[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793JD18ZGHWDNFC1BAGFGAA":3,"skill-same:01M793JD18ZGHWDNFC1BAGFGAA":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},"01M793JD18ZGHWDNFC1BAGFGAA","fit-and-diagnose",null,"Fit ordinary PySR regressors, inspect Pareto fronts, select equations, and diagnose slow or poor searches.","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\u002Fpysr\u002Fsub-skills\u002Ffit-and-diagnose\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: fit-and-diagnose\ndescription: \"Fit ordinary PySR regressors, inspect Pareto fronts, select\n  equations, and diagnose slow or poor searches.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# PySR fit-and-diagnose\n\nUse this sub-skill when the task is an ordinary PySR symbolic-regression fit: prepare tabular data, choose a small operator set, run `PySRRegressor.fit`, inspect `model.equations_`, pick equations from the Pareto front, call `predict`\u002F`sympy`\u002F`latex`, or debug a slow or low-quality search.\n\n## Route first\n\n| User need | Use here? | Route |\n| --- | --- | --- |\n| Plain `PySRRegressor` fit, data shape, feature names, weights, denoising, feature selection, Pareto selection | Yes | Continue below. |\n| Custom Julia operators, custom elementwise\u002Ffull losses, units, operator constraints, required\u002Fforbidden structure by loss penalties | No | `..\u002Fcustomization-and-constraints\u002FSKILL.md` |\n| Known expression templates, parametric expressions, shared\u002Fvector-valued templates, guesses for templates | No | `..\u002Fstructured-expressions\u002FSKILL.md` |\n| Saved hall-of-fame files, reload\u002Fcheckpoints, SymPy\u002FLaTeX\u002FJAX\u002FTorch export details, TensorBoard artifacts | No | `..\u002Fexport-and-artifacts\u002FSKILL.md` |\n| Installation, first Julia startup, threading, multiprocessing, Slurm, long-run scaling, reproducibility environment | Usually no | `..\u002Fruntime-and-scaling\u002FSKILL.md` |\n\n## Minimal operating loop\n\n1. **Validate data shape.** Use `X` as `(n_samples, n_features)` and `y` as `(n_samples,)` for one target or `(n_samples, n_outputs)` for independent multi-output fits. Prefer a pandas DataFrame when feature names matter; otherwise pass safe `variable_names` to `fit`.\n2. **Start with a small operator set.** Use only operators that are plausible for the domain. For a polynomial-like first pass, start with `binary_operators=[\"+\", \"-\", \"*\"]`; add `\u002F`, trig, `exp`, or other operators only when justified.\n3. **Bound the first run.** Start short to validate the setup, then run longer. Use `niterations`, `timeout_in_seconds`, or `max_evals` for budget control. Avoid interpreting the first Julia compile as a search failure.\n4. **Fit and inspect the whole front.** `model.fit(X, y, weights=..., variable_names=...)` stores a Pareto front in `model.equations_`. Print it and inspect loss versus complexity rather than reporting only the auto-selected row.\n5. **Select explicitly when needed.** `model_selection=\"best\"` balances loss and simplicity; `\"accuracy\"` chooses minimum loss; `\"score\"` chooses the largest score. Pass `index=` to `predict`, `sympy`, or `latex` to evaluate a specific row.\n6. **Iterate scientifically.** If results are trivial or slow, simplify features\u002Foperators, adjust `maxsize`, use `select_k_features` for high-dimensional tabular data, consider `denoise=True` or weights for noisy data, and only then add more compute.\n\nSee `references\u002Fworkflows.md` for recipes, `references\u002Fapi-reference.md` for focused signatures and option semantics, and `references\u002Ftroubleshooting.md` for failure modes.\n\n## Safe bundled smoke helper\n\n`scripts\u002Fpysr_quickstart_smoke.py` is a small, deterministic helper for agents. It is help\u002Fdry-run oriented by default and imports PySR only when `--run-fit` is supplied.\n\n```bash\npython scripts\u002Fpysr_quickstart_smoke.py --help\npython scripts\u002Fpysr_quickstart_smoke.py --run-fit --niterations 1 --timeout-seconds 20\n```\n\nThe helper is a smoke check, not a benchmark. A successful run proves that import, a tiny fit, `equations_`, `predict`, `sympy`, and `latex` are usable in the current environment; it does not prove convergence on the user's dataset.\n","# PySR fit-and-diagnose\n\nUse this sub-skill when the task is an ordinary PySR symbolic-regression fit: prepare tabular data, choose a small operator set, run `PySRRegressor.fit`, inspect `model.equations_`, pick equations from the Pareto front, call `predict`\u002F`sympy`\u002F`latex`, or debug a slow or low-quality search.