[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796B706F6RN2MP265Y7NCD2":3,"skill-same:01M796B706F6RN2MP265Y7NCD2":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},"01M796B706F6RN2MP265Y7NCD2","model-library",null,"Discover timm model names, instantiate models, load pretrained or local weights, adapt heads\u002Finput channels\u002Fpooling, inspect pretrained configs, extract features, and debug model registry or weight-loading issues.","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\u002Ftimm\u002Fsub-skills\u002Fmodel-library\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-library\ndescription: \"Discover timm model names, instantiate models, load pretrained or\n  local weights, adapt heads\u002Finput channels\u002Fpooling, inspect pretrained configs,\n  extract features, and debug model registry or weight-loading issues.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Model Library\n\nUse this sub-skill when a task asks an agent to choose or instantiate a timm architecture, enumerate available models or pretrained tags, load weights, adapt classification heads or input channels, inspect model defaults, extract feature maps, or troubleshoot model creation and pretrained loading.\n\n## Fast Path\n\n1. Import from the public package surface: `import timm`, then use `timm.list_models`, `timm.list_pretrained`, `timm.get_pretrained_cfg`, and `timm.create_model`.\n2. Prefer no-download checks while iterating: `timm.create_model(name, pretrained=False)` and run a small random forward pass.\n3. Use `list_models(filter='*resnet*')` for architecture discovery and `list_pretrained(filter='*resnet*')` for exact `architecture.tag` pretrained identifiers.\n4. Create a model with the exact signature from timm 1.0.28.dev0: `create_model(model_name, pretrained=False, pretrained_cfg=None, pretrained_cfg_overlay=None, checkpoint_path=None, cache_dir=None, scriptable=None, exportable=None, no_jit=None, **kwargs)`.\n5. Adapt common dimensions at construction time: `num_classes`, `in_chans`, `global_pool`, `features_only`, `out_indices`, `output_stride`, `scriptable`, `exportable`, and `no_jit`.\n6. Inspect `model.pretrained_cfg` or `timm.get_pretrained_cfg(model_name).to_dict()` before choosing transforms, class counts, input channels, or cache\u002Fdownload behavior.\n\n## Decision Guide\n\n- Need model discovery or exact API signatures: read `references\u002Fapi-reference.md`.\n- Need classifier\u002Finput\u002Fpooling\u002Ffeature-extraction recipes: read `references\u002Fmodel-workflows.md`.\n- Need to diagnose unknown names, tag failures, cache\u002Fauth\u002Fdownload problems, checkpoint mismatches, or feature shape surprises: read `references\u002Ftroubleshooting.md`.\n- Need a safe local smoke test without network access: run `python sub-skills\u002Fmodel-library\u002Fscripts\u002Fmodel_smoke_check.py --model resnet18 --num-classes 7` from the skill root or copy the script into a project.\n\n## Boundary Routing\n\n- Use `..\u002Fdata-pipelines\u002F` for transforms, loaders, `resolve_data_config`, augmentation, and preprocessing pipelines after reading `pretrained_cfg` here.\n- Use `..\u002Ftraining-workflows\u002F` for optimizers, schedulers, losses, training loops, fine-tuning scripts, and distributed training.\n- Use `..\u002Fexport-and-interoperability\u002F` for ONNX, TorchScript export flows, checkpoint conversion tools, Hugging Face push\u002Fpull packaging, and deployment formats.\n- Use `..\u002Flayers-and-components\u002F` for low-level timm layers, blocks, activations, pooling modules, and component internals.\n\n## Guardrails\n\n- Do not set `pretrained=True` in smoke checks unless downloads, cache location, and Hugging Face authentication are expected and acceptable.\n- Do not assume all names returned by `list_models()` have pretrained weights; use `list_pretrained()` or `is_model_pretrained()` when weights matter.\n- Do not hardcode image normalization, crop size, or class count for pretrained models; inspect `pretrained_cfg` and route preprocessing details to `data-pipelines`.\n- Do not assume `features_only=True` returns the same number of feature levels for every model family; inspect `model.feature_info.channels()` and `model.feature_info.reduction()`.