[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M798PVEVVJNPD4QFMCW4540X":3,"skill-same:01M798PVEVVJNPD4QFMCW4540X":58},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M798PVEVVJNPD4QFMCW4540X","proxy_training_recovery",null,"Run bounded proxy PINN training comparisons that exercise residual construction, NTK weighting, and optimizer updates.","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\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Fntk_pinn_analysis\u002Fproxy_training_recovery\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: proxy_training_recovery\ndescription: Run bounded proxy PINN training comparisons that exercise residual construction, NTK weighting, and optimizer updates.\n---\n\n# Proxy Training Recovery\n\nUse this skill to produce executable recovery evidence for the NTK-PINN paper when full large-scale experiments are blocked or out of scope under soft recovery mode. The skill compares equal weighting with adaptive NTK weighting on a deterministic Poisson-style proxy.\n\n## Inputs\n\n- Problem item from `pinn_residual_problem`.\n- NTK diagnostics from `ntk_block_spectrum`.\n- Adaptive weights from `adaptive_ntk_weighting`.\n- Initial scalar parameters and optimizer settings.\n\n## Outputs\n\n- Training trace with `params_before`, `params_after`, `loss_before`, and `loss_after`.\n- Numeric comparison metric `adaptive_loss_ratio_improvement`.\n- Mechanism checks showing residual loss, boundary loss, NTK traces, adaptive weights, and optimizer updates all ran.\n\n## Workflow\n\n1. Use the problem item to define separated boundary and residual losses.\n2. Use deterministic Jacobians to compute NTK block traces and Algorithm 1 weights.\n3. Run equal-weight and adaptive-weight gradient steps from the same initial parameters.\n4. Measure how close the component-loss ratio is to one after training.\n5. Save logs that downstream Distiller validators can inspect.\n\n## Validation\n\nRun:\n\n```bash\npython tests\u002Ftest_proxy_training.py\n```\n\nThe tests assert parameter updates, numeric losses, and improved adaptive component balance.\n\n## Limitations\n\nThis is a soft-mode proxy and must be declared as such. It is not a full reproduction of all paper figures, but it executes the core mechanism in a bounded way.\n","# Proxy Training Recovery\n\nUse this skill to produce executable recovery evidence for the NTK-PINN paper when full large-scale experiments are blocked or out of scope under soft recovery mode. The skill compares equal weighting with adaptive NTK weighting on a deterministic Poisson-style proxy.\n\n## Inputs\n\n- Problem item from `pinn_residual_problem`.\n- NTK diagnostics from `ntk_block_spectrum`.\n- Adaptive weights from `adaptive_ntk_weighting`.\n- Initial scalar parameters and optimizer settings.\n\n## Outputs\n\n- Training trace with `params_before`, `params_after`, `loss_before`, and `loss_after`.\n- Numeric comparison metric `adaptive_loss_ratio_improvement`.\n- Mechanism checks showing residual loss, boundary loss, NTK traces, adaptive weights, and optimizer updates all ran.\n\n## Workflow\n\n1. Use the problem item to define separated boundary and residual losses.\n2. Use deterministic Jacobians to compute NTK block traces and Algorithm 1 weights.\n3. Run equal-weight and adaptive-weight gradient steps from the same initial parameters.\n4. Measure how close the component-loss ratio is to one after training.\n5. Save logs that downstream Distiller validators can inspect.\n\n## Validation\n\nRun:\n\n```bash\npython tests\u002Ftest_proxy_training.py\n```\n\nThe tests assert parameter updates, numeric losses, and improved adaptive component balance.\n\n## Limitations\n\nThis is a soft-mode proxy and must be declared as such. It is not a full reproduction of all paper figures, but it executes the core mechanism in a bounded way.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Fntk_pinn_analysis\u002Fproxy_training_recovery",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill proxy_training_recovery",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill proxy_training_recovery",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill proxy_training_recovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Fntk_pinn_analysis\u002Fproxy_training_recovery\u002FSKILL.md",true,[44,50,54],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fproxy_train.py","SCRIPT","脚本",3470,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Fntk_pinn_analysis\u002Fproxy_training_recovery\u002Fscripts\u002Fproxy_train.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_learning_rate_stress.py",248,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Fntk_pinn_analysis\u002Fproxy_training_recovery\u002Ftests\u002Ftest_learning_rate_stress.py",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"tests\u002Ftest_proxy_training.py",406,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fpinn\u002Fskill\u002Fntk_pinn_analysis\u002Fproxy_training_recovery\u002Ftests\u002Ftest_proxy_training.py",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"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",[],[]]