[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7939K4Q40JAVVTTWN506QBZ":3,"skill-same:01M7939K4Q40JAVVTTWN506QBZ":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},"01M7939K4Q40JAVVTTWN506QBZ","pymoo",null,"Use pymoo for single-, multi-, and many-objective optimization, custom problems, evolutionary operators, performance tuning, and Pareto analysis.","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\u002Fpymoo\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pymoo\ndescription: \"Use pymoo for single-, multi-, and many-objective optimization,\n  custom problems, evolutionary operators, performance tuning, and Pareto\n  analysis.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# pymoo\n\nUse this repo skill when a task involves pymoo, evolutionary computation,\nsingle-objective optimization, multi-objective or many-objective optimization,\nPareto fronts, custom optimization problems, genetic operators, reference\ndirections, constraint handling, performance indicators, or pymoo visualization.\n\npymoo is a Python package for optimization workflows. It minimizes all\nobjectives, represents inequality constraints as `G \u003C= 0`, and centers common\nusage around a `Problem`, an `Algorithm`, a termination criterion, and\n`pymoo.optimize.minimize`.\n\n## Quick install and smoke\n\nPublic install path:\n\n```bash\npython -m pip install -U pymoo\n```\n\nMinimal import\u002Fruntime check:\n\n```bash\npython - \u003C\u003C'PY'\nfrom pymoo.algorithms.moo.nsga2 import NSGA2\nfrom pymoo.optimize import minimize\nfrom pymoo.problems import get_problem\n\nres = minimize(get_problem(\"zdt1\"), NSGA2(pop_size=20), (\"n_gen\", 3), seed=1, verbose=False)\nprint(res.F.shape, res.algorithm.evaluator.n_eval)\nPY\n```\n\nFor a bundled self-check after installing pymoo, run\n[scripts\u002Fpymoo_quickstart_smoke.py](scripts\u002Fpymoo_quickstart_smoke.py).\n\n## Route by task\n\n| User task signal | Read |\n| --- | --- |\n| Run NSGA-II\u002FNSGA-III\u002FGA\u002FDE\u002FPSO\u002FMOEA\u002FD, choose an algorithm, set termination, use `minimize`, inspect `Result`, callbacks, history, ask-and-tell, external evaluation loop | [optimization-workflows](sub-skills\u002Foptimization-workflows\u002FSKILL.md) |\n| Define a custom problem, choose `Problem` vs `ElementwiseProblem` vs `FunctionalProblem`, use `get_problem`, fix `F`\u002F`G`\u002F`H` shapes, convert maximization or constraints, handle bounds\u002FPareto fronts | [problem-modeling](sub-skills\u002Fproblem-modeling\u002FSKILL.md) |\n| Configure real\u002Finteger\u002Fbinary\u002Fchoice variables, mixed-variable search, sampling\u002Fcrossover\u002Fmutation\u002Frepair, duplicate elimination, initial populations, custom object\u002Fpermutation operators, hyperparameter helper APIs | [operators-and-variables](sub-skills\u002Foperators-and-variables\u002FSKILL.md) |\n| Speed up slow evaluations, vectorize objectives, add thread\u002Fprocess starmap, use optional joblib\u002Fdask\u002Fray, check Cython compiled extensions, reason about optional GPU\u002Fbackend paths, control history\u002Fprogress overhead | [performance-and-parallelization](sub-skills\u002Fperformance-and-parallelization\u002FSKILL.md) |\n| Compute hypervolume, GD\u002FIGD\u002Fepsilon\u002FKKTPM\u002FR-metric, generate reference directions, use decomposition or MCDM, analyze convergence\u002Fhistory, save headless Pareto plots | [analysis-and-visualization](sub-skills\u002Fanalysis-and-visualization\u002FSKILL.md) |\n\n## Operating rules that prevent common pymoo mistakes\n\n1. **Minimization only**: negate objectives that are originally maximized.\n2. **Constraint sign**: inequality constraints are feasible when `out[\"G\"] \u003C= 0`;\n   equality residuals belong in `out[\"H\"]` with `n_eq_constr`.\n3. **Validate problem shapes first**: check tiny `problem.evaluate(...)` samples\n   before tuning algorithms.\n4. **Use explicit budgets**: pass termination tuples such as `(\"n_gen\", 50)` or\n   `(\"n_evals\", 5000)` for reproducible scripts.\n5. **Seed stochastic runs**: pass `seed=...` and control randomness inside custom\n   objective code, especially under parallel evaluation.