[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CYA8NKHD6C4MSVHGNF49FE":3,"skill-same:01M7CYA8NKHD6C4MSVHGNF49FE":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CYA8NKHD6C4MSVHGNF49FE","cognee-integrations",null,"Use when the user wants to connect cognee to external services — switching LLM or embedding providers (OpenAI, Azure, Gemini, Anthropic, Ollama, OpenRouter), changing databases (Postgres, PGVector, Neo4j, Neptune, Turso), S3 storage, or the MCP server for IDE integration.","GG-QandV\u002Fclone_cognee","GG-QandV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F220055168?v=4","01M7CY9H49G02Z6F9P4PYKFXRM","Yevhenii N","01M7CY9H5AR4XHN42K520M67C4",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FGG-QandV\u002Fclone_cognee\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcognee-integrations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cognee-integrations\ndescription: Use when the user wants to connect cognee to external services — switching LLM or embedding providers (OpenAI, Azure, Gemini, Anthropic, Ollama, OpenRouter), changing databases (Postgres, PGVector, Neo4j, Neptune, Turso), S3 storage, or the MCP server for IDE integration.\n---\n\n# Set up cognee integrations\n\nAll integration config is environment variables (`.env`). The authoritative,\nalways-current list with commented examples is `.env.template` at the repo\nroot — check it before inventing variable names. Install the matching extra\nbefore switching a backend (e.g. `pip install cognee[postgres]`).\n\n## LLM providers\n\nDefault is OpenAI (`LLM_API_KEY` is all you need). To switch, set\n`LLM_PROVIDER`, `LLM_MODEL`, `LLM_API_KEY`, and (where relevant)\n`LLM_ENDPOINT` \u002F `LLM_API_VERSION`:\n\n- **Azure OpenAI**: `LLM_PROVIDER=azure`, `LLM_MODEL=azure\u002Fgpt-4o-mini`, endpoint + api version required.\n- **Gemini** (no extra needed): `LLM_PROVIDER=gemini`, `LLM_MODEL=gemini\u002Fgemini-2.0-flash-exp`.\n- **Anthropic** (`cognee[anthropic]`): `LLM_PROVIDER=anthropic`, model e.g. `claude-3-5-sonnet-20241022`.\n- **Ollama, local** (`cognee[ollama]`): `LLM_PROVIDER=ollama`, `LLM_ENDPOINT=http:\u002F\u002Flocalhost:11434\u002Fv1`, and set the embedding block + `HUGGINGFACE_TOKENIZER` too.\n- **Custom \u002F OpenRouter \u002F vLLM**: `LLM_PROVIDER=custom` with the provider's OpenAI-compatible endpoint.\n- **AWS Bedrock** (`cognee[aws]`): `LLM_PROVIDER=bedrock` + AWS credentials\u002Fregion.\n\n**The classic trap**: LLM and embeddings are configured independently\n(`EMBEDDING_PROVIDER`, `EMBEDDING_MODEL`, `EMBEDDING_ENDPOINT`,\n`EMBEDDING_API_KEY`). Configuring only one leaves the other on OpenAI —\neither keep a valid OpenAI key or configure both.\n\n## Databases\n\n- **Relational** (`DB_PROVIDER`): sqlite (default) or postgres\n  (`cognee[postgres]`; host\u002Fport\u002Fuser\u002Fpassword\u002Fname via `DB_*` vars).\n- **Vector** (`VECTOR_DB_PROVIDER`): lancedb (default), pgvector\n  (`cognee[postgres]`, needs `VECTOR_DB_URL`), neptune_analytics\n  (`cognee[neptune]`), turso (`cognee[turso]`). Anything else (ChromaDB,\n  Qdrant, Weaviate, Milvus, …) lives in community adapters — install from\n  https:\u002F\u002Fgithub.com\u002Ftopoteretes\u002Fcognee-community and register with\n  `use_vector_adapter` before use; setting `VECTOR_DB_PROVIDER` alone raises\n  \"Unsupported vector database provider\".\n- **Graph** (`GRAPH_DATABASE_PROVIDER`): ladybug (default), neo4j\n  (`cognee[neo4j]`, bolt URL + credentials), neptune (`cognee[neptune]`),\n  ladybug-remote, postgres (no raw Cypher \u002F natural-language search).\n\nThe repo `docker-compose.yml` ships ready-to-use `postgres` (pgvector) and\n`neo4j` profiles with matching default credentials. From a container, reach\nhost services with `DB_HOST=host.docker.internal`.\n\n## Storage, cache, and the rest\n\n- **S3 storage** (`cognee[aws]`): `STORAGE_BACKEND=s3` + bucket\u002Fcredentials,\n  and point `DATA_ROOT_DIRECTORY`\u002F`SYSTEM_ROOT_DIRECTORY` at `s3:\u002F\u002F` paths.\n- **Session cache**: `CACHE_BACKEND` = sqlite (default) | postgres | redis | fs | tapes.\n- **Ontologies**: `ONTOLOGY_FILE_PATH` to an OWL file, resolver\u002Fmatching via\n  `ONTOLOGY_RESOLVER` \u002F `MATCHING_STRATEGY`.