[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZDBBPFPX0VJYC0HASBXWE":3,"skill-same:01M78ZDBBPFPX0VJYC0HASBXWE":66},{"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},"01M78ZDBBPFPX0VJYC0HASBXWE","indexing-and-querying",null,"Build and query LlamaIndex indexes, persist and reload storage, configure retrievers\u002Fquery engines\u002Fresponse synthesizers, and choose advanced retrieval patterns.","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\u002Fllama-index\u002Fsub-skills\u002Findexing-and-querying\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: indexing-and-querying\ndescription: \"Build and query LlamaIndex indexes, persist and reload storage,\n  configure retrievers\u002Fquery engines\u002Fresponse synthesizers, and choose advanced\n  retrieval patterns.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Indexing and Querying\n\nUse this sub-skill when a user needs practical LlamaIndex RAG mechanics after data has already been loaded or chunked into `Document` or `BaseNode` objects.\n\n## Owns\n\n- Build `VectorStoreIndex` and `SummaryIndex` from documents or nodes.\n- Persist and reload indexes with `StorageContext` and `load_index_from_storage`.\n- Configure `as_retriever`, `as_query_engine`, `VectorIndexRetriever`, `RetrieverQueryEngine`, and response synthesizers.\n- Compose advanced retrieval with `QueryFusionRetriever`, `RouterRetriever`, `RecursiveRetriever`, `RouterQueryEngine`, and `SubQuestionQueryEngine`.\n- Diagnose indexing\u002Fquery failures such as missing models, empty retrieval, persistence path mistakes, filters, tool metadata, and async\u002Fsynthesis mode issues.\n\n## Route Elsewhere\n\n- Use `..\u002Fingestion-and-loading\u002F` for file readers, loaders, chunking, `SentenceSplitter`, `IngestionPipeline`, metadata extraction, and node creation.\n- Use `..\u002Fintegrations-and-storage\u002F` for provider-specific vector stores, database\u002Fcloud installs, and integration-specific credentials.\n- Use `..\u002Fcustomization-and-structured-outputs\u002F` for prompt templates, structured outputs, Pydantic output classes, and output formatting.\n\n## Quick Start\n\n```python\nfrom llama_index.core import Document, Settings, VectorStoreIndex\nfrom llama_index.core.embeddings.mock_embed_model import MockEmbedding\nfrom llama_index.core.llms.mock import MockLLM\n\nSettings.embed_model = MockEmbedding(embed_dim=8)\nSettings.llm = MockLLM(max_tokens=64)\n\nindex = VectorStoreIndex.from_documents([\n    Document(text=\"LlamaIndex builds indexes over nodes.\"),\n    Document(text=\"Retrievers fetch relevant nodes for a query engine.\"),\n])\nquery_engine = index.as_query_engine(similarity_top_k=2)\nprint(query_engine.query(\"What do retrievers do?\"))\n```\n\nFor a no-network smoke test, run the bundled script:\n\n```bash\npython sub-skills\u002Findexing-and-querying\u002Fscripts\u002Fbuild_tiny_mock_index.py\n```\n\n## Workflow\n\n1. Confirm the user already has `Document` or node objects; if not, route loading\u002Fchunking to `ingestion-and-loading`.\n2. Choose index type: `VectorStoreIndex` for semantic similarity retrieval; `SummaryIndex` for small ordered corpora, summaries, or query-all behavior.\n3. Set explicit `Settings.embed_model` and `Settings.llm` or pass models directly to constructors\u002Fquery engines; avoid accidental remote defaults when the environment has no API keys.\n4. Build with `VectorStoreIndex.from_documents(documents)` or `VectorStoreIndex(nodes=nodes)`; constructors accept nodes, not raw `Document` objects.\n5. Query simply with `index.as_query_engine(...)`, or split retrieval\u002Fsynthesis with `index.as_retriever(...)`, `get_response_synthesizer(...)`, and `RetrieverQueryEngine(...)`.\n6. Persist using `index.storage_context.persist(persist_dir=...)`; reload with `StorageContext.from_defaults(persist_dir=...)` and `load_index_from_storage(...)`.\n7. For multi-index systems, wrap engines\u002Fretrievers as tools with clear metadata before using routers or sub-question engines.\n\n## References\n\n- `references\u002Findex-query-recipes.md`: practical recipes for indexes, persistence, retrieval, routers, fusion, and synthesis.\n- `references\u002Fapi-reference.md`: verified constructor signatures and import paths for indexing\u002Fquery APIs.\n- `references\u002Ftroubleshooting.md`: failure-mode diagnosis for embeddings, LLMs, storage, filters, routing, async, and optional integrations.\n","# Indexing and Querying\n\nUse this sub-skill when a user needs practical LlamaIndex RAG mechanics after data has already been loaded or chunked into `Document` or `BaseNode` objects.\n\n## Owns\n\n- Build `VectorStoreIndex` and `SummaryIndex` from documents or nodes.