\n6. **Match algorithm to search space**: mixed\u002Fdiscrete\u002Fpermutation variables need\n   matching variables\u002Foperators or repair, not just a float-coded algorithm.\n7. **Keep optional extras explicit**: base pymoo includes matplotlib and core\n   numerical dependencies; joblib\u002Fdask\u002Fray, Optuna, COMO-CMA-ES, pyrecorder, and\n   GPU frameworks are optional task-specific additions.\n8. **Use headless plotting in agents**: set a non-interactive Matplotlib backend\n   and save figures instead of relying on GUI `show()`.\n\n## Shared references\n\n- [API entrypoints](references\u002Fapi-entrypoints.md): cross-sub-skill import map,\n  version\u002Fextras notes, and first checks.\n- [Troubleshooting](references\u002Ftroubleshooting.md): install\u002Fimport, compiled\n  extension, optional dependency, and cross-workflow failure routing.\n- [Repo provenance](references\u002Frepo-provenance.md): source version and evidence\n  baseline for refresh decisions.\n- [Repo routing metadata](references\u002Frepo-routing-metadata.json): structured\n  router metadata consumed during managed import.\n\n## Bundled self-check scripts\n\n- [scripts\u002Fpymoo_quickstart_smoke.py](scripts\u002Fpymoo_quickstart_smoke.py): base\n  import, compiled-extension status, and tiny `NSGA2`\u002F`ZDT1` run.\n- Sub-skill scripts cover custom-problem shape validation, mixed-variable search,\n  parallel elementwise evaluation, indicator checks, compiled-extension checks,\n  and headless scatter plotting.\n\n## Avoid this skill when\n\n- The task is generic mathematical optimization with SciPy and does not use\n  pymoo APIs, evolutionary operators, Pareto fronts, or pymoo problem classes.\n- The task is hyperparameter optimization with Optuna\u002FRay Tune alone and no pymoo\n  algorithm\u002Fproblem integration.\n- The task requires training deep learning models or GPU tensor code unrelated to\n  pymoo's optional vectorized objective pattern.\n","# pymoo\n\nUse this repo skill when a task involves pymoo, evolutionary computation,\nsingle-objective optimization, multi-objective or many-objective optimization,\nPareto fronts, custom optimization problems, genetic operators, reference\ndirections, constraint handling, performance indicators, or pymoo visualization.\n\npymoo is a Python package for optimization workflows. It minimizes all\nobjectives, represents inequality constraints as `G \u003C= 0`, and centers common\nusage around a `Problem`, an `Algorithm`, a termination criterion, and\n`pymoo.optimize.minimize`.\n\n## Quick install and smoke\n\nPublic install path:\n\n```bash\npython -m pip install -U pymoo\n```\n\nMinimal import\u002Fruntime check:\n\n```bash\npython - \u003C\u003C'PY'\nfrom pymoo.algorithms.moo.nsga2 import NSGA2\nfrom pymoo.optimize import minimize\nfrom pymoo.problems import get_problem\n\nres = minimize(get_problem(\"zdt1\"), NSGA2(pop_size=20), (\"n_gen\", 3), seed=1, verbose=False)\nprint(res.F.shape, res.algorithm.evaluator.n_eval)\nPY\n```\n\nFor a bundled self-check after installing pymoo, run\n[scripts\u002Fpymoo_quickstart_smoke.py](scripts\u002Fpymoo_quickstart_smoke.py).\n\n## Route by task\n\n| User task signal | Read |\n| --- | --- |\n| Run NSGA-II\u002FNSGA-III\u002FGA\u002FDE\u002FPSO\u002FMOEA\u002FD, choose an algorithm, set termination, use `minimize`, inspect `Result`, callbacks, history, ask-and-tell, external evaluation loop | [optimization-workflows](sub-skills\u002Foptimization-workflows\u002FSKILL.md) |\n| Define a custom problem, choose `Problem` vs `ElementwiseProblem` vs `FunctionalProblem`, use `get_problem`, fix `F`\u002F`G`\u002F`H` shapes, convert maximization or constraints, handle bounds\u002FPareto fronts | [problem-modeling](sub-skills\u002Fproblem-modeling\u002FSKILL.md) |\n| Configure real\u002Finteger\u002Fbinary\u002Fchoice variables, mixed-variable search, sampling\u002Fcrossover\u002Fmutation\u002Frepair, duplicate elimination, initial populations, custom object\u002Fpermutation operators, hyperparameter helper APIs | [operators-and-variables](sub-skills\u002Foperators-and-variables\u002FSKILL.md) |\n| Speed up slow evaluations, vectorize objectives, add thread\u002Fprocess starmap, use optional joblib\u002Fdask\u002Fray, check Cython compiled extensions, reason about optional GPU\u002Fbackend paths, control history\u002Fprogress overhead | [performance-and-parallelization](sub-skills\u002Fperformance-and-parallelization\u002FSKILL.md) |\n| Compute hypervolume, GD\u002FIGD\u002Fepsilon\u002FKKTPM\u002FR-metric, generate reference directions, use decomposition or MCDM, analyze convergence\u002Fhistory, save headless Pareto plots | [analysis-and-visualization](sub-skills\u002Fanalysis-and-visualization\u002FSKILL.md) |\n\n## Operating rules that prevent common pymoo mistakes\n\n1. **Minimization only**: negate objectives that are originally maximized.