n  - State management within a single LangGraph run — use checkpointer instead\nsee_also:\n  - langgraph\n  - crewai\n  - pydantic-ai\n---\n\n# Mem0 — Intelligent Memory Layer for AI Agents\n\n**Source:** mem0ai\u002Fmem0 (Apache 2.0) — persistent, intelligent memory for AI applications\n\n## Why Mem0\n\n- Automatically extracts facts from conversations and stores them\n- Semantically searches memories relevant to current context\n- Deduplicates and updates conflicting memories\n- Scoped by `user_id`, `agent_id`, `run_id` — flexible memory isolation\n- Supports vector (default) + graph + key-value backends\n\n## Install\n\n```bash\npip install mem0ai\n# Optional: graph memory\npip install mem0ai[graph]\n```\n\n## Quick Start (Managed Cloud)\n\n```python\nfrom mem0 import MemoryClient\n\nclient = MemoryClient(api_key=\"your-mem0-api-key\")\n\n# Add memories from a conversation\nmessages = [\n    {\"role\": \"user\", \"content\": \"I'm Alice and I love hiking.\"},\n    {\"role\": \"assistant\", \"content\": \"That's great! Do you have a favorite trail?\"},\n    {\"role\": \"user\", \"content\": \"Yes, the Pacific Crest Trail is my favorite.\"},\n]\nclient.add(messages, user_id=\"alice\")\n\n# Search memories\nresults = client.search(\"outdoor activities\", user_id=\"alice\")\nfor mem in results:\n    print(mem[\"memory\"])  # \"User loves hiking\" \u002F \"Favorite trail is PCT\"\n\n# Get all memories for a user\nall_mems = client.get_all(user_id=\"alice\")\n\n# Update a memory\nclient.update(memory_id=\"mem-xxx\", data=\"User loves hiking and cycling\")\n\n# Delete\nclient.delete(memory_id=\"mem-xxx\")\nclient.delete_all(user_id=\"alice\")\n```\n\n## Self-Hosted (Open Source)\n\n```python\nfrom mem0 import Memory\n\nconfig = {\n    \"llm\": {\n        \"provider\": \"anthropic\",\n        \"config\": {\n            \"model\": \"claude-sonnet-4-5\",\n            \"api_key\": \"your-anthropic-key\",\n        },\n    },\n    \"embedder\": {\n        \"provider\": \"openai\",\n        \"config\": {\"model\": \"text-embedding-3-small\"},\n    },\n    \"vector_store\": {\n        \"provider\": \"qdrant\",\n        \"config\": {\n            \"collection_name\": \"mem0_memories\",\n            \"host\": \"localhost\",\n            \"port\": 6333,\n        },\n    },\n}\n\nmemory = Memory.from_config(config)\n```\n\n## Memory Scoping\n\n```python\nfrom mem0 import Memory\n\nm = Memory()\n\n# User-scoped memory (persists across sessions)\nm.add(\"User prefers dark mode\", user_id=\"user-123\")\nm.add(\"User is a Python developer\", user_id=\"user-123\")\n\n# Agent-scoped memory (shared across users for this agent)\nm.add(\"This agent specializes in cooking recipes\", agent_id=\"chef-bot\")\n\n# Session-scoped memory (single conversation)\nm.add(\"User asked about pasta today\", user_id=\"user-123\", run_id=\"session-abc\")\n\n# Search within scope\nresults = m.search(\"coding preferences\", user_id=\"user-123\")\n```\n\n## Integration with AI Agents\n\n```python\nfrom mem0 import Memory\nfrom anthropic import Anthropic\n\nmemory = Memory()\nclient = Anthropic()\n\ndef chat_with_memory(user_id: str, user_message: str) -> str:\n    # 1. Search relevant memories\n    relevant_memories = memory.search(user_message, user_id=user_id)\n    mem_context = \"\\n\".join(f\"- {m['memory']}\" for m in relevant_memories)\n\n    # 2. Build prompt with memory context\n    system = f\"\"\"You are a helpful assistant.\nRelevant memories about this user:\n{mem_context if mem_context else \"No memories yet.\"}\n\"\"\"\n\n    # 3. Get LLM response\n    response = client.messages.create(\n        model=\"claude-sonnet-4-5\",\n        max_tokens=1024,\n        system=system,\n        messages=[{\"role\": \"user\", \"content\": user_message}],\n    )\n    answer = response.content[0].text\n\n    # 4. Extract and store new memories from this exchange\n    memory.add(\n        [\n            {\"role\": \"user\", \"content\": user_message},\n            {\"role\": \"assistant\", \"content\": answer},\n        ],\n        user_id=user_id,\n    )\n\n    return answer\n\n# Usage\nprint(chat_with_memory(\"alice\", \"My name is Alice and I love hiking.