[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78V7G9SWYRV8GZ1CE8GDRFZ":3,"skill-same:01M78V7G9SWYRV8GZ1CE8GDRFZ":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78V7G9SWYRV8GZ1CE8GDRFZ","memory-knowledge-and-rag",null,"Guides agents using CrewAI memory, knowledge sources, RAG clients and loaders, embedding providers, vector stores, reset-memory commands, and optional retrieval dependencies.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcrewai\u002Fsub-skills\u002Fmemory-knowledge-and-rag\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: memory-knowledge-and-rag\ndescription: \"Guides agents using CrewAI memory, knowledge sources, RAG clients\n  and loaders, embedding providers, vector stores, reset-memory commands, and\n  optional retrieval dependencies.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Memory, Knowledge, and RAG\n\nUse this sub-skill when work involves CrewAI `Memory`, `Knowledge`, `knowledge_sources`, memory scopes\u002Fslices, RAG vector clients, `RagTool`, official RAG loaders, embedding providers, ChromaDB\u002FQdrant\u002FLanceDB storage, or `crewai reset-memories` behavior.\n\n## Route First\n\n- For memory construction, recall depth, scopes, slices, crew\u002Fagent memory behavior, and reset commands, read [references\u002Fmemory-and-knowledge.md](references\u002Fmemory-and-knowledge.md).\n- For `Knowledge`, `knowledge_sources`, crew-level vs agent-level knowledge, source classes, storage collections, and score thresholds, read [references\u002Fmemory-and-knowledge.md](references\u002Fmemory-and-knowledge.md).\n- For direct RAG clients, `RagTool`, data type detection, official loaders, and network\u002Ffile loader boundaries, read [references\u002Frag-loaders.md](references\u002Frag-loaders.md).\n- For embedding provider specs, vector DB configuration, LanceDB\u002FChromaDB\u002FQdrant storage defaults, optional dependencies, and dimension-mismatch prevention, read [references\u002Fembedding-and-storage.md](references\u002Fembedding-and-storage.md).\n- For common failures and fixes, including embedder dimension mismatch, missing optional dependencies, storage path confusion, reset target confusion, unsupported file types, and credential-bound loaders, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- To safely check installed memory, knowledge, RAG, and optional loader imports without LLMs, credentials, network, or destructive operations, run [scripts\u002Fcheck_rag_imports.py](scripts\u002Fcheck_rag_imports.py) with `--help` first.\n\n## Boundaries\n\n- Stay here for retrieval architecture: `Memory`, `Knowledge`, `RagTool`, RAG clients, vector stores, embedders, loaders, reset commands, and optional retrieval dependencies.\n- Use [..\u002Ffiles-and-multimodal\u002FSKILL.md](..\u002Ffiles-and-multimodal\u002FSKILL.md) for low-level file input resolution, MIME\u002Fprovider constraints, multimodal task files, and non-RAG file processing.\n- Use [..\u002Ftools-and-mcp\u002FSKILL.md](..\u002Ftools-and-mcp\u002FSKILL.md) for general tool wrappers, custom `BaseTool` design, MCP, and non-RAG `crewai_tools` exports.\n- Use [..\u002Fllm-and-providers\u002FSKILL.md](..\u002Fllm-and-providers\u002FSKILL.md) for LLM provider credentials, model IDs, base URLs, streaming, and chat\u002Fcompletion auth.\n- Use [..\u002Fcore-runtime\u002FSKILL.md](..\u002Fcore-runtime\u002FSKILL.md) for `Agent`, `Task`, `Crew`, kickoff, process, guardrail, callback, and output design that happens around retrieval.\n- Return to [..\u002F..\u002FSKILL.md](..\u002F..\u002FSKILL.md) when a request spans multiple CrewAI capability areas and needs root routing context.\n\n## Safe Defaults\n\n- Prefer local `StringKnowledgeSource`, `TextFileKnowledgeSource`, JSON\u002FCSV sources, or local `RagTool.add(path=...)` when the user has not approved network retrieval.\n- Do not instantiate loaders that fetch web pages, GitHub repositories, YouTube transcripts, or databases unless the user authorizes network\u002Fdatabase access and provides credentials if needed.\n- Keep embedding provider secrets in runtime environment or user config; never put real API keys, tokens, database URIs, or full local storage paths in generated content.\n- Use one embedding model per existing collection. If the embedder changes, reset or rebuild the relevant memory\u002Fknowledge\u002FRAG collection rather than mixing vector dimensions.\n\n## Usability Targets\n\n- Diagnose a dimension mismatch after changing embedding providers and choose the smallest safe reset\u002Frebuild target.\n- Build a knowledge-enabled crew with local document loaders while avoiding accidental network retrieval.\n","# Memory, Knowledge, and RAG\n\nUse this sub-skill when work involves CrewAI `Memory`, `Knowledge`, `knowledge_sources`, memory scopes\u002Fslices, RAG vector clients, `RagTool`, official RAG loaders, embedding providers, ChromaDB\u002FQdrant\u002FLanceDB storage, or `crewai reset-memories` behavior.