[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7984B28178FRF567NACXVST":3,"skill-same:01M7984B28178FRF567NACXVST":54},{"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},"01M7984B28178FRF567NACXVST","toxigen_classifier_recovery",null,"Run a bounded ToxiGen-style classifier update and report validator-compatible before-after loss, AUC, and parameter evidence.","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\u002Ftoxigen_toxicity_evaluation\u002Ftoxigen_classifier_recovery\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: toxigen_classifier_recovery\ndescription: Run a bounded ToxiGen-style classifier update and report validator-compatible before-after loss, AUC, and parameter evidence.\n---\n\n# ToxiGen Classifier Recovery\n\nUse this skill when a recovery experiment needs to demonstrate the paper's classifier-improvement mechanism without full HateBERT or RoBERTa fine-tuning. It trains a tiny logistic classifier over deterministic text features and emits before\u002Fafter metrics.\n\nDo not use this skill to claim full paper Table 4 reproduction. A result from this skill is a reduced proxy unless it is replaced by a real model fine-tuning stack.\n\n## Inputs\n\n- Generated or curated examples with `text` and `label`.\n- Optional group and generation method metadata.\n- Learning rate and update-step count.\n\n## Outputs\n\n- `loss_before`, `loss_after`, `auc_before`, `auc_after`.\n- `params_before`, `params_after`, and `optimizer_state_changed`.\n- Per-example probabilities before and after the update.\n\n## Workflow\n\n1. Extract deterministic features from each text: bias\u002Ftoxicity cue count, benign cue count, identity cue count, and normalized length.\n2. Initialize logistic weights and bias to zero unless supplied.\n3. Compute binary cross-entropy and pairwise AUC.\n4. Run bounded gradient-descent updates.\n5. Recompute metrics and emit a trace with parameter-change evidence.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fclassifier_recovery.py --self-test\npython tests\u002Ftest_classifier_recovery.py\n```\n\nThe tests verify that parameters change and that loss does not increase on a simple fixture.\n\n## Limitations\n\nThis skill is intentionally small and deterministic. It is useful for mechanism-faithful soft recovery, edge-case tests, and harness validation, not for reporting deployed toxicity classifier performance.\n","# ToxiGen Classifier Recovery\n\nUse this skill when a recovery experiment needs to demonstrate the paper's classifier-improvement mechanism without full HateBERT or RoBERTa fine-tuning. It trains a tiny logistic classifier over deterministic text features and emits before\u002Fafter metrics.\n\nDo not use this skill to claim full paper Table 4 reproduction. A result from this skill is a reduced proxy unless it is replaced by a real model fine-tuning stack.\n\n## Inputs\n\n- Generated or curated examples with `text` and `label`.\n- Optional group and generation method metadata.\n- Learning rate and update-step count.\n\n## Outputs\n\n- `loss_before`, `loss_after`, `auc_before`, `auc_after`.\n- `params_before`, `params_after`, and `optimizer_state_changed`.\n- Per-example probabilities before and after the update.\n\n## Workflow\n\n1. Extract deterministic features from each text: bias\u002Ftoxicity cue count, benign cue count, identity cue count, and normalized length.\n2. Initialize logistic weights and bias to zero unless supplied.\n3. Compute binary cross-entropy and pairwise AUC.\n4. Run bounded gradient-descent updates.\n5. Recompute metrics and emit a trace with parameter-change evidence.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fclassifier_recovery.py --self-test\npython tests\u002Ftest_classifier_recovery.py\n```\n\nThe tests verify that parameters change and that loss does not increase on a simple fixture.\n\n## Limitations\n\nThis skill is intentionally small and deterministic. It is useful for mechanism-faithful soft recovery, edge-case tests, and harness validation, not for reporting deployed toxicity classifier performance.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Ftoxigen_toxicity_evaluation\u002Ftoxigen_classifier_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 toxigen_classifier_recovery",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill toxigen_classifier_recovery",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill toxigen_classifier_recovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Ftoxigen_toxicity_evaluation\u002Ftoxigen_classifier_recovery\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fclassifier_recovery.py","SCRIPT","脚本",6528,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Ftoxigen_toxicity_evaluation\u002Ftoxigen_classifier_recovery\u002Fscripts\u002Fclassifier_recovery.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_classifier_recovery.py",1290,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Ftoxigen_toxicity_evaluation\u002Ftoxigen_classifier_recovery\u002Ftests\u002Ftest_classifier_recovery.py",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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",[],[]]