\"))\nprint(chat_with_memory(\"alice\", \"What do you know about me?\"))\n```\n\n## Graph Memory (Relationships)\n\n```python\nfrom mem0 import Memory\n\nconfig = {\n    \"graph_store\": {\n        \"provider\": \"neo4j\",\n        \"config\": {\n            \"url\": \"bolt:\u002F\u002Flocalhost:7687\",\n            \"username\": \"neo4j\",\n            \"password\": \"password\",\n        },\n    },\n    \"llm\": {\"provider\": \"anthropic\", \"config\": {\"model\": \"claude-sonnet-4-5\"}},\n    \"version\": \"v1.1\",  # required for graph memory\n}\n\nmemory = Memory.from_config(config)\n\n# Graph memory automatically extracts relationships\nmemory.add(\"Alice works at Anthropic and knows Bob\", user_id=\"user-1\")\nmemory.add(\"Bob is a senior engineer\", user_id=\"user-1\")\n\n# Graph-aware search finds Alice→Anthropic→Bob relationships\nresults = memory.search(\"Who does Alice work with?\", user_id=\"user-1\")\n```\n\n## Async Support\n\n```python\nimport asyncio\nfrom mem0 import AsyncMemory\n\nasync def main():\n    memory = AsyncMemory()\n\n    await memory.add(\n        [{\"role\": \"user\", \"content\": \"I'm learning Rust\"}],\n        user_id=\"user-1\",\n    )\n\n    results = await memory.search(\"programming languages\", user_id=\"user-1\")\n    for m in results:\n        print(m[\"memory\"], m[\"score\"])\n\n    # Get all\n    all_mems = await memory.get_all(user_id=\"user-1\")\n\nasyncio.run(main())\n```\n\n## Memory with Metadata & Filters\n\n```python\nfrom mem0 import Memory\n\nm = Memory()\n\n# Add with metadata\nm.add(\n    \"User prefers vegetarian food\",\n    user_id=\"alice\",\n    metadata={\"category\": \"preference\", \"source\": \"onboarding\"},\n)\n\n# Search with filters\nresults = m.search(\n    \"food preferences\",\n    user_id=\"alice\",\n    filters={\"metadata\": {\"category\": \"preference\"}},\n    limit=5,\n)\n\n# Get specific memory by ID\nmem = m.get(memory_id=\"mem-xxx\")\nprint(mem[\"memory\"], mem[\"created_at\"])\n```\n\n## CrewAI Integration\n\n```python\nfrom crewai import Agent\nfrom mem0 import Memory\n\nmemory = Memory()\n\nclass MemoryAwareAgent:\n    def __init__(self, user_id: str):\n        self.user_id = user_id\n        self.memory = memory\n\n    def get_context(self, task: str) -> str:\n        mems = self.memory.search(task, user_id=self.user_id)\n        return \"\\n\".join(f\"- {m['memory']}\" for m in mems)\n\n    def save_interaction(self, messages: list):\n        self.memory.add(messages, user_id=self.user_id)\n```\n\n## Memory Stats\n\n```python\nm = Memory()\n\n# Get memory count for user\nall_mems = m.get_all(user_id=\"alice\")\nprint(f\"Total memories: {len(all_mems)}\")\n\n# Memory history (updates over time)\nhistory = m.history(memory_id=\"mem-xxx\")\nfor event in history:\n    print(event[\"event\"], event[\"old_memory\"], event[\"new_memory\"])\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `memory.search()` returns list of dicts with `memory` and `score` keys — not plain strings\n- [ ] `memory.add()` accepts either a string or a list of messages (conversation format)\n- [ ] Scoping: must pass at least one of `user_id`, `agent_id`, or `run_id`\n- [ ] Graph memory requires `\"version\": \"v1.1\"` in config\n- [ ] Self-hosted requires vector store running (Qdrant\u002FChroma\u002Fpgvector) + LLM configured\n- [ ] `AsyncMemory` for async contexts — `Memory` uses sync API only\n- [ ] Memories are automatically deduplicated\u002Fmerged — duplicate adds won't create duplicates\n","# Mem0 — Intelligent Memory Layer for AI Agents\n\n**Source:** mem0ai\u002Fmem0 (Apache 2.0) — persistent, intelligent memory for AI applications\n\n## Why Mem0\n\n- Automatically extracts facts from conversations and stores them\n- Semantically searches memories relevant to current context\n- Deduplicates and updates conflicting memories\n- Scoped by `user_id`, `agent_id`, `run_id` — flexible memory isolation\n- Supports vector (default) + graph + key-value backends\n\n## Install\n\n```bash\npip install mem0ai\n# Optional: graph memory\npip install mem0ai[graph]\n```\n\n## Quick Start (Managed Cloud)\n\n```python\nfrom mem0 import MemoryClient\n\nclient = MemoryClient(api_key=\"your-mem0-api-key\")\n\n# Add memories from a conversation\nmessages = [\n    {\"role\": \"user\", \"content\": \"I'm Alice and I love hiking.