[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YPCEVHZ6EYTCMENJCNAVA":3,"skill-same:01M78YPCEVHZ6EYTCMENJCNAVA":75},{"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},"01M78YPCEVHZ6EYTCMENJCNAVA","keras-tuner",null,"Routes KerasTuner workflows for defining hyperparameter spaces, running search algorithms, tuning image and scikit-learn models, and coordinating distributed chief\u002Fworker search state.","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\u002Fkeras-tuner\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: keras-tuner\ndescription: \"Routes KerasTuner workflows for defining hyperparameter spaces,\n  running search algorithms, tuning image and scikit-learn models, and\n  coordinating distributed chief\u002Fworker search state.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# KerasTuner\n\nUse this skill when the task mentions `keras_tuner`, `KerasTuner`, `HyperParameters`, `HyperModel`, `Oracle`, `Tuner`, `RandomSearch`, `GridSearch`, `Hyperband`, `BayesianOptimization`, `SklearnTuner`, `HyperResNet`, `HyperXception`, `HyperEfficientNet`, `HyperImageAugment`, or distributed `KERASTUNER_*` search state.\n\n## What this skill covers\n\n- Defining search spaces with `HyperParameters` and `HyperModel`.\n- Running the built-in search algorithms and reading back best trials.\n- Tuning scikit-learn estimators with `SklearnTuner`.\n- Using the built-in image hypermodels and augmentation search helpers.\n- Debugging distributed chief\u002Fworker oracle coordination.\n\n## Install and quick check\n\nFor a normal CPU-backed KerasTuner install:\n\n```bash\npython -m pip install \"keras-tuner[tensorflow-cpu]\" tensorboard\n```\n\nFor Bayesian optimization or scikit-learn tuning, add the optional backend package set:\n\n```bash\npython -m pip install \"keras-tuner[tensorflow-cpu,bayesian]\" tensorboard\n```\n\nIf you are using a GPU TensorFlow environment, swap `tensorflow-cpu` for `tensorflow`.\n\nFor editable development from a source checkout, run this from the checkout\nroot that contains `setup.py`; the generated skill directory is documentation\nand is not itself an installable checkout:\n\n```bash\npython -m pip install -e \".[tensorflow-cpu,bayesian]\" tensorboard\n```\n\nMinimal check:\n\n```bash\npython -c \"import keras_tuner; from keras_tuner.backend import config; print(keras_tuner.__version__, config.backend())\"\n```\n\nRun `scripts\u002Fcheck_env.py` when you want a slightly richer import and backend sanity check.\n\n## Route map\n\n- Read `sub-skills\u002Ftuning\u002FSKILL.md` for generic hyperparameter search, custom `HyperModel` classes, `Oracle`\u002F`Tuner` subclassing, trial inspection, and reload\u002Fresume workflows.\n- Read `sub-skills\u002Fimage-hypermodels\u002FSKILL.md` for `HyperResNet`, `HyperXception`, `HyperEfficientNet`, and `HyperImageAugment`.\n- Read `sub-skills\u002Fsklearn-tuning\u002FSKILL.md` for `SklearnTuner`, estimator factories, cross-validation, sample weights, and pickle-backed model saving.\n- Read `sub-skills\u002Fdistributed-tuning\u002FSKILL.md` for `KERASTUNER_ORACLE_IP`, `KERASTUNER_ORACLE_PORT`, `KERASTUNER_TUNER_ID`, and local chief\u002Fworker coordination.\n\n## What to read next\n\n- `references\u002Fapi-reference.md` for verified signatures and class responsibilities.\n- `references\u002Fworkflows.md` for end-to-end tuning patterns.\n- `references\u002Ftroubleshooting.md` for install\u002Fimport, optional dependency, and search failures.\n- `references\u002Frepo-provenance.md` before deciding whether this skill matches the current checkout.\n\n## Operational notes\n\n- This package is Python-first; there is no separate CLI to route here.\n- Use `keras_tuner.backend.config.backend()` to check the active backend, not `keras_tuner.backend.backend`.\n- Bayesian optimization and scikit-learn tuning need the optional `bayesian` dependency set.\n- In this 1.4.8 TensorFlow path, Keras model trials also import TensorBoard's HParams API; install `tensorboard` even when you do not pass a TensorBoard callback.\n- The built-in image models may be slow to build; `HyperEfficientNet` can also trigger a first-run Keras Applications weight download.\n- Distributed tuning needs the chief\u002Fworker environment variables to be set together.\nUnless a command says otherwise, run the shell snippets from this skill's root directory (the directory containing this `SKILL.md`); from another cwd, use the corresponding absolute path.\n\n## Fast path\n\nIf you only need to confirm the install, backend, and public exports, run:\n\n```bash\npython scripts\u002Fcheck_env.py\n```\n\nIf you need a workflow-specific smoke check, run the helper from the skill\nroot, using its full bundle-relative path, such as\n`python sub-skills\u002Ftuning\u002Fscripts\u002Fsmoke_search.py`.\n","# KerasTuner\n\nUse this skill when the task mentions `keras_tuner`, `KerasTuner`, `HyperParameters`, `HyperModel`, `Oracle`, `Tuner`, `RandomSearch`, `GridSearch`, `Hyperband`, `BayesianOptimization`, `SklearnTuner`, `HyperResNet`, `HyperXception`, `HyperEfficientNet`, `HyperImageAugment`, or distributed `KERASTUNER_*` search state.