\n2. **Constraint sign**: inequality constraints are feasible when `out[\"G\"] \u003C= 0`;\n   equality residuals belong in `out[\"H\"]` with `n_eq_constr`.\n3. **Validate problem shapes first**: check tiny `problem.evaluate(...)` samples\n   before tuning algorithms.\n4. **Use explicit budgets**: pass termination tuples such as `(\"n_gen\", 50)` or\n   `(\"n_evals\", 5000)` for reproducible scripts.\n5. **Seed stochastic runs**: pass `seed=...` and control randomness inside custom\n   objective code, especially under parallel evaluation.\n6. **Match algorithm to search space**: mixed\u002Fdiscrete\u002Fpermutation variables need\n   matching variables\u002Foperators or repair, not just a float-coded algorithm.\n7. **Keep optional extras explicit**: base pymoo includes matplotlib and core\n   numerical dependencies; joblib\u002Fdask\u002Fray, Optuna, COMO-CMA-ES, pyrecorder, and\n   GPU frameworks are optional task-specific additions.\n8. **Use headless plotting in agents**: set a non-interactive Matplotlib backend\n   and save figures instead of relying on GUI `show()`.\n\n## Shared references\n\n- [API entrypoints](references\u002Fapi-entrypoints.md): cross-sub-skill import map,\n  version\u002Fextras notes, and first checks.\n- [Troubleshooting](references\u002Ftroubleshooting.md): install\u002Fimport, compiled\n  extension, optional dependency, and cross-workflow failure routing.\n- [Repo provenance](references\u002Frepo-provenance.md): source version and evidence\n  baseline for refresh decisions.\n- [Repo routing metadata](references\u002Frepo-routing-metadata.json): structured\n  router metadata consumed during managed import.\n\n## Bundled self-check scripts\n\n- [scripts\u002Fpymoo_quickstart_smoke.py](scripts\u002Fpymoo_quickstart_smoke.py): base\n  import, compiled-extension status, and tiny `NSGA2`\u002F`ZDT1` run.\n- Sub-skill scripts cover custom-problem shape validation, mixed-variable search,\n  parallel elementwise evaluation, indicator checks, compiled-extension checks,\n  and headless scatter plotting.\n\n## Avoid this skill when\n\n- The task is generic mathematical optimization with SciPy and does not use\n  pymoo APIs, evolutionary operators, Pareto fronts, or pymoo problem classes.\n- The task is hyperparameter optimization with Optuna\u002FRay Tune alone and no pymoo\n  algorithm\u002Fproblem integration.\n- The task requires training deep learning models or GPU tensor code unrelated to\n  pymoo's optional vectorized objective pattern.\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\u002Fpymoo",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 pymoo",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pymoo",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pymoo","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpymoo\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-entrypoints.md","REFERENCE","参考文档",3775,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpymoo\u002Freferences\u002Fapi-entrypoints.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",3181,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpymoo\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",332,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpymoo\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",4065,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpymoo\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fpymoo_quickstart_smoke.py","SCRIPT","脚本",2010,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpymoo\u002Fscripts\u002Fpymoo_quickstart_smoke.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",[],[]]