[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78T6594THGP22P2S8049KQ3":3,"skill-same:01M78T6594THGP22P2S8049KQ3":70},{"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},"01M78T6594THGP22P2S8049KQ3","advanced-domain-features",null,"Use BayesianOptimization advanced domain features: constraints, typed parameters, custom parameter classes, TargetSpace conversions, and sequential domain reduction.","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\u002Fbayesian-optimization\u002Fsub-skills\u002Fadvanced-domain-features\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: advanced-domain-features\ndescription: \"Use BayesianOptimization advanced domain features: constraints,\n  typed parameters, custom parameter classes, TargetSpace conversions, and\n  sequential domain reduction.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Advanced Domain Features\n\nUse this sub-skill when a task involves constrained optimization, non-float\nsearch variables, custom parameter encodings, low-level `TargetSpace`\nconversion\u002Fdebugging, or sequential domain reduction in the\n`bayesian-optimization` package.\n\n## Route here for\n\n- SciPy `NonlinearConstraint` setup with `BayesianOptimization(..., constraint=...)`.\n- `ConstraintModel` behavior: `eval`, `fit`, `predict`, `approx`, `allowed`,\n  multiple constraints, and registering known constrained observations.\n- Integer, categorical, float, or preconstructed `BayesParameter` entries in\n  `pbounds`.\n- Custom `BayesParameter` subclasses and kernel-space transforms.\n- `TargetSpace.params_to_array`, `array_to_params`, masks, bounds, and typed\n  conversion semantics.\n- `SequentialDomainReductionTransformer` setup, validation, and limitations.\n\n## Route elsewhere\n\n- Basic optimizer lifecycle, `maximize`, ask-tell loops, state save\u002Fload,\n  `predict`, and ordinary HPO recipes:\n  [`..\u002Foptimizer-workflows\u002FSKILL.md`](..\u002Foptimizer-workflows\u002FSKILL.md)\n- Acquisition selection, exploration\u002Fexploitation tuning, custom acquisition\n  functions, Constant Liar, or GPHedge:\n  [`..\u002Facquisition-control\u002FSKILL.md`](..\u002Facquisition-control\u002FSKILL.md)\n- Editing the repository, running native test selections, docs, lint, CI, or\n  release-maintenance checks:\n  [`..\u002Frepo-maintenance\u002FSKILL.md`](..\u002Frepo-maintenance\u002FSKILL.md)\n\n## Start with the relevant reference\n\n- Read [`references\u002Fconstraints.md`](references\u002Fconstraints.md) when the user\n  needs expensive\u002Flearned constraints, multi-output constraints, feasibility\n  debugging, or manual registration of constrained observations.\n- Read [`references\u002Fparameter-types.md`](references\u002Fparameter-types.md) when\n  `pbounds` includes integers, categories, preconstructed parameters, or custom\n  domain encodings.\n- Read [`references\u002Fdomain-reduction.md`](references\u002Fdomain-reduction.md) when\n  bounds should shrink during optimization or a bounds transformer fails.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when\n  errors mention mismatched constraint arguments, no allowed points, unsupported\n  constrained acquisitions, invalid categorical categories, key\u002Fdimension\n  mismatches, experimental non-float warnings, or domain reduction with typed\n  parameters.\n\n## Safe smoke check\n\nRun [`scripts\u002Fadvanced_features_smoke.py`](scripts\u002Fadvanced_features_smoke.py)\nonly after the package and its normal runtime dependencies are importable:\n\n```bash\npython scripts\u002Fadvanced_features_smoke.py --check all\n```\n\nThe helper is deterministic, uses no network and no plots, and validates tiny\nconstraint, typed-parameter, and domain-reduction behavior. Use\n`python scripts\u002Fadvanced_features_smoke.py --help` to list narrower checks.\n\n## Working rules for future agents\n\n1. Treat constraints and typed parameters as part of the domain definition, not\n   as after-the-fact filters. The optimizer wraps SciPy constraints in a\n   `ConstraintModel`, and the internal GP kernels use the `TargetSpace`\n   transform for typed domains.\n2. Keep objective and constraint keyword names identical. `TargetSpace` calls\n   both functions with the same `array_to_params(...)` result.\n3. For known observations in a constrained optimizer, always register the raw\n   constraint value with `constraint_value`; otherwise the target and\n   constraint histories cannot stay aligned.\n4. Expect a warning for non-float parameters. Integer\u002Fcategorical optimization\n   is useful, but still marked experimental by the package.\n5. Do not combine sequential domain reduction with integer, categorical, or\n   custom non-`FloatParameter` domains in the current implementation.\n6. If a task asks both for advanced domains and acquisition strategy design,\n   handle the domain facts here, then route acquisition-specific choices to\n   the acquisition-control sub-skill.\n","# Advanced Domain Features\n\nUse this sub-skill when a task involves constrained optimization, non-float\nsearch variables, custom parameter encodings, low-level `TargetSpace`\nconversion\u002Fdebugging, or sequential domain reduction in the\n`bayesian-optimization` package.\n\n## Route here for\n\n- SciPy `NonlinearConstraint` setup with `BayesianOptimization(..., constraint=...)`.\n- `ConstraintModel` behavior: `eval`, `fit`, `predict`, `approx`, `allowed`,\n  multiple constraints, and registering known constrained observations.