\"},\n    {\"role\": \"assistant\", \"content\": \"That's great! Do you have a favorite trail?\"},\n    {\"role\": \"user\", \"content\": \"Yes, the Pacific Crest Trail is my favorite.\"},\n]\nclient.add(messages, user_id=\"alice\")\n\n# Search memories\nresults = client.search(\"outdoor activities\", user_id=\"alice\")\nfor mem in results:\n    print(mem[\"memory\"])  # \"User loves hiking\" \u002F \"Favorite trail is PCT\"\n\n# Get all memories for a user\nall_mems = client.get_all(user_id=\"alice\")\n\n# Update a memory\nclient.update(memory_id=\"mem-xxx\", data=\"User loves hiking and cycling\")\n\n# Delete\nclient.delete(memory_id=\"mem-xxx\")\nclient.delete_all(user_id=\"alice\")\n```\n\n## Self-Hosted (Open Source)\n\n```python\nfrom mem0 import Memory\n\nconfig = {\n    \"llm\": {\n        \"provider\": \"anthropic\",\n        \"config\": {\n            \"model\": \"claude-sonnet-4-5\",\n            \"api_key\": \"your-anthropic-key\",\n        },\n    },\n    \"embedder\": {\n        \"provider\": \"openai\",\n        \"config\": {\"model\": \"text-embedding-3-small\"},\n    },\n    \"vector_store\": {\n        \"provider\": \"qdrant\",\n        \"config\": {\n            \"collection_name\": \"mem0_memories\",\n            \"host\": \"localhost\",\n            \"port\": 6333,\n        },\n    },\n}\n\nmemory = Memory.from_config(config)\n```\n\n## Memory Scoping\n\n```python\nfrom mem0 import Memory\n\nm = Memory()\n\n# User-scoped memory (persists across sessions)\nm.add(\"User prefers dark mode\", user_id=\"user-123\")\nm.add(\"User is a Python developer\", user_id=\"user-123\")\n\n# Agent-scoped memory (shared across users for this agent)\nm.add(\"This agent specializes in cooking recipes\", agent_id=\"chef-bot\")\n\n# Session-scoped memory (single conversation)\nm.add(\"User asked about pasta today\", user_id=\"user-123\", run_id=\"session-abc\")\n\n# Search within scope\nresults = m.search(\"coding preferences\", user_id=\"user-123\")\n```\n\n## Integration with AI Agents\n\n```python\nfrom mem0 import Memory\nfrom anthropic import Anthropic\n\nmemory = Memory()\nclient = Anthropic()\n\ndef chat_with_memory(user_id: str, user_message: str) -> str:\n    # 1. Search relevant memories\n    relevant_memories = memory.search(user_message, user_id=user_id)\n    mem_context = \"\\n\".join(f\"- {m['memory']}\" for m in relevant_memories)\n\n    # 2. Build prompt with memory context\n    system = f\"\"\"You are a helpful assistant.\nRelevant memories about this user:\n{mem_context if mem_context else \"No memories yet.\"}\n\"\"\"\n\n    # 3. Get LLM response\n    response = client.messages.create(\n        model=\"claude-sonnet-4-5\",\n        max_tokens=1024,\n        system=system,\n        messages=[{\"role\": \"user\", \"content\": user_message}],\n    )\n    answer = response.content[0].text\n\n    # 4. Extract and store new memories from this exchange\n    memory.add(\n        [\n            {\"role\": \"user\", \"content\": user_message},\n            {\"role\": \"assistant\", \"content\": answer},\n        ],\n        user_id=user_id,\n    )\n\n    return answer\n\n# Usage\nprint(chat_with_memory(\"alice\", \"My name is Alice and I love hiking.\"))\nprint(chat_with_memory(\"alice\", \"What do you know about me?