\n\n## What this skill covers\n\n- Defining search spaces with `HyperParameters` and `HyperModel`.\n- Running the built-in search algorithms and reading back best trials.\n- Tuning scikit-learn estimators with `SklearnTuner`.\n- Using the built-in image hypermodels and augmentation search helpers.\n- Debugging distributed chief\u002Fworker oracle coordination.\n\n## Install and quick check\n\nFor a normal CPU-backed KerasTuner install:\n\n```bash\npython -m pip install \"keras-tuner[tensorflow-cpu]\" tensorboard\n```\n\nFor Bayesian optimization or scikit-learn tuning, add the optional backend package set:\n\n```bash\npython -m pip install \"keras-tuner[tensorflow-cpu,bayesian]\" tensorboard\n```\n\nIf you are using a GPU TensorFlow environment, swap `tensorflow-cpu` for `tensorflow`.\n\nFor editable development from a source checkout, run this from the checkout\nroot that contains `setup.py`; the generated skill directory is documentation\nand is not itself an installable checkout:\n\n```bash\npython -m pip install -e \".[tensorflow-cpu,bayesian]\" tensorboard\n```\n\nMinimal check:\n\n```bash\npython -c \"import keras_tuner; from keras_tuner.backend import config; print(keras_tuner.__version__, config.backend())\"\n```\n\nRun `scripts\u002Fcheck_env.py` when you want a slightly richer import and backend sanity check.\n\n## Route map\n\n- Read `sub-skills\u002Ftuning\u002FSKILL.md` for generic hyperparameter search, custom `HyperModel` classes, `Oracle`\u002F`Tuner` subclassing, trial inspection, and reload\u002Fresume workflows.\n- Read `sub-skills\u002Fimage-hypermodels\u002FSKILL.md` for `HyperResNet`, `HyperXception`, `HyperEfficientNet`, and `HyperImageAugment`.\n- Read `sub-skills\u002Fsklearn-tuning\u002FSKILL.md` for `SklearnTuner`, estimator factories, cross-validation, sample weights, and pickle-backed model saving.\n- Read `sub-skills\u002Fdistributed-tuning\u002FSKILL.md` for `KERASTUNER_ORACLE_IP`, `KERASTUNER_ORACLE_PORT`, `KERASTUNER_TUNER_ID`, and local chief\u002Fworker coordination.\n\n## What to read next\n\n- `references\u002Fapi-reference.md` for verified signatures and class responsibilities.\n- `references\u002Fworkflows.md` for end-to-end tuning patterns.\n- `references\u002Ftroubleshooting.md` for install\u002Fimport, optional dependency, and search failures.\n- `references\u002Frepo-provenance.md` before deciding whether this skill matches the current checkout.\n\n## Operational notes\n\n- This package is Python-first; there is no separate CLI to route here.\n- Use `keras_tuner.backend.config.backend()` to check the active backend, not `keras_tuner.backend.backend`.\n- Bayesian optimization and scikit-learn tuning need the optional `bayesian` dependency set.\n- In this 1.4.8 TensorFlow path, Keras model trials also import TensorBoard's HParams API; install `tensorboard` even when you do not pass a TensorBoard callback.\n- The built-in image models may be slow to build; `HyperEfficientNet` can also trigger a first-run Keras Applications weight download.\n- Distributed tuning needs the chief\u002Fworker environment variables to be set together.\nUnless a command says otherwise, run the shell snippets from this skill's root directory (the directory containing this `SKILL.md`); from another cwd, use the corresponding absolute path.\n\n## Fast path\n\nIf you only need to confirm the install, backend, and public exports, run:\n\n```bash\npython scripts\u002Fcheck_env.py\n```\n\nIf you need a workflow-specific smoke check, run the helper from the skill\nroot, using its full bundle-relative path, such as\n`python sub-skills\u002Ftuning\u002Fscripts\u002Fsmoke_search.py`.\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\u002Fkeras-tuner",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 keras-tuner",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill keras-tuner",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill keras-tuner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-tuner\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",6809,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-tuner\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",1861,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-tuner\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",305,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-tuner\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",4436,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-tuner\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fworkflows.md",3703,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-tuner\u002Freferences\u002Fworkflows.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fcheck_env.py","SCRIPT","脚本",2704,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fkeras-tuner\u002Fscripts\u002Fcheck_env.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]