\n- Integer, categorical, float, or preconstructed `BayesParameter` entries in\n  `pbounds`.\n- Custom `BayesParameter` subclasses and kernel-space transforms.\n- `TargetSpace.params_to_array`, `array_to_params`, masks, bounds, and typed\n  conversion semantics.\n- `SequentialDomainReductionTransformer` setup, validation, and limitations.\n\n## Route elsewhere\n\n- Basic optimizer lifecycle, `maximize`, ask-tell loops, state save\u002Fload,\n  `predict`, and ordinary HPO recipes:\n  [`..\u002Foptimizer-workflows\u002FSKILL.md`](..\u002Foptimizer-workflows\u002FSKILL.md)\n- Acquisition selection, exploration\u002Fexploitation tuning, custom acquisition\n  functions, Constant Liar, or GPHedge:\n  [`..\u002Facquisition-control\u002FSKILL.md`](..\u002Facquisition-control\u002FSKILL.md)\n- Editing the repository, running native test selections, docs, lint, CI, or\n  release-maintenance checks:\n  [`..\u002Frepo-maintenance\u002FSKILL.md`](..\u002Frepo-maintenance\u002FSKILL.md)\n\n## Start with the relevant reference\n\n- Read [`references\u002Fconstraints.md`](references\u002Fconstraints.md) when the user\n  needs expensive\u002Flearned constraints, multi-output constraints, feasibility\n  debugging, or manual registration of constrained observations.\n- Read [`references\u002Fparameter-types.md`](references\u002Fparameter-types.md) when\n  `pbounds` includes integers, categories, preconstructed parameters, or custom\n  domain encodings.\n- Read [`references\u002Fdomain-reduction.md`](references\u002Fdomain-reduction.md) when\n  bounds should shrink during optimization or a bounds transformer fails.\n- Read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) when\n  errors mention mismatched constraint arguments, no allowed points, unsupported\n  constrained acquisitions, invalid categorical categories, key\u002Fdimension\n  mismatches, experimental non-float warnings, or domain reduction with typed\n  parameters.\n\n## Safe smoke check\n\nRun [`scripts\u002Fadvanced_features_smoke.py`](scripts\u002Fadvanced_features_smoke.py)\nonly after the package and its normal runtime dependencies are importable:\n\n```bash\npython scripts\u002Fadvanced_features_smoke.py --check all\n```\n\nThe helper is deterministic, uses no network and no plots, and validates tiny\nconstraint, typed-parameter, and domain-reduction behavior. Use\n`python scripts\u002Fadvanced_features_smoke.py --help` to list narrower checks.\n\n## Working rules for future agents\n\n1. Treat constraints and typed parameters as part of the domain definition, not\n   as after-the-fact filters. The optimizer wraps SciPy constraints in a\n   `ConstraintModel`, and the internal GP kernels use the `TargetSpace`\n   transform for typed domains.\n2. Keep objective and constraint keyword names identical. `TargetSpace` calls\n   both functions with the same `array_to_params(...)` result.\n3. For known observations in a constrained optimizer, always register the raw\n   constraint value with `constraint_value`; otherwise the target and\n   constraint histories cannot stay aligned.\n4. Expect a warning for non-float parameters. Integer\u002Fcategorical optimization\n   is useful, but still marked experimental by the package.\n5. Do not combine sequential domain reduction with integer, categorical, or\n   custom non-`FloatParameter` domains in the current implementation.\n6. If a task asks both for advanced domains and acquisition strategy design,\n   handle the domain facts here, then route acquisition-specific choices to\n   the acquisition-control sub-skill.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Fadvanced-domain-features",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 advanced-domain-features",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill advanced-domain-features",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill advanced-domain-features","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Fadvanced-domain-features\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fconstraints.md","REFERENCE","参考文档",7497,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Fadvanced-domain-features\u002Freferences\u002Fconstraints.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdomain-reduction.md",7189,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Fadvanced-domain-features\u002Freferences\u002Fdomain-reduction.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fparameter-types.md",9733,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Fadvanced-domain-features\u002Freferences\u002Fparameter-types.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",8886,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Fadvanced-domain-features\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fadvanced_features_smoke.py","SCRIPT","脚本",11306,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fbayesian-optimization\u002Fsub-skills\u002Fadvanced-domain-features\u002Fscripts\u002Fadvanced_features_smoke.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"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.","Apache-2.0","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":75,"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":75,"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":75,"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":75,"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":75,"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",[],[]]