\n","# Model Library\n\nUse this sub-skill when a task asks an agent to choose or instantiate a timm architecture, enumerate available models or pretrained tags, load weights, adapt classification heads or input channels, inspect model defaults, extract feature maps, or troubleshoot model creation and pretrained loading.\n\n## Fast Path\n\n1. Import from the public package surface: `import timm`, then use `timm.list_models`, `timm.list_pretrained`, `timm.get_pretrained_cfg`, and `timm.create_model`.\n2. Prefer no-download checks while iterating: `timm.create_model(name, pretrained=False)` and run a small random forward pass.\n3. Use `list_models(filter='*resnet*')` for architecture discovery and `list_pretrained(filter='*resnet*')` for exact `architecture.tag` pretrained identifiers.\n4. Create a model with the exact signature from timm 1.0.28.dev0: `create_model(model_name, pretrained=False, pretrained_cfg=None, pretrained_cfg_overlay=None, checkpoint_path=None, cache_dir=None, scriptable=None, exportable=None, no_jit=None, **kwargs)`.\n5. Adapt common dimensions at construction time: `num_classes`, `in_chans`, `global_pool`, `features_only`, `out_indices`, `output_stride`, `scriptable`, `exportable`, and `no_jit`.\n6. Inspect `model.pretrained_cfg` or `timm.get_pretrained_cfg(model_name).to_dict()` before choosing transforms, class counts, input channels, or cache\u002Fdownload behavior.\n\n## Decision Guide\n\n- Need model discovery or exact API signatures: read `references\u002Fapi-reference.md`.\n- Need classifier\u002Finput\u002Fpooling\u002Ffeature-extraction recipes: read `references\u002Fmodel-workflows.md`.\n- Need to diagnose unknown names, tag failures, cache\u002Fauth\u002Fdownload problems, checkpoint mismatches, or feature shape surprises: read `references\u002Ftroubleshooting.md`.\n- Need a safe local smoke test without network access: run `python sub-skills\u002Fmodel-library\u002Fscripts\u002Fmodel_smoke_check.py --model resnet18 --num-classes 7` from the skill root or copy the script into a project.\n\n## Boundary Routing\n\n- Use `..\u002Fdata-pipelines\u002F` for transforms, loaders, `resolve_data_config`, augmentation, and preprocessing pipelines after reading `pretrained_cfg` here.\n- Use `..\u002Ftraining-workflows\u002F` for optimizers, schedulers, losses, training loops, fine-tuning scripts, and distributed training.\n- Use `..\u002Fexport-and-interoperability\u002F` for ONNX, TorchScript export flows, checkpoint conversion tools, Hugging Face push\u002Fpull packaging, and deployment formats.\n- Use `..\u002Flayers-and-components\u002F` for low-level timm layers, blocks, activations, pooling modules, and component internals.\n\n## Guardrails\n\n- Do not set `pretrained=True` in smoke checks unless downloads, cache location, and Hugging Face authentication are expected and acceptable.\n- Do not assume all names returned by `list_models()` have pretrained weights; use `list_pretrained()` or `is_model_pretrained()` when weights matter.\n- Do not hardcode image normalization, crop size, or class count for pretrained models; inspect `pretrained_cfg` and route preprocessing details to `data-pipelines`.\n- Do not assume `features_only=True` returns the same number of feature levels for every model family; inspect `model.feature_info.channels()` and `model.feature_info.reduction()`.\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\u002Ftimm\u002Fsub-skills\u002Fmodel-library",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 model-library",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-library",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-library","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftimm\u002Fsub-skills\u002Fmodel-library\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",8769,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftimm\u002Fsub-skills\u002Fmodel-library\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmodel-workflows.md",7364,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftimm\u002Fsub-skills\u002Fmodel-library\u002Freferences\u002Fmodel-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",6764,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftimm\u002Fsub-skills\u002Fmodel-library\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fmodel_smoke_check.py","SCRIPT","脚本",2833,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftimm\u002Fsub-skills\u002Fmodel-library\u002Fscripts\u002Fmodel_smoke_check.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",[],[]]