[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7942G9BH2PWM9THXNEFV0WW":3,"skill-same:01M7942G9BH2PWM9THXNEFV0WW":75},{"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},"01M7942G9BH2PWM9THXNEFV0WW","rank-bm25",null,"Guides tokenized lexical document retrieval with the rank_bm25 Python package, including BM25Okapi, BM25L, BM25Plus, full-corpus scoring, top-n retrieval, batch scoring, and input troubleshooting.","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\u002Frank-bm25\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: rank-bm25\ndescription: \"Guides tokenized lexical document retrieval with the rank_bm25\n  Python package, including BM25Okapi, BM25L, BM25Plus, full-corpus scoring,\n  top-n retrieval, batch scoring, and input troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# rank_bm25\n\nUse this skill when a task asks for the `rank_bm25` package, Okapi BM25,\nBM25L, BM25+, sparse lexical ranking, or a small in-memory search index over\npre-tokenized documents. It teaches the package API; it is not a production\nsearch-service design and it does not cover the commented-out BM25Adpt\u002FBM25T\nclasses.\n\n## Route the task\n\n- **Install or import**: install the public `rank_bm25` distribution, ensure\n  NumPy is available, and run the import check below.\n- **Build and rank an index**: read [workflows.md](references\u002Fworkflows.md)\n  for a complete tokenization, indexing, scoring, and top-n recipe.\n- **Choose an algorithm or use advanced methods**: read\n  [api-reference.md](references\u002Fapi-reference.md) for verified signatures,\n  defaults, return types, parameter meaning, and batch-score semantics.\n- **Diagnose a failed ranking workflow**: read\n  [troubleshooting.md](references\u002Ftroubleshooting.md), then use the bundled\n  [smoke_rank_bm25.py](scripts\u002Fsmoke_rank_bm25.py) helper for a deterministic\n  tiny-fixture check.\n- **Check whether this knowledge matches a checkout**: read\n  [repo-provenance.md](references\u002Frepo-provenance.md) before deciding whether\n  the skill needs refreshing.\n\n## Minimal setup and import check\n\n```bash\npython -m pip install rank_bm25\npython -c \"from rank_bm25 import BM25Okapi, BM25L, BM25Plus; print('rank_bm25 ready')\"\n```\n\nThe package has no console CLI and its runtime dependency is NumPy. CPU\nexecution is the supported baseline for the covered in-memory workflows.\n\n## Core operating contract\n\n1. Represent every document as a sequence of string tokens, for example\n   `document.split()`; pass a list of those token sequences as `corpus`.\n2. Apply the same lowercasing, normalization, stopword handling, and\n   tokenization policy to documents and queries yourself. The package does no\n   text preprocessing.\n3. Choose `BM25Okapi`, `BM25L`, or `BM25Plus`, construct it once for a corpus,\n   and reuse the index for compatible tokenized queries.\n4. Use `get_scores(query)` for one score per indexed document,\n   `get_top_n(query, documents, n=5)` when you need the original documents,\n   or `get_batch_scores(query, doc_ids)` for a selected index subset.\n5. Keep the original `documents` list in exactly the same order as the corpus;\n   `get_top_n` checks the lengths and maps score indices back into that list.\n6. Validate one known query and expected top document before scaling the corpus.\n   Run `python scripts\u002Fsmoke_rank_bm25.py` from this skill directory or any\n   current working directory after installing the package.\n\nThe package is intentionally lightweight and in-memory. For full API details,\nrecipes, and predictable failure recovery, follow the linked references rather\nthan reopening the source repository.\n","# rank_bm25\n\nUse this skill when a task asks for the `rank_bm25` package, Okapi BM25,\nBM25L, BM25+, sparse lexical ranking, or a small in-memory search index over\npre-tokenized documents. It teaches the package API; it is not a production\nsearch-service design and it does not cover the commented-out BM25Adpt\u002FBM25T\nclasses.\n\n## Route the task\n\n- **Install or import**: install the public `rank_bm25` distribution, ensure\n  NumPy is available, and run the import check below.\n- **Build and rank an index**: read [workflows.md](references\u002Fworkflows.md)\n  for a complete tokenization, indexing, scoring, and top-n recipe.\n- **Choose an algorithm or use advanced methods**: read\n  [api-reference.md](references\u002Fapi-reference.md) for verified signatures,\n  defaults, return types, parameter meaning, and batch-score semantics.\n- **Diagnose a failed ranking workflow**: read\n  [troubleshooting.md](references\u002Ftroubleshooting.md), then use the bundled\n  [smoke_rank_bm25.py](scripts\u002Fsmoke_rank_bm25.py) helper for a deterministic\n  tiny-fixture check.\n- **Check whether this knowledge matches a checkout**: read\n  [repo-provenance.md](references\u002Frepo-provenance.md) before deciding whether\n  the skill needs refreshing.\n\n## Minimal setup and import check\n\n```bash\npython -m pip install rank_bm25\npython -c \"from rank_bm25 import BM25Okapi, BM25L, BM25Plus; print('rank_bm25 ready')\"\n```\n\nThe package has no console CLI and its runtime dependency is NumPy. CPU\nexecution is the supported baseline for the covered in-memory workflows.\n\n## Core operating contract\n\n1. Represent every document as a sequence of string tokens, for example\n   `document.split()`; pass a list of those token sequences as `corpus`.\n2. Apply the same lowercasing, normalization, stopword handling, and\n   tokenization policy to documents and queries yourself. The package does no\n   text preprocessing.\n3. Choose `BM25Okapi`, `BM25L`, or `BM25Plus`, construct it once for a corpus,\n   and reuse the index for compatible tokenized queries.\n4. Use `get_scores(query)` for one score per indexed document,\n   `get_top_n(query, documents, n=5)` when you need the original documents,\n   or `get_batch_scores(query, doc_ids)` for a selected index subset.\n5. Keep the original `documents` list in exactly the same order as the corpus;\n   `get_top_n` checks the lengths and maps score indices back into that list.\n6. Validate one known query and expected top document before scaling the corpus.\n   Run `python scripts\u002Fsmoke_rank_bm25.py` from this skill directory or any\n   current working directory after installing the package.\n\nThe package is intentionally lightweight and in-memory. For full API details,\nrecipes, and predictable failure recovery, follow the linked references rather\nthan reopening the source repository.\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\u002Frank-bm25",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 rank-bm25",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill rank-bm25",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill rank-bm25","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frank-bm25\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",4760,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frank-bm25\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",1779,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frank-bm25\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",333,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frank-bm25\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",5435,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frank-bm25\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fworkflows.md",3271,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frank-bm25\u002Freferences\u002Fworkflows.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fsmoke_rank_bm25.py","SCRIPT","脚本",2411,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frank-bm25\u002Fscripts\u002Fsmoke_rank_bm25.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]