\n- Persist and reload indexes with `StorageContext` and `load_index_from_storage`.\n- Configure `as_retriever`, `as_query_engine`, `VectorIndexRetriever`, `RetrieverQueryEngine`, and response synthesizers.\n- Compose advanced retrieval with `QueryFusionRetriever`, `RouterRetriever`, `RecursiveRetriever`, `RouterQueryEngine`, and `SubQuestionQueryEngine`.\n- Diagnose indexing\u002Fquery failures such as missing models, empty retrieval, persistence path mistakes, filters, tool metadata, and async\u002Fsynthesis mode issues.\n\n## Route Elsewhere\n\n- Use `..\u002Fingestion-and-loading\u002F` for file readers, loaders, chunking, `SentenceSplitter`, `IngestionPipeline`, metadata extraction, and node creation.\n- Use `..\u002Fintegrations-and-storage\u002F` for provider-specific vector stores, database\u002Fcloud installs, and integration-specific credentials.\n- Use `..\u002Fcustomization-and-structured-outputs\u002F` for prompt templates, structured outputs, Pydantic output classes, and output formatting.\n\n## Quick Start\n\n```python\nfrom llama_index.core import Document, Settings, VectorStoreIndex\nfrom llama_index.core.embeddings.mock_embed_model import MockEmbedding\nfrom llama_index.core.llms.mock import MockLLM\n\nSettings.embed_model = MockEmbedding(embed_dim=8)\nSettings.llm = MockLLM(max_tokens=64)\n\nindex = VectorStoreIndex.from_documents([\n    Document(text=\"LlamaIndex builds indexes over nodes.\"),\n    Document(text=\"Retrievers fetch relevant nodes for a query engine.\"),\n])\nquery_engine = index.as_query_engine(similarity_top_k=2)\nprint(query_engine.query(\"What do retrievers do?\"))\n```\n\nFor a no-network smoke test, run the bundled script:\n\n```bash\npython sub-skills\u002Findexing-and-querying\u002Fscripts\u002Fbuild_tiny_mock_index.py\n```\n\n## Workflow\n\n1. Confirm the user already has `Document` or node objects; if not, route loading\u002Fchunking to `ingestion-and-loading`.\n2. Choose index type: `VectorStoreIndex` for semantic similarity retrieval; `SummaryIndex` for small ordered corpora, summaries, or query-all behavior.\n3. Set explicit `Settings.embed_model` and `Settings.llm` or pass models directly to constructors\u002Fquery engines; avoid accidental remote defaults when the environment has no API keys.\n4. Build with `VectorStoreIndex.from_documents(documents)` or `VectorStoreIndex(nodes=nodes)`; constructors accept nodes, not raw `Document` objects.\n5. Query simply with `index.as_query_engine(...)`, or split retrieval\u002Fsynthesis with `index.as_retriever(...)`, `get_response_synthesizer(...)`, and `RetrieverQueryEngine(...)`.\n6. Persist using `index.storage_context.persist(persist_dir=...)`; reload with `StorageContext.from_defaults(persist_dir=...)` and `load_index_from_storage(...)`.\n7. For multi-index systems, wrap engines\u002Fretrievers as tools with clear metadata before using routers or sub-question engines.\n\n## References\n\n- `references\u002Findex-query-recipes.md`: practical recipes for indexes, persistence, retrieval, routers, fusion, and synthesis.\n- `references\u002Fapi-reference.md`: verified constructor signatures and import paths for indexing\u002Fquery APIs.\n- `references\u002Ftroubleshooting.md`: failure-mode diagnosis for embeddings, LLMs, storage, filters, routing, async, and optional integrations.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fllama-index\u002Fsub-skills\u002Findexing-and-querying",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 indexing-and-querying",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill indexing-and-querying",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill indexing-and-querying","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllama-index\u002Fsub-skills\u002Findexing-and-querying\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",8711,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllama-index\u002Fsub-skills\u002Findexing-and-querying\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Findex-query-recipes.md",10050,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllama-index\u002Fsub-skills\u002Findexing-and-querying\u002Freferences\u002Findex-query-recipes.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",7843,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllama-index\u002Fsub-skills\u002Findexing-and-querying\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fbuild_tiny_mock_index.py","SCRIPT","脚本",1553,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllama-index\u002Fsub-skills\u002Findexing-and-querying\u002Fscripts\u002Fbuild_tiny_mock_index.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]