[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791HT6YYDRRESBSHSB6PB7W":3,"skill-same:01M791HT6YYDRRESBSHSB6PB7W":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},"01M791HT6YYDRRESBSHSB6PB7W","hardware-and-models",null,"Operate on ODS GPU\u002Fbackend detection, hardware tiers, model catalogs, inference overlays, and model lifecycle safely.","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\u002Fods\u002Fsub-skills\u002Fhardware-and-models\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: hardware-and-models\ndescription: \"Operate on ODS GPU\u002Fbackend detection, hardware tiers, model\n  catalogs, inference overlays, and model lifecycle safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# ODS hardware and models sub-skill\n\nUse this sub-skill when an ODS task touches GPU\u002Fbackend detection, hardware class or tier mapping, backend contracts, model catalog\u002Fprofile selection, inference backend compose overlays, model download\u002Fload\u002Fswap behavior, bootstrap-to-full model upgrades, or model-state lifecycle.\n\nDo not use this sub-skill for dashboard model UI implementation details; route those to `dashboard-and-api`. Do not use it for end-user `ods model` command syntax or host-agent command dispatch; route those to `ops-cli-and-host-tools`. For broad release lane selection, route to `testing-and-release` after identifying the owning hardware\u002Fmodel files.\n\n## Operating workflow\n\n1. For backend, detection, tier, compose overlay, and exact file\u002Ftest ownership, read [`references\u002Fbackend-and-tier-reference.md`](references\u002Fbackend-and-tier-reference.md).\n2. For model catalog selection, downloads, bootstrap\u002Ffull swaps, model-state, and lifecycle workflows, read [`references\u002Fmodel-management-workflows.md`](references\u002Fmodel-management-workflows.md).\n3. For symptoms and repair decisions, read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md).\n4. To inspect a local ODS source tree without mutation, run:\n\n   ```bash\n   python3 scripts\u002Finspect_model_catalog.py --root \u003CODS_SOURCE_OR_PROJECT_ROOT>\n   ```\n\n   The helper is read-only. It summarizes `config\u002Fmodel-library.json`, `config\u002Fbackends\u002F*.json`, and hardware class data if those files are present.\n\n## Safety and evidence rules\n\n- Separate product capability claims from current verification. Source evidence documents ODS support for NVIDIA\u002FCUDA, AMD\u002FLemonade\u002FROCm\u002FVulkan, Intel Arc\u002FSYCL, Apple Metal\u002Fnative llama-server, CPU fallback, and cloud\u002FAPI modes, but a future agent may claim live GPU validation only after running the matching host-specific checks.\n- Repo-skill verification for this sub-skill can use safe CPU\u002Fhost static checks. GPU smoke tests, model downloads, installers, Docker lifecycle, and backend health probes are product validations that require explicit user intent and suitable hardware.\n- Treat tier\u002Fmodel throughput estimates as catalog or source estimates until measured on the user's host.\n- Prefer read-only inspection and focused native tests before any installer, download, compose, or model activation action.\n\n## Common change routing\n\n- Hardware classification or backend default: inspect\u002Fupdate detection, classifier, hardware class, backend contract, and compose selection facts; validate with the exact tests listed in the backend\u002Ftier reference.\n- Tier-to-model or profile change: inspect\u002Fupdate Linux, macOS, and Windows tier maps plus catalog selector\u002Fcatalog coherence; validate with tier-map parity, catalog, integrity, and Windows contracts.\n- Model lifecycle or swap behavior: inspect model management workflow facts, model-state\u002Fswitchboard contracts, bootstrap-upgrade behavior, and runtime adapter expectations; validate with focused model lifecycle and runtime tunable tests.\n- Compose overlay for an inference backend: inspect overlay layering and llama.cpp\u002FLemonade command parity; validate overlay coherence and runtime tunable preservation.\n\n## Source provenance\n\nThis runtime skill distills evidence from relative ODS source paths such as `ods\u002Finstallers\u002Flib\u002Fdetection.sh`, `ods\u002Finstallers\u002Flib\u002Ftier-map.sh`, `ods\u002Finstallers\u002Fmacos\u002Flib\u002Ftier-map.sh`, `ods\u002Finstallers\u002Fwindows\u002Flib\u002Ftier-map.ps1`, `ods\u002Fconfig\u002Fbackends\u002F`, `ods\u002Fconfig\u002Fmodel-library.json`, `ods\u002Fconfig\u002Fhardware-classes.json`, `ods\u002Fconfig\u002Fgpu-database.json`, `ods\u002Fscripts\u002Fselect-model.py`, `ods\u002Fscripts\u002Fdetect-hardware.sh`, `ods\u002Fscripts\u002Fclassify-hardware.sh`, `ods\u002Fscripts\u002Fload-backend-contract.sh`, `ods\u002Fbin\u002Fmodel_switchboard\u002F`, compose overlays, and tier\u002Fmodel tests. Future usage should rely on this bundled guidance, the bundled read-only helper, and public ODS commands\u002Ftests rather than links to private inspection artifacts.\n","# ODS hardware and models sub-skill\n\nUse this sub-skill when an ODS task touches GPU\u002Fbackend detection, hardware class or tier mapping, backend contracts, model catalog\u002Fprofile selection, inference backend compose overlays, model download\u002Fload\u002Fswap behavior, bootstrap-to-full model upgrades, or model-state lifecycle.