[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78WB12ZGPP26HTPZM3PHC40":3,"skill-same:01M78WB12ZGPP26HTPZM3PHC40":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},"01M78WB12ZGPP26HTPZM3PHC40","docarray",null,"Use DocArray for multimodal Pydantic-style documents, typed DocList and DocVec batches, serialization and local storage, FastAPI payloads, and vector retrieval indexes.","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\u002Fdocarray\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: docarray\ndescription: \"Use DocArray for multimodal Pydantic-style documents, typed\n  DocList and DocVec batches, serialization and local storage, FastAPI payloads,\n  and vector retrieval indexes.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# DocArray\n\nUse this repo skill when a task names DocArray or asks for a Python data model for multimodal records, typed document batches, document serialization, local document storage, FastAPI document payloads, or vector-index retrieval.\n\n## Verified baseline\n\nThe verified default is a CPU workflow using DocArray base dependencies plus the `proto`, `pandas`, and `web` extras. Install the public package for normal use:\n\n```bash\npip install -U docarray\n# add only the surfaces you need:\npip install -U \"docarray[proto,pandas,web]\"\npython -c \"import docarray; print(docarray.__version__)\"\n```\n\nFor the current verified `DocVec` path, prefer `numpy\u003C2` and run the bundled smoke helpers before trusting a new environment. Optional tensor frameworks, media loaders, cloud stores, and external vector databases are not implied by the base install.\n\n## Route by task\n\n- **Model a record or multimodal schema**: read [`document-modeling`](sub-skills\u002Fdocument-modeling\u002FSKILL.md) for `BaseDoc`, predefined modality docs, dynamic schemas, `DocList`, `DocVec`, nested fields, and typed tensor shapes.\n- **Serialize, store, stream, or serve documents**: read [`serialization-storage`](sub-skills\u002Fserialization-storage\u002FSKILL.md) for JSON, protobuf, bytes, base64, binary files, CSV\u002FDataFrame exchange, `file:\u002F\u002F`, S3 boundaries, and `DocArrayResponse`.\n- **Index, search, filter, or persist vectors**: read [`vector-indexing`](sub-skills\u002Fvector-indexing\u002FSKILL.md) for `InMemoryExactNNIndex`, query builders, subindexes, persistence, and optional backend selection.\n\nTasks that span multiple surfaces should start here, choose the schema in `document-modeling`, then hand the resulting typed documents to `serialization-storage` or `vector-indexing`.\n\n## Fast decisions\n\n| Need | First choice | Watch for |\n| --- | --- | --- |\n| One validated data point | `BaseDoc` subclass | Required fields, nested docs, and per-document tensor shapes. |\n| Mutable\u002Freorderable\u002Fstreaming collection | `DocList[MyDoc]` | Typed lists are homogeneous; bare `DocList` may be heterogeneous. |\n| Contiguous ML batch | `DocVec[MyDoc]` | Homogeneous fields; optional doc\u002Ftensor columns must be all present or all missing. |\n| Human-readable transport | JSON | Rich tensor\u002Flist unions may need explicit schema handling. |\n| Compact trusted transport | protobuf or protobuf-array | Install `docarray[proto]`; document unions are not protobuf-safe. |\n| Local retrieval prototype | `InMemoryExactNNIndex[MyDoc]` | Dimensioned vector field and backend-specific filter\u002Fquery behavior. |\n| Production\u002Fvector service | Optional backend | Install and verify the chosen client, service, credentials, schema, and metric separately. |\n\n## Common failure boundaries\n\n- Missing `google.protobuf`, `pandas`, `fastapi`, or backend client: install the matching narrow extra; do not install `full` by default.\n- `DocVec` fails with a NumPy `device` error: check NumPy compatibility and try `numpy\u003C2` for the current verified CPU path.\n- File-store push raises `FileNotFoundError`: create the explicit parent namespace directory first.\n- CSV cannot rebuild tensor fields: use JSON, protobuf-array, binary, or DataFrame instead; CSV is safest for scalar rows.\n- In-memory query builder does not support text search, and equal-score result ties can expose a comparison edge case; see the vector troubleshooting reference.\n\nRead [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting recovery guidance and [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill matches a changed checkout.\n\n## Routing metadata path convention\n\nIn `references\u002Frepo-routing-metadata.json`, every `useful_entry_points` value is a path relative to this DocArray skill root (the directory containing this `SKILL.md`), not a repository- or bundle-prefixed path.\n\n## Safe bundled checks\n\nThese helpers are self-contained and do not require the original repository checkout:\n\n```bash\npython sub-skills\u002Fdocument-modeling\u002Fscripts\u002Fschema_smoke.py --help\npython sub-skills\u002Fserialization-storage\u002Fscripts\u002Froundtrip_smoke.py --help\npython sub-skills\u002Fvector-indexing\u002Fscripts\u002Finmemory_index_smoke.py --help\npython scripts\u002Fcheck_env.py --help\n```\n\nRun the relevant helper after installing the package and selected extras. Helpers use tiny in-memory or temporary-file fixtures; they do not start databases, use credentials, or download models.\n\n## Public capability boundaries\n\nDocArray also exposes Torch, TensorFlow, JAX, image\u002Faudio\u002Fvideo\u002Fmesh loaders, S3, HNSWLib, Qdrant, Weaviate, Elasticsearch, Redis, Milvus, MongoDB Atlas, Epsilla, and Jina\u002FFastAPI integrations. Those are routed by the sub-skills but remain optional until their exact dependency variant, service\u002Fnetwork\u002Fcredential plan, and native smoke have been verified.\n","# DocArray\n\nUse this repo skill when a task names DocArray or asks for a Python data model for multimodal records, typed document batches, document serialization, local document storage, FastAPI document payloads, or vector-index retrieval.