\n\n## MCP server (IDE integration)\n\n`docker compose --profile mcp up` starts the MCP server on port 8001\n(Streamable HTTP at `http:\u002F\u002Flocalhost:8001\u002Fmcp`), built from `cognee-mcp\u002F`. Point Cursor \u002F Claude Desktop \u002F\nClaude Code at it to use cognee memory from the IDE. Configure its `DB_*` env\nto match the main service so both see the same data.\n\n## After changing providers mid-project\n\nEmbeddings from different models are not comparable — after switching the\nembedding provider or model, reset local state (`cognee-cli forget --all` or\n`await cognee.forget(everything=True)`) and re-ingest with `remember()`.\n\nTo drop just the graph and vectors while keeping the ingested files, use\n`await cognee.forget(dataset=\"my_project\", memory_only=True)` — the dataset can\nthen be rebuilt under the new embedding model without re-uploading anything.\n","# Set up cognee integrations\n\nAll integration config is environment variables (`.env`). The authoritative,\nalways-current list with commented examples is `.env.template` at the repo\nroot — check it before inventing variable names. Install the matching extra\nbefore switching a backend (e.g. `pip install cognee[postgres]`).\n\n## LLM providers\n\nDefault is OpenAI (`LLM_API_KEY` is all you need). To switch, set\n`LLM_PROVIDER`, `LLM_MODEL`, `LLM_API_KEY`, and (where relevant)\n`LLM_ENDPOINT` \u002F `LLM_API_VERSION`:\n\n- **Azure OpenAI**: `LLM_PROVIDER=azure`, `LLM_MODEL=azure\u002Fgpt-4o-mini`, endpoint + api version required.\n- **Gemini** (no extra needed): `LLM_PROVIDER=gemini`, `LLM_MODEL=gemini\u002Fgemini-2.0-flash-exp`.\n- **Anthropic** (`cognee[anthropic]`): `LLM_PROVIDER=anthropic`, model e.g. `claude-3-5-sonnet-20241022`.\n- **Ollama, local** (`cognee[ollama]`): `LLM_PROVIDER=ollama`, `LLM_ENDPOINT=http:\u002F\u002Flocalhost:11434\u002Fv1`, and set the embedding block + `HUGGINGFACE_TOKENIZER` too.\n- **Custom \u002F OpenRouter \u002F vLLM**: `LLM_PROVIDER=custom` with the provider's OpenAI-compatible endpoint.\n- **AWS Bedrock** (`cognee[aws]`): `LLM_PROVIDER=bedrock` + AWS credentials\u002Fregion.\n\n**The classic trap**: LLM and embeddings are configured independently\n(`EMBEDDING_PROVIDER`, `EMBEDDING_MODEL`, `EMBEDDING_ENDPOINT`,\n`EMBEDDING_API_KEY`). Configuring only one leaves the other on OpenAI —\neither keep a valid OpenAI key or configure both.\n\n## Databases\n\n- **Relational** (`DB_PROVIDER`): sqlite (default) or postgres\n  (`cognee[postgres]`; host\u002Fport\u002Fuser\u002Fpassword\u002Fname via `DB_*` vars).\n- **Vector** (`VECTOR_DB_PROVIDER`): lancedb (default), pgvector\n  (`cognee[postgres]`, needs `VECTOR_DB_URL`), neptune_analytics\n  (`cognee[neptune]`), turso (`cognee[turso]`). Anything else (ChromaDB,\n  Qdrant, Weaviate, Milvus, …) lives in community adapters — install from\n  https:\u002F\u002Fgithub.com\u002Ftopoteretes\u002Fcognee-community and register with\n  `use_vector_adapter` before use; setting `VECTOR_DB_PROVIDER` alone raises\n  \"Unsupported vector database provider\".\n- **Graph** (`GRAPH_DATABASE_PROVIDER`): ladybug (default), neo4j\n  (`cognee[neo4j]`, bolt URL + credentials), neptune (`cognee[neptune]`),\n  ladybug-remote, postgres (no raw Cypher \u002F natural-language search).\n\nThe repo `docker-compose.yml` ships ready-to-use `postgres` (pgvector) and\n`neo4j` profiles with matching default credentials. From a container, reach\nhost services with `DB_HOST=host.docker.internal`.\n\n## Storage, cache, and the rest\n\n- **S3 storage** (`cognee[aws]`): `STORAGE_BACKEND=s3` + bucket\u002Fcredentials,\n  and point `DATA_ROOT_DIRECTORY`\u002F`SYSTEM_ROOT_DIRECTORY` at `s3:\u002F\u002F` paths.\n- **Session cache**: `CACHE_BACKEND` = sqlite (default) | postgres | redis | fs | tapes.\n- **Ontologies**: `ONTOLOGY_FILE_PATH` to an OWL file, resolver\u002Fmatching via\n  `ONTOLOGY_RESOLVER` \u002F `MATCHING_STRATEGY`.\n\n## MCP server (IDE integration)\n\n`docker compose --profile mcp up` starts the MCP server on port 8001\n(Streamable HTTP at `http:\u002F\u002Flocalhost:8001\u002Fmcp`), built from `cognee-mcp\u002F`. Point Cursor \u002F Claude Desktop \u002F\nClaude Code at it to use cognee memory from the IDE. Configure its `DB_*` env\nto match the main service so both see the same data.\n\n## After changing providers mid-project\n\nEmbeddings from different models are not comparable — after switching the\nembedding provider or model, reset local state (`cognee-cli forget --all` or\n`await cognee.forget(everything=True)`) and re-ingest with `remember()`.