\n\n## Route First\n\n- For memory construction, recall depth, scopes, slices, crew\u002Fagent memory behavior, and reset commands, read [references\u002Fmemory-and-knowledge.md](references\u002Fmemory-and-knowledge.md).\n- For `Knowledge`, `knowledge_sources`, crew-level vs agent-level knowledge, source classes, storage collections, and score thresholds, read [references\u002Fmemory-and-knowledge.md](references\u002Fmemory-and-knowledge.md).\n- For direct RAG clients, `RagTool`, data type detection, official loaders, and network\u002Ffile loader boundaries, read [references\u002Frag-loaders.md](references\u002Frag-loaders.md).\n- For embedding provider specs, vector DB configuration, LanceDB\u002FChromaDB\u002FQdrant storage defaults, optional dependencies, and dimension-mismatch prevention, read [references\u002Fembedding-and-storage.md](references\u002Fembedding-and-storage.md).\n- For common failures and fixes, including embedder dimension mismatch, missing optional dependencies, storage path confusion, reset target confusion, unsupported file types, and credential-bound loaders, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- To safely check installed memory, knowledge, RAG, and optional loader imports without LLMs, credentials, network, or destructive operations, run [scripts\u002Fcheck_rag_imports.py](scripts\u002Fcheck_rag_imports.py) with `--help` first.\n\n## Boundaries\n\n- Stay here for retrieval architecture: `Memory`, `Knowledge`, `RagTool`, RAG clients, vector stores, embedders, loaders, reset commands, and optional retrieval dependencies.\n- Use [..\u002Ffiles-and-multimodal\u002FSKILL.md](..\u002Ffiles-and-multimodal\u002FSKILL.md) for low-level file input resolution, MIME\u002Fprovider constraints, multimodal task files, and non-RAG file processing.\n- Use [..\u002Ftools-and-mcp\u002FSKILL.md](..\u002Ftools-and-mcp\u002FSKILL.md) for general tool wrappers, custom `BaseTool` design, MCP, and non-RAG `crewai_tools` exports.\n- Use [..\u002Fllm-and-providers\u002FSKILL.md](..\u002Fllm-and-providers\u002FSKILL.md) for LLM provider credentials, model IDs, base URLs, streaming, and chat\u002Fcompletion auth.\n- Use [..\u002Fcore-runtime\u002FSKILL.md](..\u002Fcore-runtime\u002FSKILL.md) for `Agent`, `Task`, `Crew`, kickoff, process, guardrail, callback, and output design that happens around retrieval.\n- Return to [..\u002F..\u002FSKILL.md](..\u002F..\u002FSKILL.md) when a request spans multiple CrewAI capability areas and needs root routing context.\n\n## Safe Defaults\n\n- Prefer local `StringKnowledgeSource`, `TextFileKnowledgeSource`, JSON\u002FCSV sources, or local `RagTool.add(path=...)` when the user has not approved network retrieval.\n- Do not instantiate loaders that fetch web pages, GitHub repositories, YouTube transcripts, or databases unless the user authorizes network\u002Fdatabase access and provides credentials if needed.\n- Keep embedding provider secrets in runtime environment or user config; never put real API keys, tokens, database URIs, or full local storage paths in generated content.\n- Use one embedding model per existing collection. If the embedder changes, reset or rebuild the relevant memory\u002Fknowledge\u002FRAG collection rather than mixing vector dimensions.\n\n## Usability Targets\n\n- Diagnose a dimension mismatch after changing embedding providers and choose the smallest safe reset\u002Frebuild target.\n- Build a knowledge-enabled crew with local document loaders while avoiding accidental network retrieval.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fcrewai\u002Fsub-skills\u002Fmemory-knowledge-and-rag",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill memory-knowledge-and-rag",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill memory-knowledge-and-rag",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill memory-knowledge-and-rag","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcrewai\u002Fsub-skills\u002Fmemory-knowledge-and-rag\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fembedding-and-storage.md","REFERENCE","参考文档",9383,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcrewai\u002Fsub-skills\u002Fmemory-knowledge-and-rag\u002Freferences\u002Fembedding-and-storage.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmemory-and-knowledge.md",10734,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcrewai\u002Fsub-skills\u002Fmemory-knowledge-and-rag\u002Freferences\u002Fmemory-and-knowledge.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Frag-loaders.md",9834,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcrewai\u002Fsub-skills\u002Fmemory-knowledge-and-rag\u002Freferences\u002Frag-loaders.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",10845,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcrewai\u002Fsub-skills\u002Fmemory-knowledge-and-rag\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck_rag_imports.py","SCRIPT","脚本",8295,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcrewai\u002Fsub-skills\u002Fmemory-knowledge-and-rag\u002Fscripts\u002Fcheck_rag_imports.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]