[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792QPBAXV864RF9G97EZNP2":3,"skill-same:01M792QPBAXV864RF9G97EZNP2":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},"01M792QPBAXV864RF9G97EZNP2","sr",null,"Single-dataset symbolic regression with PhySO SR, including units, weights, presets, logging, and Pareto inspection.","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\u002Fphyso\u002Fsub-skills\u002Fsr\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sr\ndescription: \"Single-dataset symbolic regression with PhySO SR, including units,\n  weights, presets, logging, and Pareto inspection.\"\nread_when: \"Use when the user has one X\u002Fy dataset and wants physo.SR guidance,\n  dimensional-analysis units, y_weights, candidate_wrapper, config0\u002Fconfig0b,\n  CPU\u002Fparallel notes, logs, or a safe quick-start smoke.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# PhySO SR Sub-skill\n\n## Role\n\nUse this sub-skill to help a Researcher run **single-dataset symbolic regression** with `physo.SR`. It covers preparing one `X, y` dataset, optional point weights, dimensional-analysis units, free\u002Ffixed constants, operator choices, light run configurations, logging, and result\u002FPareto-front inspection. For root routing across all PhySO sub-skills, see the parent skill at [`..\u002F..\u002FSKILL.md`](..\u002F..\u002FSKILL.md).\n\n## Boundaries\n\nIncluded:\n- One dataset with `X` shaped `(n_dim, n_samples)` and `y` shaped `(n_samples,)`.\n- `X_names`, `X_units`, `y_name`, `y_units`, fixed constants, and SR free constants.\n- `y_weights` as either one scalar or one per-sample vector aligned with `y`.\n- `candidate_wrapper`, `op_names`, `use_protected_ops`, `config0`\u002F`config0b` selection, `epochs`, `stop_reward`, `max_n_evaluations`, logging, and CPU-safe execution.\n- Handoff to Pareto\u002Flog inspection helpers after a run.\n\nExcluded:\n- Multi-dataset `physo.ClassSR`, class free constants, and realization-specific free constants; use sibling [`class-sr`](..\u002Fclass-sr\u002FSKILL.md) when the user has multiple datasets or class\u002Fspe constants.\n- Benchmark-problem definitions or maintainer benchmark runners; use sibling [`benchmarks`](..\u002Fbenchmarks\u002FSKILL.md) for packaged Feynman\u002FClass benchmark loaders.\n- Low-level expression\u002Flibrary construction and random-expression sampling; use sibling [`toolkit`](..\u002Ftoolkit\u002FSKILL.md) for those APIs.\n- Generic PyTorch or scikit-learn regression advice outside the PhySO SR workflow.\n\n## Verified entry points\n\n- `physo.SR(X, y, y_weights=1.0, X_names=None, X_units=None, y_name=None, y_units=None, fixed_consts=None, fixed_consts_units=None, free_consts_names=None, free_consts_units=None, free_consts_init_val=None, op_names=None, use_protected_ops=True, stop_reward=1.0, max_n_evaluations=None, stop_after_n_epochs=10, epochs=None, candidate_wrapper=None, run_config=None, get_run_logger=None, get_run_visualiser=None, parallel_mode=True, n_cpus=None, device=\"cpu\")`\n- `physo.config.config0.config0` and `physo.config.config0b.config0b` for light SR presets.\n- `physo.learn.monitoring.RunLogger` and `physo.learn.monitoring.RunVisualiser` for logs and optional plots.\n- `logs.get_pareto_front()` from the returned logger.\n- `physo.read_pareto_pkl`, `physo.read_pareto_csv`, and `physo.load_expr` for saved-result inspection.\n\n## Operating workflow\n\n1. **Route first.** Stay here for one `X, y` dataset. If the request mentions several realizations, shared formula across datasets, class constants, or per-dataset constants, route to `class-sr`.\n2. **Prepare numeric inputs.** Convert tabular data to floating arrays, then transpose feature matrices so `X.shape == (n_dim, n_samples)` and `y.shape == (n_samples,)`. Keep `y_weights` either a scalar or a per-sample float array with the same shape as `y`.\n3. **Define units and constants.** If dimensional analysis matters, give every variable and constant a consistent units vector of length up to seven; otherwise omit units or use zero vectors. SR free constants are single-dataset\u002Fclass-style constants only.\n4. **Choose operators and wrappers.** Start with the default operator set unless the task needs a narrow grammar. Keep `candidate_wrapper` callable, top-level if multiprocessing is used, differentiable, and implemented with torch operations when free constants are optimized.