[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Y15YPAD72DC855P98M10N":3,"skill-same:01M78Y15YPAD72DC855P98M10N":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},"01M78Y15YPAD72DC855P98M10N","hnswlib",null,"Use hnswlib 0.9.0 for CPU approximate nearest-neighbor search through its Python bindings or C++11 header-only API, including indexing, filtering, persistence, mutation, and recall checks.","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\u002Fhnswlib\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hnswlib\ndescription: \"Use hnswlib 0.9.0 for CPU approximate nearest-neighbor search\n  through its Python bindings or C++11 header-only API, including indexing,\n  filtering, persistence, mutation, and recall checks.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# hnswlib\n\nUse this repo skill when a task needs `hnswlib` for approximate nearest-neighbor\n(ANN) indexing, querying, filtering, persistence, updates, deletion\u002Freplacement,\nparameter tuning, or exact-recall comparison. The source contract is hnswlib\n0.9.0. It exposes a CPU-native Python extension and a header-only C++11 API; it\ndoes not expose CUDA, ROCm, MPS, or a service\u002FCLI.\n\n## Route first\n\n- For NumPy arrays, `hnswlib.Index`, `hnswlib.BFIndex`, `knn_query`, Python\n  callbacks, pickle, or Python persistence, read\n  [sub-skills\u002Fpython-bindings\u002FSKILL.md](sub-skills\u002Fpython-bindings\u002FSKILL.md).\n- For C++ headers, `HierarchicalNSW`, `BruteforceSearch`, `searchKnn`, filters,\n  stop conditions, multivector\u002Fepsilon search, CMake, or thread ownership,\n  read [sub-skills\u002Fcpp-header-api\u002FSKILL.md](sub-skills\u002Fcpp-header-api\u002FSKILL.md).\n- Read [references\u002Finstallation.md](references\u002Finstallation.md) before a source\n  build or when an import\u002Fcompiler failure is involved.\n- Read [references\u002Fparameter-tuning.md](references\u002Fparameter-tuning.md) when\n  choosing `M`, `ef_construction`, `ef`, capacity, or a recall target.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when a\n  failure spans installation, persistence, data validation, or concurrency.\n\n## Shared operating contract\n\n1. Identify the metric (`l2`, `ip`, or `cosine`), vector dimension, capacity,\n   label type\u002Fpolicy, query `k`, target recall, and whether deletion, replacement,\n   filtering, resizing, or persistence is required.\n2. Prefer the public package install (`pip install hnswlib`) when a compatible\n   wheel exists. A source build needs NumPy, pybind11, a C++11 compiler, and the\n   platform's native threading\u002FOpenMP handling; use the installation reference.\n3. Keep `k \u003C=` the eligible live population and set `ef >= k`. ANN quality and\n   speed depend on both construction and search parameters; validate material\n   recall claims against `BFIndex` or another exact oracle.\n4. Treat index files as binary artifacts tied to compatible metric\u002Fdimension and\n   a deliberate capacity. Set `ef` again after file-based loading because file\n   persistence resets it to the default; pickle preserves Python index state.\n5. Coordinate lifecycle phases. Do not overlap querying with adding, resizing,\n   saving\u002Floading, or destruction. Python filters should use one query thread;\n   keep C++ spaces, filters, stop conditions, and buffers alive for each call.\n6. Use temporary or application-owned paths and bounded fixtures for smoke checks.\n   Do not run large BigANN\u002FSIFT downloads, benchmark-scale tests, or stress suites\n   as a default operating workflow.\n\n## Minimum smoke checks\n\nPython users should run the relevant bundled helper with `--help` and then a\nsmall default invocation from an environment where `hnswlib` is installed:\n`sub-skills\u002Fpython-bindings\u002Fscripts\u002Fpython_lifecycle_smoke.py`,\n`python_filter_smoke.py`, `python_mutation_smoke.py`, or `python_pickle_smoke.py`.\nC++ users should run\n`sub-skills\u002Fcpp-header-api\u002Fscripts\u002Frun_cpp_smoke.sh --help`, then provide an\ninclude root containing `hnswlib\u002Fhnswlib.h`.\n\n## Provenance and scope\n\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) when checking\nwhether this skill matches a repository revision. Read\n[references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json)\nonly as structured routing metadata; it is not an API manual.\n","# hnswlib\n\nUse this repo skill when a task needs `hnswlib` for approximate nearest-neighbor\n(ANN) indexing, querying, filtering, persistence, updates, deletion\u002Freplacement,\nparameter tuning, or exact-recall comparison. The source contract is hnswlib\n0.9.0. It exposes a CPU-native Python extension and a header-only C++11 API; it\ndoes not expose CUDA, ROCm, MPS, or a service\u002FCLI.