\n\nTo drop just the graph and vectors while keeping the ingested files, use\n`await cognee.forget(dataset=\"my_project\", memory_only=True)` — the dataset can\nthen be rebuilt under the new embedding model without re-uploading anything.\n",{"name":5,"description":7},"main","d3c91e153685d31a8df7acf5f8b28647a774ff33",".claude\u002Fskills\u002Fcognee-integrations","https:\u002F\u002Fgithub.com\u002FGG-QandV\u002Fclone_cognee","https:\u002F\u002Fgithub.com\u002FGG-QandV","https:\u002F\u002Fkeysingate.com\u002F","2026-09-17 18:52:29",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add GG-QandV\u002Fclone_cognee --skill cognee-integrations",{"tool":37,"command":38},"bunx","bunx skills add GG-QandV\u002Fclone_cognee --skill cognee-integrations",{"tool":40,"command":41},"pnpm","pnpm dlx skills add GG-QandV\u002Fclone_cognee --skill cognee-integrations","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGG-QandV\u002Fclone_cognee\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcognee-integrations\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7CYBGRTBNN40SCW8A70NPYC","skill-feedback-writer","Use to identify missing instructions in another skill based on its output.","https:\u002F\u002Fgithub.com\u002FGG-QandV\u002Fclone_cognee\u002Fblob\u002Fmain\u002Fexamples\u002Fdemos\u002Ffeedback\u002Fskill_feedback_loop\u002Fskills\u002Fskill-feedback-writer\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7CYBF54ZRAADPJAAZ27QM7D","pr-comment-evaluator","Use to judge whether a PR review comment sounds polite.","https:\u002F\u002Fgithub.com\u002FGG-QandV\u002Fclone_cognee\u002Fblob\u002Fmain\u002Fexamples\u002Fdemos\u002Ffeedback\u002Fskill_feedback_loop\u002Fskills\u002Fpr-comment-evaluator\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7CYBDRNDMBX4N85SHXXM6X3","diff-risk-explainer","Use to briefly explain small code diffs.","https:\u002F\u002Fgithub.com\u002FGG-QandV\u002Fclone_cognee\u002Fblob\u002Fmain\u002Fexamples\u002Fdemos\u002Ffeedback\u002Fskill_feedback_loop\u002Fskills\u002Fdiff-risk-explainer\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7CYATY5MQ0WE9D9WZZ15FA2","cognee","Use this skill whenever the user asks about Cognee, AI memory, persistent agent memory, self-improving agents, agents learning from feedback, knowledge graphs, graph-based RAG, long-term memory for agents, short-term memory for agents, personalization, personas, temporal search, temporal knowledge graphs, ontology-based extraction, ontology grounding, feedback, Cypher search, natural-language graph search, chunk search, RAG search, cross-session memory, session feedback, feedback loops, session based memory, redis based memory, knowledge promotion. Also use when the user describes the workflow such as: \"turn documents into a knowledge graph\", \"build memory from files\", \"search my graph\", \"extract entities and relations\", \"sync data into a graph\", \"update graph memory\", \"store memories for an agent\", \"help my agent learn over time\", \"visualize a knowledge graph built from documents\", \"let the agent learn\", \"adaptive agents\", \"personalized agents\", \"session based personalization\", \"find important ontologies\", \"find custom pydantic models\", \"isolate agentic behaviour\", \"add permission control to retrieval\", \"reduce context bloating\".","https:\u002F\u002Fgithub.com\u002FGG-QandV\u002Fclone_cognee\u002Fblob\u002Fmain\u002Fcognee\u002Fskill.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7CYANBAR44V6KV0Y3V9CXDB","cognee-server","Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK or other clients to it, and choosing the right auth posture.","https:\u002F\u002Fgithub.com\u002FGG-QandV\u002Fclone_cognee\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcognee-server\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7CYAEP5XHRND568JR5E9YSK","cognee-permissions","Use when working with cognee's permission system — understanding or changing how users, roles, and tenants get access to datasets, how ACL grants work, where permissions are enforced in add\u002Fcognify\u002Fsearch\u002Fdelete, and how the grant records surface in the memory-provenance view.","https:\u002F\u002Fgithub.com\u002FGG-QandV\u002Fclone_cognee\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcognee-permissions\u002FSKILL.md",[],[]]