\n\n## Route first\n\n| User need | Use here? | Route |\n| --- | --- | --- |\n| Plain `PySRRegressor` fit, data shape, feature names, weights, denoising, feature selection, Pareto selection | Yes | Continue below. |\n| Custom Julia operators, custom elementwise\u002Ffull losses, units, operator constraints, required\u002Fforbidden structure by loss penalties | No | `..\u002Fcustomization-and-constraints\u002FSKILL.md` |\n| Known expression templates, parametric expressions, shared\u002Fvector-valued templates, guesses for templates | No | `..\u002Fstructured-expressions\u002FSKILL.md` |\n| Saved hall-of-fame files, reload\u002Fcheckpoints, SymPy\u002FLaTeX\u002FJAX\u002FTorch export details, TensorBoard artifacts | No | `..\u002Fexport-and-artifacts\u002FSKILL.md` |\n| Installation, first Julia startup, threading, multiprocessing, Slurm, long-run scaling, reproducibility environment | Usually no | `..\u002Fruntime-and-scaling\u002FSKILL.md` |\n\n## Minimal operating loop\n\n1. **Validate data shape.** Use `X` as `(n_samples, n_features)` and `y` as `(n_samples,)` for one target or `(n_samples, n_outputs)` for independent multi-output fits. Prefer a pandas DataFrame when feature names matter; otherwise pass safe `variable_names` to `fit`.\n2. **Start with a small operator set.** Use only operators that are plausible for the domain. For a polynomial-like first pass, start with `binary_operators=[\"+\", \"-\", \"*\"]`; add `\u002F`, trig, `exp`, or other operators only when justified.\n3. **Bound the first run.** Start short to validate the setup, then run longer. Use `niterations`, `timeout_in_seconds`, or `max_evals` for budget control. Avoid interpreting the first Julia compile as a search failure.\n4. **Fit and inspect the whole front.** `model.fit(X, y, weights=..., variable_names=...)` stores a Pareto front in `model.equations_`. Print it and inspect loss versus complexity rather than reporting only the auto-selected row.\n5. **Select explicitly when needed.** `model_selection=\"best\"` balances loss and simplicity; `\"accuracy\"` chooses minimum loss; `\"score\"` chooses the largest score. Pass `index=` to `predict`, `sympy`, or `latex` to evaluate a specific row.\n6. **Iterate scientifically.** If results are trivial or slow, simplify features\u002Foperators, adjust `maxsize`, use `select_k_features` for high-dimensional tabular data, consider `denoise=True` or weights for noisy data, and only then add more compute.\n\nSee `references\u002Fworkflows.md` for recipes, `references\u002Fapi-reference.md` for focused signatures and option semantics, and `references\u002Ftroubleshooting.md` for failure modes.\n\n## Safe bundled smoke helper\n\n`scripts\u002Fpysr_quickstart_smoke.py` is a small, deterministic helper for agents. It is help\u002Fdry-run oriented by default and imports PySR only when `--run-fit` is supplied.\n\n```bash\npython scripts\u002Fpysr_quickstart_smoke.py --help\npython scripts\u002Fpysr_quickstart_smoke.py --run-fit --niterations 1 --timeout-seconds 20\n```\n\nThe helper is a smoke check, not a benchmark. A successful run proves that import, a tiny fit, `equations_`, `predict`, `sympy`, and `latex` are usable in the current environment; it does not prove convergence on the user's dataset.\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\u002Fpysr\u002Fsub-skills\u002Ffit-and-diagnose",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 fit-and-diagnose",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill fit-and-diagnose",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill fit-and-diagnose","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpysr\u002Fsub-skills\u002Ffit-and-diagnose\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",8172,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpysr\u002Fsub-skills\u002Ffit-and-diagnose\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",7846,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpysr\u002Fsub-skills\u002Ffit-and-diagnose\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",8604,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpysr\u002Fsub-skills\u002Ffit-and-diagnose\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fpysr_quickstart_smoke.py","SCRIPT","脚本",4920,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpysr\u002Fsub-skills\u002Ffit-and-diagnose\u002Fscripts\u002Fpysr_quickstart_smoke.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",[],[]]