\n\n## Route first\n\n- For NumPy arrays, `hnswlib.Index`, `hnswlib.BFIndex`, `knn_query`, Python\n  callbacks, pickle, or Python persistence, read\n  [sub-skills\u002Fpython-bindings\u002FSKILL.md](sub-skills\u002Fpython-bindings\u002FSKILL.md).\n- For C++ headers, `HierarchicalNSW`, `BruteforceSearch`, `searchKnn`, filters,\n  stop conditions, multivector\u002Fepsilon search, CMake, or thread ownership,\n  read [sub-skills\u002Fcpp-header-api\u002FSKILL.md](sub-skills\u002Fcpp-header-api\u002FSKILL.md).\n- Read [references\u002Finstallation.md](references\u002Finstallation.md) before a source\n  build or when an import\u002Fcompiler failure is involved.\n- Read [references\u002Fparameter-tuning.md](references\u002Fparameter-tuning.md) when\n  choosing `M`, `ef_construction`, `ef`, capacity, or a recall target.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when a\n  failure spans installation, persistence, data validation, or concurrency.\n\n## Shared operating contract\n\n1. Identify the metric (`l2`, `ip`, or `cosine`), vector dimension, capacity,\n   label type\u002Fpolicy, query `k`, target recall, and whether deletion, replacement,\n   filtering, resizing, or persistence is required.\n2. Prefer the public package install (`pip install hnswlib`) when a compatible\n   wheel exists. A source build needs NumPy, pybind11, a C++11 compiler, and the\n   platform's native threading\u002FOpenMP handling; use the installation reference.\n3. Keep `k \u003C=` the eligible live population and set `ef >= k`. ANN quality and\n   speed depend on both construction and search parameters; validate material\n   recall claims against `BFIndex` or another exact oracle.\n4. Treat index files as binary artifacts tied to compatible metric\u002Fdimension and\n   a deliberate capacity. Set `ef` again after file-based loading because file\n   persistence resets it to the default; pickle preserves Python index state.\n5. Coordinate lifecycle phases. Do not overlap querying with adding, resizing,\n   saving\u002Floading, or destruction. Python filters should use one query thread;\n   keep C++ spaces, filters, stop conditions, and buffers alive for each call.\n6. Use temporary or application-owned paths and bounded fixtures for smoke checks.\n   Do not run large BigANN\u002FSIFT downloads, benchmark-scale tests, or stress suites\n   as a default operating workflow.\n\n## Minimum smoke checks\n\nPython users should run the relevant bundled helper with `--help` and then a\nsmall default invocation from an environment where `hnswlib` is installed:\n`sub-skills\u002Fpython-bindings\u002Fscripts\u002Fpython_lifecycle_smoke.py`,\n`python_filter_smoke.py`, `python_mutation_smoke.py`, or `python_pickle_smoke.py`.\nC++ users should run\n`sub-skills\u002Fcpp-header-api\u002Fscripts\u002Frun_cpp_smoke.sh --help`, then provide an\ninclude root containing `hnswlib\u002Fhnswlib.h`.\n\n## Provenance and scope\n\nRead [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) when checking\nwhether this skill matches a repository revision. Read\n[references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json)\nonly as structured routing metadata; it is not an API manual.\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\u002Fhnswlib",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 hnswlib",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill hnswlib",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill hnswlib","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhnswlib\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Finstallation.md","REFERENCE","参考文档",2706,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhnswlib\u002Freferences\u002Finstallation.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fparameter-tuning.md",2926,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhnswlib\u002Freferences\u002Fparameter-tuning.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",1630,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhnswlib\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",316,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhnswlib\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",4941,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhnswlib\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fenvironment_smoke.py","SCRIPT","脚本",1650,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fhnswlib\u002Fscripts\u002Fenvironment_smoke.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",[],[]]