[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792RNQ4BVEST71KXJ7J6DRY":3,"skill-same:01M792RNQ4BVEST71KXJ7J6DRY":56},{"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},"01M792RNQ4BVEST71KXJ7J6DRY","model-catalog",null,"Select PINTO_model_zoo models by task family, model number\u002Fdirectory\u002Fname, format flags, and remarks without reopening source evidence.","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\u002Fpinto-model-zoo\u002Fsub-skills\u002Fmodel-catalog\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-catalog\ndescription: \"Select PINTO_model_zoo models by task family, model\n  number\u002Fdirectory\u002Fname, format flags, and remarks without reopening source\n  evidence.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Model Catalog\n\nUse this sub-skill when the task is to shortlist a model from the bundled catalog, interpret format flags, or map a loose request like `ONNX hand pose` or `132_YOLOX` to a concrete folder.\n\n## Fast route\n\n1. Check the license gate first: do not recommend a model for use, redistribution, or execution until the target folder's license terms are acceptable.\n2. Query the bundled helper for a short list:\n\n   ```bash\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --category \"2D\u002F3D Hand Detection\" --format ONNX\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --format OV --contains pose\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --number 132\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --directory 132_YOLOX\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --list-formats\n   ```\n\n3. Read [references\u002Fcatalog-selection.md](references\u002Fcatalog-selection.md) for category, flag, directory, name, and remark semantics.\n4. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when a filter returns no match, a folder number is ambiguous, a backend flag does not fit the target runtime, or the remarks imply a resolution\u002Finput constraint.\n5. Hand off to `..\u002Fmodel-acquisition\u002F` for downloads and artifact handling, `..\u002Finference-demos\u002F` for running an existing model, or `..\u002Fconversion-and-deployment\u002F` for format conversion, quantization, or deployment planning.\n\n## Boundary with sibling sub-skills\n\n- Need to find or rank candidates only -> stay here.\n- Need download scripts, artifact acquisition, or cookie\u002Fnetwork planning -> `..\u002Fmodel-acquisition\u002F`.\n- Need to run an existing demo\u002Ftest script or interpret runtime output -> `..\u002Finference-demos\u002F`.\n- Need to convert, quantize, export, or deploy a model artifact -> `..\u002Fconversion-and-deployment\u002F`.\n\n## What stays here\n\n- catalog lookup and shortlist generation\n- format legend interpretation\n- no-network model selection\n- resolution\u002Fshape hint reading from remarks\n- number\u002Fdirectory\u002Fname mapping\n\n## Bundled files\n\n- [references\u002Fmodel-catalog.json](..\u002F..\u002Freferences\u002Fmodel-catalog.json) — the self-contained catalog data.\n- [references\u002Fcatalog-selection.md](references\u002Fcatalog-selection.md) — selection rules, filter examples, and flag meanings.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) — common failure modes and recovery steps.\n- [..\u002F..\u002Fscripts\u002Fquery_model_catalog.py](..\u002F..\u002Fscripts\u002Fquery_model_catalog.py) — offline query helper for the bundled catalog.\n","# Model Catalog\n\nUse this sub-skill when the task is to shortlist a model from the bundled catalog, interpret format flags, or map a loose request like `ONNX hand pose` or `132_YOLOX` to a concrete folder.\n\n## Fast route\n\n1. Check the license gate first: do not recommend a model for use, redistribution, or execution until the target folder's license terms are acceptable.\n2. Query the bundled helper for a short list:\n\n   ```bash\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --category \"2D\u002F3D Hand Detection\" --format ONNX\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --format OV --contains pose\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --number 132\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --directory 132_YOLOX\n   python ..\u002F..\u002Fscripts\u002Fquery_model_catalog.py --list-formats\n   ```\n\n3. Read [references\u002Fcatalog-selection.md](references\u002Fcatalog-selection.md) for category, flag, directory, name, and remark semantics.\n4. Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when a filter returns no match, a folder number is ambiguous, a backend flag does not fit the target runtime, or the remarks imply a resolution\u002Finput constraint.\n5. Hand off to `..\u002Fmodel-acquisition\u002F` for downloads and artifact handling, `..\u002Finference-demos\u002F` for running an existing model, or `..\u002Fconversion-and-deployment\u002F` for format conversion, quantization, or deployment planning.\n\n## Boundary with sibling sub-skills\n\n- Need to find or rank candidates only -> stay here.\n- Need download scripts, artifact acquisition, or cookie\u002Fnetwork planning -> `..\u002Fmodel-acquisition\u002F`.\n- Need to run an existing demo\u002Ftest script or interpret runtime output -> `..\u002Finference-demos\u002F`.\n- Need to convert, quantize, export, or deploy a model artifact -> `..\u002Fconversion-and-deployment\u002F`.\n\n## What stays here\n\n- catalog lookup and shortlist generation\n- format legend interpretation\n- no-network model selection\n- resolution\u002Fshape hint reading from remarks\n- number\u002Fdirectory\u002Fname mapping\n\n## Bundled files\n\n- [references\u002Fmodel-catalog.json](..\u002F..\u002Freferences\u002Fmodel-catalog.json) — the self-contained catalog data.\n- [references\u002Fcatalog-selection.md](references\u002Fcatalog-selection.md) — selection rules, filter examples, and flag meanings.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) — common failure modes and recovery steps.\n- [..\u002F..\u002Fscripts\u002Fquery_model_catalog.py](..\u002F..\u002Fscripts\u002Fquery_model_catalog.py) — offline query helper for the bundled catalog.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fmodel-catalog",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 model-catalog",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-catalog",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-catalog","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fmodel-catalog\u002FSKILL.md",[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcatalog-selection.md","REFERENCE","参考文档",3932,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fmodel-catalog\u002Freferences\u002Fcatalog-selection.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",2545,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fmodel-catalog\u002Freferences\u002Ftroubleshooting.md",[57,65,72,79,86,93],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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",[],[]]