[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79833231JVFWP9TD1CJ36AW":3,"skill-same:01M79833231JVFWP9TD1CJ36AW":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},"01M79833231JVFWP9TD1CJ36AW","gsm8k_recovery_evaluation",null,"Run a bounded GSM8K verifier recovery harness with source provenance, generated-skill invocation logs, and solve-rate metrics.","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\u002Fbbox\u002Fskill\u002Fgsm8k_training_verifiers\u002Fgsm8k_recovery_evaluation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gsm8k_recovery_evaluation\ndescription: Run a bounded GSM8K verifier recovery harness with source provenance, generated-skill invocation logs, and solve-rate metrics.\n---\n\n# GSM8K Recovery Evaluation\n\nUse this skill to run the soft-mode recovery experiment for the GSM8K verifier paper. It orchestrates the generated answer, candidate, verifier-training, and verifier-search skills and emits validator-compatible recovery artifacts.\n\nDo not run this skill against the original repository during recovery. Use only the runtime handoff's allowed current-attempt snapshot files.\n\n## Inputs\n\n- Attempt directory with `module_plan.json`.\n- Runtime handoff with allowed snapshot paths.\n- Generated skills root.\n\n## Outputs\n\n- Recovery result with numeric `solve_rate`.\n- Generated data item and training trace.\n- Command and generated-skill invocation logs.\n- Source manifest that excludes the original repository.\n\n## Workflow\n\n1. Read `environment\u002Fruntime_handoff.json`.\n2. Resolve the allowed GSM8K snapshot file.\n3. Generate reduced candidate records.\n4. Train the lightweight verifier and save loss\u002Fparameter trace.\n5. Rank candidates and produce predictions.\n6. Evaluate solve rate.\n7. Write mechanism checks and provenance artifacts.\n\n## Validation\n\nRun the harness and then the Distiller recovery validator:\n\n```bash\npython scripts\u002Frun_recovery.py --attempt-dir \u002Fpath\u002Fto\u002Fattempt --skills-root \u002Fpath\u002Fto\u002Fgenerated_skills\npython \u002Fshare\u002Fproject\u002Fyuyang\u002Fworkspace\u002FPaper2Skills\u002FDistiller\u002Fskills\u002Frecover-paper\u002Fscripts\u002Fvalidate_recovery_experiment.py \u002Fpath\u002Fto\u002Fattempt --output \u002Fpath\u002Fto\u002Fattempt\u002Frecovery\u002Fexperiment_validation.json\n```\n\n## Limitations\n\nThis harness is a reduced proxy when full model checkpoints and GPT-3-family training infrastructure are unavailable. It must keep full-model booleans false and explicitly record reduced training as the accepted soft-mode scope.\n","# GSM8K Recovery Evaluation\n\nUse this skill to run the soft-mode recovery experiment for the GSM8K verifier paper. It orchestrates the generated answer, candidate, verifier-training, and verifier-search skills and emits validator-compatible recovery artifacts.\n\nDo not run this skill against the original repository during recovery. Use only the runtime handoff's allowed current-attempt snapshot files.\n\n## Inputs\n\n- Attempt directory with `module_plan.json`.\n- Runtime handoff with allowed snapshot paths.\n- Generated skills root.\n\n## Outputs\n\n- Recovery result with numeric `solve_rate`.\n- Generated data item and training trace.\n- Command and generated-skill invocation logs.\n- Source manifest that excludes the original repository.\n\n## Workflow\n\n1. Read `environment\u002Fruntime_handoff.json`.\n2. Resolve the allowed GSM8K snapshot file.\n3. Generate reduced candidate records.\n4. Train the lightweight verifier and save loss\u002Fparameter trace.\n5. Rank candidates and produce predictions.\n6. Evaluate solve rate.\n7. Write mechanism checks and provenance artifacts.\n\n## Validation\n\nRun the harness and then the Distiller recovery validator:\n\n```bash\npython scripts\u002Frun_recovery.py --attempt-dir \u002Fpath\u002Fto\u002Fattempt --skills-root \u002Fpath\u002Fto\u002Fgenerated_skills\npython \u002Fshare\u002Fproject\u002Fyuyang\u002Fworkspace\u002FPaper2Skills\u002FDistiller\u002Fskills\u002Frecover-paper\u002Fscripts\u002Fvalidate_recovery_experiment.py \u002Fpath\u002Fto\u002Fattempt --output \u002Fpath\u002Fto\u002Fattempt\u002Frecovery\u002Fexperiment_validation.json\n```\n\n## Limitations\n\nThis harness is a reduced proxy when full model checkpoints and GPT-3-family training infrastructure are unavailable. It must keep full-model booleans false and explicitly record reduced training as the accepted soft-mode scope.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fgsm8k_training_verifiers\u002Fgsm8k_recovery_evaluation",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 gsm8k_recovery_evaluation",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill gsm8k_recovery_evaluation",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill gsm8k_recovery_evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fgsm8k_training_verifiers\u002Fgsm8k_recovery_evaluation\u002FSKILL.md",true,[44,50,54],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fevaluation.py","SCRIPT","脚本",1441,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fgsm8k_training_verifiers\u002Fgsm8k_recovery_evaluation\u002Fscripts\u002Fevaluation.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"scripts\u002Frun_recovery.py",11350,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fgsm8k_training_verifiers\u002Fgsm8k_recovery_evaluation\u002Fscripts\u002Frun_recovery.py",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"tests\u002Ftest_recovery_evaluation.py",642,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fgsm8k_training_verifiers\u002Fgsm8k_recovery_evaluation\u002Ftests\u002Ftest_recovery_evaluation.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",[],[]]