[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78T7CF7KMSMHA71KDTSFWYZ":3,"skill-same:01M78T7CF7KMSMHA71KDTSFWYZ":71},{"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},"01M78T7CF7KMSMHA71KDTSFWYZ","model-management",null,"Manage BentoML model stores, model references, framework save\u002Fload helpers, optional dependencies, and model troubleshooting for services and builds.","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\u002Fbentoml\u002Fsub-skills\u002Fmodel-management\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-management\ndescription: \"Manage BentoML model stores, model references, framework save\u002Fload\n  helpers, optional dependencies, and model troubleshooting for services and\n  builds.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# BentoML Model Management\n\nUse this sub-skill when an agent needs to save, inspect, package, load, import\u002Fexport, or diagnose BentoML models. Keep service endpoint design in `..\u002Fservice-authoring\u002FSKILL.md`; keep Bento build\u002Fcontainer packaging mechanics in `..\u002Fpackaging-and-containerization\u002FSKILL.md`; keep BentoCloud deployment in `..\u002Fcli-and-cloud\u002FSKILL.md`.\n\n## First Decision\n\n1. **Need a model dependency in a Service or Bento build?** Declare `BentoModel(\"name:version\")`, `BentoModel(\"name:latest\")`, or `HuggingFaceModel(\"org\u002Fmodel\")` as a Service class variable so BentoML can include\u002Fresolve it during build and deployment.\n2. **Need to put files into BentoML's local store?** Use `bentoml.models.create(name)` as a context manager for arbitrary model directories, or a framework helper such as `bentoml.sklearn.save_model()` when that framework helper is appropriate and installed.\n3. **Need to inspect or move a stored model?** Use `bentoml models list\u002Fget\u002Fexport\u002Fimport\u002Fdelete` or the Python equivalents under `bentoml.models`.\n4. **Need to load framework-native objects?** Prefer the matching helper (`bentoml.sklearn.load_model`, `bentoml.pytorch.load_model`, etc.) only when the stored model's `module` matches that helper and its optional dependencies are present.\n\n## Model Store Essentials\n\n- BentoML stores models by tag (`name:version`) and supports `:latest` resolution. `bentoml.models.get(tag)` returns a `bentoml.Model`; `bentoml.models.list(name_or_none)` returns stored model objects.\n- `bentoml.models.create(name)` yields a model reference with `path` and `path_of(...)`; write or copy model files inside that directory, then let the context manager flush and save on successful exit.\n- Model metadata includes the saved module, labels, options, metadata, context, signatures, BentoML version, Python version, and creation time. Use it to diagnose helper mismatch and serialization\u002Fversion mismatch.\n- Import\u002Fexport moves BentoML model archives or folders between stores. Use framework save\u002Fimport APIs for raw framework artifacts; `bentoml.models.import_model()` expects an exported BentoML model archive or folder.\n- Store location is controlled by the installed BentoML configuration and environment. If a model appears missing, inspect the active process environment and `bentoml models list --output json` before assuming the tag is wrong.\n\n## Service Loading Pattern\n\nDeclare model dependencies at Service class scope, then load the framework object in `__init__` or a method:\n\n```python\nimport bentoml\nfrom bentoml.models import BentoModel\n\n@bentoml.service\nclass IrisService:\n    model_ref = BentoModel(\"iris_sklearn:latest\")\n\n    def __init__(self):\n        import joblib\n        self.model = joblib.load(self.model_ref.path_of(\"model.pkl\"))\n```\n\nClass-scope declaration is important: BentoML records the model dependency for build, push, and deployment. Creating `BentoModel(...)` only inside `__init__` can produce a Bento that starts without the referenced model and later fails with a model not found error.\n\nFor Hugging Face Hub models, use `HuggingFaceModel(\"org\u002Fmodel\")` as a class variable and pass the resolved path to `transformers` loaders in `__init__`. Private or gated Hub models require the appropriate token in the runtime\u002Fbuild environment; do not bake secrets into skill content or service source.\n\n## Commands And APIs\n\n- List models: `bentoml models list` or `bentoml.models.list()`.\n- Inspect a model: `bentoml models get MODEL_TAG`, `bentoml models get MODEL_TAG --output json`, `bentoml models get MODEL_TAG --output path`, or `bentoml.models.get(\"MODEL_TAG\")`.\n- Export\u002Fimport: `bentoml models export MODEL_TAG OUT_PATH`, `bentoml models import MODEL_PATH`, `bentoml.models.export_model(tag, path)`, and `bentoml.models.import_model(path)`.\n- Delete: `bentoml models delete MODEL_TAG --yes` or `bentoml.models.delete(tag)`. Deletion can fail if a local Bento references the model.\n- Cloud transfer: `bentoml models push MODEL_TAG` and `bentoml models pull MODEL_TAG` require BentoCloud auth; keep deployment\u002Fcloud workflow in `..\u002Fcli-and-cloud\u002FSKILL.md`.\n\n## Bundled Helpers\n\n- `scripts\u002Finspect_model_store.py` lists model tags, modules, locations, metadata keys, context, and optional tag details. It is read-only.\n- `scripts\u002Fcheck_framework_extra.py` checks whether a framework helper's Python modules are importable and warns about deprecated helper-module usage. It does not install packages or download models.\n\n## References\n\n- Model store operations: `references\u002Fmodel-store.md`.\n- Framework helpers and optional dependencies: `references\u002Fframeworks.md`.\n- Troubleshooting: `references\u002Ftroubleshooting.md`.\n","# BentoML Model Management\n\nUse this sub-skill when an agent needs to save, inspect, package, load, import\u002Fexport, or diagnose BentoML models. Keep service endpoint design in `..\u002Fservice-authoring\u002FSKILL.md`; keep Bento build\u002Fcontainer packaging mechanics in `..\u002Fpackaging-and-containerization\u002FSKILL.md`; keep BentoCloud deployment in `..\u002Fcli-and-cloud\u002FSKILL.md`.