[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791BZF0WMSSEM055KDF384S":3,"skill-same:01M791BZF0WMSSEM055KDF384S":66},{"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},"01M791BZF0WMSSEM055KDF384S","nas",null,"Use NNI neural architecture search with model spaces, mutables, evaluators, strategies, execution engines, fixed-architecture export, and optional backend troubleshooting.","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\u002Fnni\u002Fsub-skills\u002Fnas\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nas\ndescription: \"Use NNI neural architecture search with model spaces, mutables,\n  evaluators, strategies, execution engines, fixed-architecture export, and\n  optional backend troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# NNI NAS\n\nUse this sub-skill when the task is about NNI Neural Architecture Search: defining a model space, choosing mutation primitives, selecting an evaluator and strategy, launching a `NasExperiment`, exporting a fixed architecture, or diagnosing NAS import\u002Fruntime dependency failures.\n\n## Route Here\n\n- The user asks to build or adapt an NNI NAS `ModelSpace`, including DARTS-style cells, `LayerChoice`, `InputChoice`, `Repeat`, `Cell`, `nni.choice`, or mutable `torch.nn` modules.\n- The user asks whether to use one-shot NAS or multi-trial NAS, or asks about `Random`, `GridSearch`, `RegularizedEvolution`, `TPE`, `PolicyBasedRL`, `DARTS`, `ENAS`, `GumbelDARTS`, `RandomOneShot`, or `Proxyless`.\n- The user asks for evaluator selection, `FunctionalEvaluator`, PyTorch Lightning evaluators, `Classification`, `Regression`, `Lightning`, `LightningModule`, or serialization with `nni.trace`.\n- The user asks how to export, freeze, retrain, or instantiate the best architecture after a NAS search using `export_top_models`, `model_context`, or `freeze`.\n- The user hits `torch`, `pytorch_lightning`, `nni.nas.nn.pytorch`, `nni.nas.evaluator`, or `nni.nas.strategy` import errors while doing NAS work.\n\n## Reroute\n\n- Generic HPO experiment lifecycle, `nnictl`, search spaces for tuners, experiment YAML, training services, and trial-code wiring: use `..\u002Fhpo-experiments\u002F`.\n- Pruning, quantization, `config_list`, `pruner`, `quantizer`, speedup, or compression evaluators: use `..\u002Fmodel-compression\u002F`.\n- Standalone tracing, serialization utilities, concrete trace inspection, or feature utility usage without a NAS goal: use `..\u002Ffeature-engineering-and-utilities\u002F`.\n\n## Start With These References\n\n- `references\u002Fworkflows.md` for model-space, evaluator, strategy, experiment, and fixed-architecture workflows.\n- `references\u002Fapi-reference.md` for key public NAS concepts and object names, including optional dependency boundaries.\n- `references\u002Ftroubleshooting.md` for backend imports, evaluator mismatch, benchmark data, GPU\u002Ftraining cost, and model-space mutation errors.\n- `scripts\u002Fcheck_nas_optional_deps.py` to safely inspect local optional dependency\u002Fimport readiness without running NAS examples.\n\n## Default Approach\n\n1. Confirm the task is NAS, not generic HPO or compression.\n2. Separate the NAS design into model space, evaluator, strategy, execution configuration, and export\u002Fretrain plan.\n3. Prefer minimal, conceptual scaffolds unless the user explicitly asks to run a search; NAS execution can be expensive and often requires `torch`, datasets, Lightning, GPUs, and long training time.\n4. Warn when a chosen strategy requires optional dependencies that may not be installed; do not imply `torch` or `pytorch_lightning` are present by default.\n5. For fixed-architecture handoff, export an architecture dict and show how to instantiate or freeze the final model from that dict.\n","# NNI NAS\n\nUse this sub-skill when the task is about NNI Neural Architecture Search: defining a model space, choosing mutation primitives, selecting an evaluator and strategy, launching a `NasExperiment`, exporting a fixed architecture, or diagnosing NAS import\u002Fruntime dependency failures.\n\n## Route Here\n\n- The user asks to build or adapt an NNI NAS `ModelSpace`, including DARTS-style cells, `LayerChoice`, `InputChoice`, `Repeat`, `Cell`, `nni.choice`, or mutable `torch.nn` modules.\n- The user asks whether to use one-shot NAS or multi-trial NAS, or asks about `Random`, `GridSearch`, `RegularizedEvolution`, `TPE`, `PolicyBasedRL`, `DARTS`, `ENAS`, `GumbelDARTS`, `RandomOneShot`, or `Proxyless`.\n- The user asks for evaluator selection, `FunctionalEvaluator`, PyTorch Lightning evaluators, `Classification`, `Regression`, `Lightning`, `LightningModule`, or serialization with `nni.trace`.\n- The user asks how to export, freeze, retrain, or instantiate the best architecture after a NAS search using `export_top_models`, `model_context`, or `freeze`.\n- The user hits `torch`, `pytorch_lightning`, `nni.nas.nn.pytorch`, `nni.nas.evaluator`, or `nni.nas.strategy` import errors while doing NAS work.\n\n## Reroute\n\n- Generic HPO experiment lifecycle, `nnictl`, search spaces for tuners, experiment YAML, training services, and trial-code wiring: use `..\u002Fhpo-experiments\u002F`.\n- Pruning, quantization, `config_list`, `pruner`, `quantizer`, speedup, or compression evaluators: use `..\u002Fmodel-compression\u002F`.\n- Standalone tracing, serialization utilities, concrete trace inspection, or feature utility usage without a NAS goal: use `..\u002Ffeature-engineering-and-utilities\u002F`.\n\n## Start With These References\n\n- `references\u002Fworkflows.md` for model-space, evaluator, strategy, experiment, and fixed-architecture workflows.\n- `references\u002Fapi-reference.md` for key public NAS concepts and object names, including optional dependency boundaries.\n- `references\u002Ftroubleshooting.md` for backend imports, evaluator mismatch, benchmark data, GPU\u002Ftraining cost, and model-space mutation errors.\n- `scripts\u002Fcheck_nas_optional_deps.py` to safely inspect local optional dependency\u002Fimport readiness without running NAS examples.\n\n## Default Approach\n\n1. Confirm the task is NAS, not generic HPO or compression.\n2. Separate the NAS design into model space, evaluator, strategy, execution configuration, and export\u002Fretrain plan.\n3. Prefer minimal, conceptual scaffolds unless the user explicitly asks to run a search; NAS execution can be expensive and often requires `torch`, datasets, Lightning, GPUs, and long training time.\n4. Warn when a chosen strategy requires optional dependencies that may not be installed; do not imply `torch` or `pytorch_lightning` are present by default.\n5. For fixed-architecture handoff, export an architecture dict and show how to instantiate or freeze the final model from that dict.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fnni\u002Fsub-skills\u002Fnas",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 nas",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill nas",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill nas","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnni\u002Fsub-skills\u002Fnas\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",10229,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnni\u002Fsub-skills\u002Fnas\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",7847,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnni\u002Fsub-skills\u002Fnas\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",8838,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnni\u002Fsub-skills\u002Fnas\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fcheck_nas_optional_deps.py","SCRIPT","脚本",7151,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fnni\u002Fsub-skills\u002Fnas\u002Fscripts\u002Fcheck_nas_optional_deps.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]