\"))\n```\n\n## Graph Memory (Relationships)\n\n```python\nfrom mem0 import Memory\n\nconfig = {\n    \"graph_store\": {\n        \"provider\": \"neo4j\",\n        \"config\": {\n            \"url\": \"bolt:\u002F\u002Flocalhost:7687\",\n            \"username\": \"neo4j\",\n            \"password\": \"password\",\n        },\n    },\n    \"llm\": {\"provider\": \"anthropic\", \"config\": {\"model\": \"claude-sonnet-4-5\"}},\n    \"version\": \"v1.1\",  # required for graph memory\n}\n\nmemory = Memory.from_config(config)\n\n# Graph memory automatically extracts relationships\nmemory.add(\"Alice works at Anthropic and knows Bob\", user_id=\"user-1\")\nmemory.add(\"Bob is a senior engineer\", user_id=\"user-1\")\n\n# Graph-aware search finds Alice→Anthropic→Bob relationships\nresults = memory.search(\"Who does Alice work with?\", user_id=\"user-1\")\n```\n\n## Async Support\n\n```python\nimport asyncio\nfrom mem0 import AsyncMemory\n\nasync def main():\n    memory = AsyncMemory()\n\n    await memory.add(\n        [{\"role\": \"user\", \"content\": \"I'm learning Rust\"}],\n        user_id=\"user-1\",\n    )\n\n    results = await memory.search(\"programming languages\", user_id=\"user-1\")\n    for m in results:\n        print(m[\"memory\"], m[\"score\"])\n\n    # Get all\n    all_mems = await memory.get_all(user_id=\"user-1\")\n\nasyncio.run(main())\n```\n\n## Memory with Metadata & Filters\n\n```python\nfrom mem0 import Memory\n\nm = Memory()\n\n# Add with metadata\nm.add(\n    \"User prefers vegetarian food\",\n    user_id=\"alice\",\n    metadata={\"category\": \"preference\", \"source\": \"onboarding\"},\n)\n\n# Search with filters\nresults = m.search(\n    \"food preferences\",\n    user_id=\"alice\",\n    filters={\"metadata\": {\"category\": \"preference\"}},\n    limit=5,\n)\n\n# Get specific memory by ID\nmem = m.get(memory_id=\"mem-xxx\")\nprint(mem[\"memory\"], mem[\"created_at\"])\n```\n\n## CrewAI Integration\n\n```python\nfrom crewai import Agent\nfrom mem0 import Memory\n\nmemory = Memory()\n\nclass MemoryAwareAgent:\n    def __init__(self, user_id: str):\n        self.user_id = user_id\n        self.memory = memory\n\n    def get_context(self, task: str) -> str:\n        mems = self.memory.search(task, user_id=self.user_id)\n        return \"\\n\".join(f\"- {m['memory']}\" for m in mems)\n\n    def save_interaction(self, messages: list):\n        self.memory.add(messages, user_id=self.user_id)\n```\n\n## Memory Stats\n\n```python\nm = Memory()\n\n# Get memory count for user\nall_mems = m.get_all(user_id=\"alice\")\nprint(f\"Total memories: {len(all_mems)}\")\n\n# Memory history (updates over time)\nhistory = m.history(memory_id=\"mem-xxx\")\nfor event in history:\n    print(event[\"event\"], event[\"old_memory\"], event[\"new_memory\"])\n```\n\n## Anti-Fake-Pass Checks\n\n- [ ] `memory.search()` returns list of dicts with `memory` and `score` keys — not plain strings\n- [ ] `memory.add()` accepts either a string or a list of messages (conversation format)\n- [ ] Scoping: must pass at least one of `user_id`, `agent_id`, or `run_id`\n- [ ] Graph memory requires `\"version\": \"v1.1\"` in config\n- [ ] Self-hosted requires vector store running (Qdrant\u002FChroma\u002Fpgvector) + LLM configured\n- [ ] `AsyncMemory` for async contexts — `Memory` uses sync API only\n- [ ] Memories are automatically deduplicated\u002Fmerged — duplicate adds won't create duplicates\n",{"name":5,"see_also":24,"triggers":28,"description":7,"do_not_use_for":40},[25,26,27],"langgraph","crewai","pydantic-ai",[5,29,30,31,32,33,34,35,36,37,38,39],"mem0ai","memory layer ai agent","persistent agent memory","user memory ai","add memory agent","search memory","memory.add","memory.search","agent long term memory","personalized ai memory","cross session memory",[41,42,43],"Short-term conversation history — use LangChain ConversationBufferMemory instead","Vector search only — use pgvector or qdrant directly","State management within a single LangGraph run — use checkpointer instead","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fmem0",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 mem0",{"tool":60,"command":61},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill mem0",{"tool":63,"command":64},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill mem0","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fmem0\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",[],[]]