\n\n## First Decision\n\n1. **Need a model dependency in a Service or Bento build?** Declare `BentoModel(\"name:version\")`, `BentoModel(\"name:latest\")`, or `HuggingFaceModel(\"org\u002Fmodel\")` as a Service class variable so BentoML can include\u002Fresolve it during build and deployment.\n2. **Need to put files into BentoML's local store?** Use `bentoml.models.create(name)` as a context manager for arbitrary model directories, or a framework helper such as `bentoml.sklearn.save_model()` when that framework helper is appropriate and installed.\n3. **Need to inspect or move a stored model?** Use `bentoml models list\u002Fget\u002Fexport\u002Fimport\u002Fdelete` or the Python equivalents under `bentoml.models`.\n4. **Need to load framework-native objects?** Prefer the matching helper (`bentoml.sklearn.load_model`, `bentoml.pytorch.load_model`, etc.) only when the stored model's `module` matches that helper and its optional dependencies are present.\n\n## Model Store Essentials\n\n- BentoML stores models by tag (`name:version`) and supports `:latest` resolution. `bentoml.models.get(tag)` returns a `bentoml.Model`; `bentoml.models.list(name_or_none)` returns stored model objects.\n- `bentoml.models.create(name)` yields a model reference with `path` and `path_of(...)`; write or copy model files inside that directory, then let the context manager flush and save on successful exit.\n- Model metadata includes the saved module, labels, options, metadata, context, signatures, BentoML version, Python version, and creation time. Use it to diagnose helper mismatch and serialization\u002Fversion mismatch.\n- Import\u002Fexport moves BentoML model archives or folders between stores. Use framework save\u002Fimport APIs for raw framework artifacts; `bentoml.models.import_model()` expects an exported BentoML model archive or folder.\n- Store location is controlled by the installed BentoML configuration and environment. If a model appears missing, inspect the active process environment and `bentoml models list --output json` before assuming the tag is wrong.\n\n## Service Loading Pattern\n\nDeclare model dependencies at Service class scope, then load the framework object in `__init__` or a method:\n\n```python\nimport bentoml\nfrom bentoml.models import BentoModel\n\n@bentoml.service\nclass IrisService:\n    model_ref = BentoModel(\"iris_sklearn:latest\")\n\n    def __init__(self):\n        import joblib\n        self.model = joblib.load(self.model_ref.path_of(\"model.pkl\"))\n```\n\nClass-scope declaration is important: BentoML records the model dependency for build, push, and deployment. Creating `BentoModel(...)` only inside `__init__` can produce a Bento that starts without the referenced model and later fails with a model not found error.\n\nFor Hugging Face Hub models, use `HuggingFaceModel(\"org\u002Fmodel\")` as a class variable and pass the resolved path to `transformers` loaders in `__init__`. Private or gated Hub models require the appropriate token in the runtime\u002Fbuild environment; do not bake secrets into skill content or service source.\n\n## Commands And APIs\n\n- List models: `bentoml models list` or `bentoml.models.list()`.\n- Inspect a model: `bentoml models get MODEL_TAG`, `bentoml models get MODEL_TAG --output json`, `bentoml models get MODEL_TAG --output path`, or `bentoml.models.get(\"MODEL_TAG\")`.\n- Export\u002Fimport: `bentoml models export MODEL_TAG OUT_PATH`, `bentoml models import MODEL_PATH`, `bentoml.models.export_model(tag, path)`, and `bentoml.models.import_model(path)`.\n- Delete: `bentoml models delete MODEL_TAG --yes` or `bentoml.models.delete(tag)`. Deletion can fail if a local Bento references the model.\n- Cloud transfer: `bentoml models push MODEL_TAG` and `bentoml models pull MODEL_TAG` require BentoCloud auth; keep deployment\u002Fcloud workflow in `..\u002Fcli-and-cloud\u002FSKILL.md`.\n\n## Bundled Helpers\n\n- `scripts\u002Finspect_model_store.py` lists model tags, modules, locations, metadata keys, context, and optional tag details. It is read-only.\n- `scripts\u002Fcheck_framework_extra.py` checks whether a framework helper's Python modules are importable and warns about deprecated helper-module usage. It does not install packages or download models.\n\n## References\n\n- Model store operations: `references\u002Fmodel-store.md`.\n- Framework helpers and optional dependencies: `references\u002Fframeworks.md`.\n- Troubleshooting: `references\u002Ftroubleshooting.md`.\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\u002Fbentoml\u002Fsub-skills\u002Fmodel-management",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-management",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill model-management",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill model-management","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbentoml\u002Fsub-skills\u002Fmodel-management\u002FSKILL.md",[47,53,57,61,67],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fframeworks.md","REFERENCE","参考文档",6325,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbentoml\u002Fsub-skills\u002Fmodel-management\u002Freferences\u002Fframeworks.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmodel-store.md",4393,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbentoml\u002Fsub-skills\u002Fmodel-management\u002Freferences\u002Fmodel-store.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",5028,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbentoml\u002Fsub-skills\u002Fmodel-management\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fcheck_framework_extra.py","SCRIPT","脚本",5438,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbentoml\u002Fsub-skills\u002Fmodel-management\u002Fscripts\u002Fcheck_framework_extra.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_model_store.py",4396,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbentoml\u002Fsub-skills\u002Fmodel-management\u002Fscripts\u002Finspect_model_store.py",[72,79,86,93,100,107],{"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":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]