\n\n## Verified baseline\n\nThe verified default is a CPU workflow using DocArray base dependencies plus the `proto`, `pandas`, and `web` extras. Install the public package for normal use:\n\n```bash\npip install -U docarray\n# add only the surfaces you need:\npip install -U \"docarray[proto,pandas,web]\"\npython -c \"import docarray; print(docarray.__version__)\"\n```\n\nFor the current verified `DocVec` path, prefer `numpy\u003C2` and run the bundled smoke helpers before trusting a new environment. Optional tensor frameworks, media loaders, cloud stores, and external vector databases are not implied by the base install.\n\n## Route by task\n\n- **Model a record or multimodal schema**: read [`document-modeling`](sub-skills\u002Fdocument-modeling\u002FSKILL.md) for `BaseDoc`, predefined modality docs, dynamic schemas, `DocList`, `DocVec`, nested fields, and typed tensor shapes.\n- **Serialize, store, stream, or serve documents**: read [`serialization-storage`](sub-skills\u002Fserialization-storage\u002FSKILL.md) for JSON, protobuf, bytes, base64, binary files, CSV\u002FDataFrame exchange, `file:\u002F\u002F`, S3 boundaries, and `DocArrayResponse`.\n- **Index, search, filter, or persist vectors**: read [`vector-indexing`](sub-skills\u002Fvector-indexing\u002FSKILL.md) for `InMemoryExactNNIndex`, query builders, subindexes, persistence, and optional backend selection.\n\nTasks that span multiple surfaces should start here, choose the schema in `document-modeling`, then hand the resulting typed documents to `serialization-storage` or `vector-indexing`.\n\n## Fast decisions\n\n| Need | First choice | Watch for |\n| --- | --- | --- |\n| One validated data point | `BaseDoc` subclass | Required fields, nested docs, and per-document tensor shapes. |\n| Mutable\u002Freorderable\u002Fstreaming collection | `DocList[MyDoc]` | Typed lists are homogeneous; bare `DocList` may be heterogeneous. |\n| Contiguous ML batch | `DocVec[MyDoc]` | Homogeneous fields; optional doc\u002Ftensor columns must be all present or all missing. |\n| Human-readable transport | JSON | Rich tensor\u002Flist unions may need explicit schema handling. |\n| Compact trusted transport | protobuf or protobuf-array | Install `docarray[proto]`; document unions are not protobuf-safe. |\n| Local retrieval prototype | `InMemoryExactNNIndex[MyDoc]` | Dimensioned vector field and backend-specific filter\u002Fquery behavior. |\n| Production\u002Fvector service | Optional backend | Install and verify the chosen client, service, credentials, schema, and metric separately. |\n\n## Common failure boundaries\n\n- Missing `google.protobuf`, `pandas`, `fastapi`, or backend client: install the matching narrow extra; do not install `full` by default.\n- `DocVec` fails with a NumPy `device` error: check NumPy compatibility and try `numpy\u003C2` for the current verified CPU path.\n- File-store push raises `FileNotFoundError`: create the explicit parent namespace directory first.\n- CSV cannot rebuild tensor fields: use JSON, protobuf-array, binary, or DataFrame instead; CSV is safest for scalar rows.\n- In-memory query builder does not support text search, and equal-score result ties can expose a comparison edge case; see the vector troubleshooting reference.\n\nRead [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for cross-cutting recovery guidance and [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before deciding whether this skill matches a changed checkout.\n\n## Routing metadata path convention\n\nIn `references\u002Frepo-routing-metadata.json`, every `useful_entry_points` value is a path relative to this DocArray skill root (the directory containing this `SKILL.md`), not a repository- or bundle-prefixed path.\n\n## Safe bundled checks\n\nThese helpers are self-contained and do not require the original repository checkout:\n\n```bash\npython sub-skills\u002Fdocument-modeling\u002Fscripts\u002Fschema_smoke.py --help\npython sub-skills\u002Fserialization-storage\u002Fscripts\u002Froundtrip_smoke.py --help\npython sub-skills\u002Fvector-indexing\u002Fscripts\u002Finmemory_index_smoke.py --help\npython scripts\u002Fcheck_env.py --help\n```\n\nRun the relevant helper after installing the package and selected extras. Helpers use tiny in-memory or temporary-file fixtures; they do not start databases, use credentials, or download models.\n\n## Public capability boundaries\n\nDocArray also exposes Torch, TensorFlow, JAX, image\u002Faudio\u002Fvideo\u002Fmesh loaders, S3, HNSWLib, Qdrant, Weaviate, Elasticsearch, Redis, Milvus, MongoDB Atlas, Epsilla, and Jina\u002FFastAPI integrations. Those are routed by the sub-skills but remain optional until their exact dependency variant, service\u002Fnetwork\u002Fcredential plan, and native smoke have been verified.\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\u002Fdocarray",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 docarray",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill docarray",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill docarray","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocarray\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Frepo-provenance.md","REFERENCE","参考文档",3021,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocarray\u002Freferences\u002Frepo-provenance.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-routing-metadata.json",398,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocarray\u002Freferences\u002Frepo-routing-metadata.json",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",2909,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocarray\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_env.py","SCRIPT","脚本",2246,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fdocarray\u002Fscripts\u002Fcheck_env.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",[],[]]