\n5. **Choose a preset.** Use `config0` for demos and short smokes. Use `config0b` when a quick SR task has free constants and you want more LBFGS constant-optimization steps without moving to heavier presets. Deep-copy presets before editing.\n6. **Run safely.** For notebooks, debugging, and the verified CPU smoke path, set `parallel_mode=False`, `n_cpus=1`, and `device=\"cpu\"`. This skill does not verify CUDA behavior.\n7. **Inspect results.** Treat the returned `expression` as the current best `Program`; use `logs.get_pareto_front()` for the complexity\u002Freward\u002FRMSE front, and saved Pareto pkl\u002Fcsv helpers for later inspection.\n8. **Recover from failures.** Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) before changing algorithms; most SR failures are shape, units, weights, wrapper, preset-mutation, or optional-display issues.\n\n## Input and output contract\n\nInputs expected by this sub-skill:\n- `X`: float NumPy array or torch tensor convertible to shape `(n_dim, n_samples)`.\n- `y`: float vector convertible to shape `(n_samples,)` with no NaNs.\n- Optional `y_weights`: scalar, or float vector with the same sample length as `y`.\n- Optional units: `X_units` length equals `n_dim`; `y_units`, `fixed_consts_units`, and `free_consts_units` use the same convention and vector length up to seven.\n- Optional grammar\u002Fconfig: `op_names`, `use_protected_ops`, a deep-copied `run_config`, and a torch-compatible `candidate_wrapper`.\n\nOutputs returned by `physo.SR`:\n- `expression`: a `physo.physym.program.Program` for the best expression found so far.\n- `logs`: a `RunLogger` with histories and `get_pareto_front()` returning `(complexities, programs, rewards, rmse)`.\n- Optional saved artifacts if the logger\u002Fvisualiser are configured to save: run CSV logs, Pareto CSV, Pareto pkl, and plots.\n\n## Bundled references and helper\n\n- [`references\u002Fworkflows.md`](references\u002Fworkflows.md): quick-start, weighted data, dimensional-analysis, wrapper, and result-inspection recipes.\n- [`references\u002Fconfigurations.md`](references\u002Fconfigurations.md): preset choice, safe edits, stopping criteria, parallel\u002Fdevice notes, and operator\u002Fprior alignment.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): recover from import, shape, unit, weight, wrapper, parallel, display, and Pareto-loading mistakes.\n- [`scripts\u002Fsmoke_sr_quick_start.py`](scripts\u002Fsmoke_sr_quick_start.py): short CPU-only smoke adapted from the SR quick start; it runs a tiny weighted single-dataset SR call and reloads the Pareto pkl it writes.\n\n## Related native tests and examples\n\nNative candidates for later verification of this route:\n\n- `physo.task.tests.sr_UnitTest`: deterministic `physo.SR` calls, including the canonical energy-style quick-start and a reduced-operator case that tolerates prior warnings.\n- `physo.physym.tests.execute_UnitTest`: lower-level expression execution on CPU\u002FCUDA-capable hosts; use only as execution evidence here, not as CUDA proof.\n- `physo.physym.tests.program_display_UnitTest`: string, SymPy, LaTeX, and optional tree-display behavior; display extras can fail gracefully.\n- `physo.learn.tests.monitoring_UnitTest`: SR logging, Pareto-front collection, and cleanup behavior.\n\nSource examples distilled into this sub-skill:\n\n- The bundled smoke helper adapts the canonical SR quick-start into a tiny CPU-only installed-package check.\n- The y-weights demo material is distilled into the weighted-data workflow reference rather than copied as a runnable notebook.\n- The damped harmonic oscillator demo is useful as a longer, dimensioned SR reference, but its long run settings are not bundled as a smoke helper.\n- Feynman benchmark runners and job-file generators are maintainer\u002Freference material, not SR runtime helpers; use benchmark-focused siblings for packaged benchmark problem loaders.\n","# PhySO SR Sub-skill\n\n## Role\n\nUse this sub-skill to help a Researcher run **single-dataset symbolic regression** with `physo.SR`. It covers preparing one `X, y` dataset, optional point weights, dimensional-analysis units, free\u002Ffixed constants, operator choices, light run configurations, logging, and result\u002FPareto-front inspection. For root routing across all PhySO sub-skills, see the parent skill at [`..