\n\nDo not use this sub-skill for dashboard model UI implementation details; route those to `dashboard-and-api`. Do not use it for end-user `ods model` command syntax or host-agent command dispatch; route those to `ops-cli-and-host-tools`. For broad release lane selection, route to `testing-and-release` after identifying the owning hardware\u002Fmodel files.\n\n## Operating workflow\n\n1. For backend, detection, tier, compose overlay, and exact file\u002Ftest ownership, read [`references\u002Fbackend-and-tier-reference.md`](references\u002Fbackend-and-tier-reference.md).\n2. For model catalog selection, downloads, bootstrap\u002Ffull swaps, model-state, and lifecycle workflows, read [`references\u002Fmodel-management-workflows.md`](references\u002Fmodel-management-workflows.md).\n3. For symptoms and repair decisions, read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md).\n4. To inspect a local ODS source tree without mutation, run:\n\n   ```bash\n   python3 scripts\u002Finspect_model_catalog.py --root \u003CODS_SOURCE_OR_PROJECT_ROOT>\n   ```\n\n   The helper is read-only. It summarizes `config\u002Fmodel-library.json`, `config\u002Fbackends\u002F*.json`, and hardware class data if those files are present.\n\n## Safety and evidence rules\n\n- Separate product capability claims from current verification. Source evidence documents ODS support for NVIDIA\u002FCUDA, AMD\u002FLemonade\u002FROCm\u002FVulkan, Intel Arc\u002FSYCL, Apple Metal\u002Fnative llama-server, CPU fallback, and cloud\u002FAPI modes, but a future agent may claim live GPU validation only after running the matching host-specific checks.\n- Repo-skill verification for this sub-skill can use safe CPU\u002Fhost static checks. GPU smoke tests, model downloads, installers, Docker lifecycle, and backend health probes are product validations that require explicit user intent and suitable hardware.\n- Treat tier\u002Fmodel throughput estimates as catalog or source estimates until measured on the user's host.\n- Prefer read-only inspection and focused native tests before any installer, download, compose, or model activation action.\n\n## Common change routing\n\n- Hardware classification or backend default: inspect\u002Fupdate detection, classifier, hardware class, backend contract, and compose selection facts; validate with the exact tests listed in the backend\u002Ftier reference.\n- Tier-to-model or profile change: inspect\u002Fupdate Linux, macOS, and Windows tier maps plus catalog selector\u002Fcatalog coherence; validate with tier-map parity, catalog, integrity, and Windows contracts.\n- Model lifecycle or swap behavior: inspect model management workflow facts, model-state\u002Fswitchboard contracts, bootstrap-upgrade behavior, and runtime adapter expectations; validate with focused model lifecycle and runtime tunable tests.\n- Compose overlay for an inference backend: inspect overlay layering and llama.cpp\u002FLemonade command parity; validate overlay coherence and runtime tunable preservation.\n\n## Source provenance\n\nThis runtime skill distills evidence from relative ODS source paths such as `ods\u002Finstallers\u002Flib\u002Fdetection.sh`, `ods\u002Finstallers\u002Flib\u002Ftier-map.sh`, `ods\u002Finstallers\u002Fmacos\u002Flib\u002Ftier-map.sh`, `ods\u002Finstallers\u002Fwindows\u002Flib\u002Ftier-map.ps1`, `ods\u002Fconfig\u002Fbackends\u002F`, `ods\u002Fconfig\u002Fmodel-library.json`, `ods\u002Fconfig\u002Fhardware-classes.json`, `ods\u002Fconfig\u002Fgpu-database.json`, `ods\u002Fscripts\u002Fselect-model.py`, `ods\u002Fscripts\u002Fdetect-hardware.sh`, `ods\u002Fscripts\u002Fclassify-hardware.sh`, `ods\u002Fscripts\u002Fload-backend-contract.sh`, `ods\u002Fbin\u002Fmodel_switchboard\u002F`, compose overlays, and tier\u002Fmodel tests. Future usage should rely on this bundled guidance, the bundled read-only helper, and public ODS commands\u002Ftests rather than links to private inspection artifacts.\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\u002Fods\u002Fsub-skills\u002Fhardware-and-models",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 hardware-and-models",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill hardware-and-models",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill hardware-and-models","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fods\u002Fsub-skills\u002Fhardware-and-models\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fbackend-and-tier-reference.md","REFERENCE","参考文档",13685,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fods\u002Fsub-skills\u002Fhardware-and-models\u002Freferences\u002Fbackend-and-tier-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmodel-management-workflows.md",10924,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fods\u002Fsub-skills\u002Fhardware-and-models\u002Freferences\u002Fmodel-management-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",10593,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fods\u002Fsub-skills\u002Fhardware-and-models\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Finspect_model_catalog.py","SCRIPT","脚本",11534,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fods\u002Fsub-skills\u002Fhardware-and-models\u002Fscripts\u002Finspect_model_catalog.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",[],[]]