[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7941AX4JDWMNW29KWEAVYVQ":3,"skill-same:01M7941AX4JDWMNW29KWEAVYVQ":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7941AX4JDWMNW29KWEAVYVQ","pretrained-indexing-search",null,"Use RAGatouille RAGPretrainedModel for pretrained checkpoint loading, persisted index creation\u002Floading\u002Fsearch, document IDs\u002Fmetadata, and experimental index CRUD.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fragatouille\u002Fsub-skills\u002Fpretrained-indexing-search\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pretrained-indexing-search\ndescription: \"Use RAGatouille RAGPretrainedModel for pretrained checkpoint\n  loading, persisted index creation\u002Floading\u002Fsearch, document IDs\u002Fmetadata, and\n  experimental index CRUD.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Pretrained Indexing Search\n\nUse this sub-skill when a task needs RAGatouille's `RAGPretrainedModel` for persisted ColBERT\u002FPLAID indexes: loading a pretrained checkpoint, loading an existing index, building an index from documents, searching it, validating result dictionaries, or doing experimental add\u002Fdelete updates.\n\n## Route Here For\n\n- Loading models with `RAGPretrainedModel.from_pretrained(...)` or existing persisted indexes with `RAGPretrainedModel.from_index(...)`.\n- Creating disk-backed indexes with `RAG.index(...)`, including `document_ids`, `document_metadatas`, splitting, preprocessing, `index_root`, `index_name`, `overwrite_index`, `bsize`, and `use_faiss` choices.\n- Searching persisted indexes with `RAG.search(...)`, including single-query vs multi-query result shape, `k`, `doc_ids`, `force_fast`, and `zero_index_ranks`.\n- Updating persisted indexes with `RAG.add_to_index(...)` or `RAG.delete_from_index(...)`, while treating CRUD support as experimental.\n- Diagnosing input-shape, ID, metadata, index-name, loading, CPU\u002FGPU\u002FFAISS, and dependency compatibility problems before running expensive model work.\n\n## Route Elsewhere\n\n- Use `..\u002Findex-free-reranking\u002FSKILL.md` for `rerank`, `encode`, `search_encoded_docs`, or small transient in-memory document sets.\n- Use `..\u002Ftraining-data-finetuning\u002FSKILL.md` for `RAGTrainer`, data prep, hard negatives, training, or fine-tuning.\n- Use `..\u002Fintegrations-export\u002FSKILL.md` for LangChain retrievers\u002Fcompressors, LlamaIndex integration examples, Hugging Face export, or Vespa ONNX export.\n\n## Start Here\n\n1. Read `references\u002Fapi-reference.md` for verified signatures, defaults, persisted index layout, and result schemas.\n2. Read `references\u002Fworkflows.md` for copyable indexing, existing-index search, metadata, filtering, and CRUD recipes.\n3. Read `references\u002Ftroubleshooting.md` before changing dependencies, running downloads, indexing large corpora, using Windows\u002FWSL, or debugging ID\u002Fmetadata\u002Fsearch failures.\n4. Run `scripts\u002Fvalidate_index_inputs.py --help` when you need an offline sanity check for collection, document ID, and metadata consistency before model downloads or indexing.\n\n## Safety Notes\n\n- `from_pretrained` can download model weights; do not run it in lightweight validation unless downloads are allowed.\n- Indexing\u002Fsearch can be slow and may use GPU, FAISS, or PyTorch k-means paths; prefer offline validation and small examples before expensive runs.\n- Keep scripts that use RAGatouille inside `if __name__ == \"__main__\":` when running as standalone programs.\n- For RAGatouille 0.0.9post2, avoid latest LangChain 1.x if `import ragatouille` fails on `langchain.retrievers.document_compressors.base`.\n","# Pretrained Indexing Search\n\nUse this sub-skill when a task needs RAGatouille's `RAGPretrainedModel` for persisted ColBERT\u002FPLAID indexes: loading a pretrained checkpoint, loading an existing index, building an index from documents, searching it, validating result dictionaries, or doing experimental add\u002Fdelete updates.\n\n## Route Here For\n\n- Loading models with `RAGPretrainedModel.from_pretrained(...)` or existing persisted indexes with `RAGPretrainedModel.from_index(...)`.\n- Creating disk-backed indexes with `RAG.index(...)`, including `document_ids`, `document_metadatas`, splitting, preprocessing, `index_root`, `index_name`, `overwrite_index`, `bsize`, and `use_faiss` choices.\n- Searching persisted indexes with `RAG.search(...)`, including single-query vs multi-query result shape, `k`, `doc_ids`, `force_fast`, and `zero_index_ranks`.\n- Updating persisted indexes with `RAG.add_to_index(...)` or `RAG.delete_from_index(...)`, while treating CRUD support as experimental.\n- Diagnosing input-shape, ID, metadata, index-name, loading, CPU\u002FGPU\u002FFAISS, and dependency compatibility problems before running expensive model work.\n\n## Route Elsewhere\n\n- Use `..\u002Findex-free-reranking\u002FSKILL.md` for `rerank`, `encode`, `search_encoded_docs`, or small transient in-memory document sets.\n- Use `..\u002Ftraining-data-finetuning\u002FSKILL.md` for `RAGTrainer`, data prep, hard negatives, training, or fine-tuning.\n- Use `..\u002Fintegrations-export\u002FSKILL.md` for LangChain retrievers\u002Fcompressors, LlamaIndex integration examples, Hugging Face export, or Vespa ONNX export.\n\n## Start Here\n\n1. Read `references\u002Fapi-reference.md` for verified signatures, defaults, persisted index layout, and result schemas.\n2. Read `references\u002Fworkflows.md` for copyable indexing, existing-index search, metadata, filtering, and CRUD recipes.\n3. Read `references\u002Ftroubleshooting.md` before changing dependencies, running downloads, indexing large corpora, using Windows\u002FWSL, or debugging ID\u002Fmetadata\u002Fsearch failures.\n4. Run `scripts\u002Fvalidate_index_inputs.py --help` when you need an offline sanity check for collection, document ID, and metadata consistency before model downloads or indexing.\n\n## Safety Notes\n\n- `from_pretrained` can download model weights; do not run it in lightweight validation unless downloads are allowed.\n- Indexing\u002Fsearch can be slow and may use GPU, FAISS, or PyTorch k-means paths; prefer offline validation and small examples before expensive runs.\n- Keep scripts that use RAGatouille inside `if __name__ == \"__main__\":` when running as standalone programs.\n- For RAGatouille 0.0.9post2, avoid latest LangChain 1.x if `import ragatouille` fails on `langchain.retrievers.document_compressors.base`.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fragatouille\u002Fsub-skills\u002Fpretrained-indexing-search",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill pretrained-indexing-search",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pretrained-indexing-search",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pretrained-indexing-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fragatouille\u002Fsub-skills\u002Fpretrained-indexing-search\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",8378,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fragatouille\u002Fsub-skills\u002Fpretrained-indexing-search\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",8740,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fragatouille\u002Fsub-skills\u002Fpretrained-indexing-search\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",9060,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fragatouille\u002Fsub-skills\u002Fpretrained-indexing-search\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fvalidate_index_inputs.py","SCRIPT","脚本",9669,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fragatouille\u002Fsub-skills\u002Fpretrained-indexing-search\u002Fscripts\u002Fvalidate_index_inputs.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]