\u002F..\u002FSKILL.md`](..\u002F..\u002FSKILL.md).\n\n## Boundaries\n\nIncluded:\n- One dataset with `X` shaped `(n_dim, n_samples)` and `y` shaped `(n_samples,)`.\n- `X_names`, `X_units`, `y_name`, `y_units`, fixed constants, and SR free constants.\n- `y_weights` as either one scalar or one per-sample vector aligned with `y`.\n- `candidate_wrapper`, `op_names`, `use_protected_ops`, `config0`\u002F`config0b` selection, `epochs`, `stop_reward`, `max_n_evaluations`, logging, and CPU-safe execution.\n- Handoff to Pareto\u002Flog inspection helpers after a run.\n\nExcluded:\n- Multi-dataset `physo.ClassSR`, class free constants, and realization-specific free constants; use sibling [`class-sr`](..\u002Fclass-sr\u002FSKILL.md) when the user has multiple datasets or class\u002Fspe constants.\n- Benchmark-problem definitions or maintainer benchmark runners; use sibling [`benchmarks`](..\u002Fbenchmarks\u002FSKILL.md) for packaged Feynman\u002FClass benchmark loaders.\n- Low-level expression\u002Flibrary construction and random-expression sampling; use sibling [`toolkit`](..\u002Ftoolkit\u002FSKILL.md) for those APIs.\n- Generic PyTorch or scikit-learn regression advice outside the PhySO SR workflow.\n\n## Verified entry points\n\n- `physo.SR(X, y, y_weights=1.0, X_names=None, X_units=None, y_name=None, y_units=None, fixed_consts=None, fixed_consts_units=None, free_consts_names=None, free_consts_units=None, free_consts_init_val=None, op_names=None, use_protected_ops=True, stop_reward=1.0, max_n_evaluations=None, stop_after_n_epochs=10, epochs=None, candidate_wrapper=None, run_config=None, get_run_logger=None, get_run_visualiser=None, parallel_mode=True, n_cpus=None, device=\"cpu\")`\n- `physo.config.config0.config0` and `physo.config.config0b.config0b` for light SR presets.\n- `physo.learn.monitoring.RunLogger` and `physo.learn.monitoring.RunVisualiser` for logs and optional plots.\n- `logs.get_pareto_front()` from the returned logger.\n- `physo.read_pareto_pkl`, `physo.read_pareto_csv`, and `physo.load_expr` for saved-result inspection.\n\n## Operating workflow\n\n1. **Route first.** Stay here for one `X, y` dataset. If the request mentions several realizations, shared formula across datasets, class constants, or per-dataset constants, route to `class-sr`.\n2. **Prepare numeric inputs.** Convert tabular data to floating arrays, then transpose feature matrices so `X.shape == (n_dim, n_samples)` and `y.shape == (n_samples,)`. Keep `y_weights` either a scalar or a per-sample float array with the same shape as `y`.\n3. **Define units and constants.** If dimensional analysis matters, give every variable and constant a consistent units vector of length up to seven; otherwise omit units or use zero vectors. SR free constants are single-dataset\u002Fclass-style constants only.\n4. **Choose operators and wrappers.** Start with the default operator set unless the task needs a narrow grammar. Keep `candidate_wrapper` callable, top-level if multiprocessing is used, differentiable, and implemented with torch operations when free constants are optimized.\n5. **Choose a preset.** Use `config0` for demos and short smokes. Use `config0b` when a quick SR task has free constants and you want more LBFGS constant-optimization steps without moving to heavier presets. Deep-copy presets before editing.\n6. **Run safely.** For notebooks, debugging, and the verified CPU smoke path, set `parallel_mode=False`, `n_cpus=1`, and `device=\"cpu\"`. This skill does not verify CUDA behavior.\n7. **Inspect results.** Treat the returned `expression` as the current best `Program`; use `logs.get_pareto_front()` for the complexity\u002Freward\u002FRMSE front, and saved Pareto pkl\u002Fcsv helpers for later inspection.\n8. **Recover from failures.** Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) before changing algorithms; most SR failures are shape, units, weights, wrapper, preset-mutation, or optional-display issues.\n\n## Input and output contract\n\nInputs expected by this sub-skill:\n- `X`: float NumPy array or torch tensor convertible to shape `(n_dim, n_samples)`.\n- `y`: float vector convertible to shape `(n_samples,)` with no NaNs.\n- Optional `y_weights`: scalar, or float vector with the same sample length as `y`.\n- Optional units: `X_units` length equals `n_dim`; `y_units`, `fixed_consts_units`, and `free_consts_units` use the same convention and vector length up to seven.\n- Optional grammar\u002Fconfig: `op_names`, `use_protected_ops`, a deep-copied `run_config`, and a torch-compatible `candidate_wrapper`.\n\nOutputs returned by `physo.SR`:\n- `expression`: a `physo.physym.program.Program` for the best expression found so far.\n- `logs`: a `RunLogger` with histories and `get_pareto_front()` returning `(complexities, programs, rewards, rmse)`.\n- Optional saved artifacts if the logger\u002Fvisualiser are configured to save: run CSV logs, Pareto CSV, Pareto pkl, and plots.\n\n## Bundled references and helper\n\n- [`references\u002Fworkflows.md`](references\u002Fworkflows.md): quick-start, weighted data, dimensional-analysis, wrapper, and result-inspection recipes.\n- [`references\u002Fconfigurations.md`](references\u002Fconfigurations.md): preset choice, safe edits, stopping criteria, parallel\u002Fdevice notes, and operator\u002Fprior alignment.\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md): recover from import, shape, unit, weight, wrapper, parallel, display, and Pareto-loading mistakes.\n- [`scripts\u002Fsmoke_sr_quick_start.py`](scripts\u002Fsmoke_sr_quick_start.py): short CPU-only smoke adapted from the SR quick start; it runs a tiny weighted single-dataset SR call and reloads the Pareto pkl it writes.\n\n## Related native tests and examples\n\nNative candidates for later verification of this route:\n\n- `physo.task.tests.sr_UnitTest`: deterministic `physo.SR` calls, including the canonical energy-style quick-start and a reduced-operator case that tolerates prior warnings.\n- `physo.physym.tests.execute_UnitTest`: lower-level expression execution on CPU\u002FCUDA-capable hosts; use only as execution evidence here, not as CUDA proof.\n- `physo.physym.tests.program_display_UnitTest`: string, SymPy, LaTeX, and optional tree-display behavior; display extras can fail gracefully.\n- `physo.learn.tests.monitoring_UnitTest`: SR logging, Pareto-front collection, and cleanup behavior.\n\nSource examples distilled into this sub-skill:\n\n- The bundled smoke helper adapts the canonical SR quick-start into a tiny CPU-only installed-package check.\n- The y-weights demo material is distilled into the weighted-data workflow reference rather than copied as a runnable notebook.\n- The damped harmonic oscillator demo is useful as a longer, dimensioned SR reference, but its long run settings are not bundled as a smoke helper.\n- Feynman benchmark runners and job-file generators are maintainer\u002Freference material, not SR runtime helpers; use benchmark-focused siblings for packaged benchmark problem loaders.\n",{"name":5,"license":14,"metadata":23,"read_when":25,"description":7,"disable-model-invocation":26},{"disco-role":24},"operating","Use when the user has one X\u002Fy dataset and wants physo.SR guidance, dimensional-analysis units, y_weights, candidate_wrapper, config0\u002Fconfig0b, CPU\u002Fparallel notes, logs, or a safe quick-start smoke.",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fphyso\u002Fsub-skills\u002Fsr",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 sr",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill sr",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill sr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphyso\u002Fsub-skills\u002Fsr\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fconfigurations.md","REFERENCE","参考文档",5530,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphyso\u002Fsub-skills\u002Fsr\u002Freferences\u002Fconfigurations.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",6786,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphyso\u002Fsub-skills\u002Fsr\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",6476,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphyso\u002Fsub-skills\u002Fsr\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fsmoke_sr_quick_start.py","SCRIPT","脚本",3587,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphyso\u002Fsub-skills\u002Fsr\u002Fscripts\u002Fsmoke_sr_quick_start.py",[68,76,83,90,97,104],{"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":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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",[],[]]