[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7987FQ6EQMQB6NRSWE24AYJ":3,"skill-same:01M7987FQ6EQMQB6NRSWE24AYJ":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},"01M7987FQ6EQMQB6NRSWE24AYJ","linear_calibration_ranking",null,"Fit non-negative layer calibration weights for LPIPS-style distances using bounded 2AFC ranking feedback.","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\u002Fbridging-data-gaps\u002Fskill\u002Flpips_perceptual_metric\u002Flinear_calibration_ranking\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: linear_calibration_ranking\ndescription: Fit non-negative layer calibration weights for LPIPS-style distances using bounded 2AFC ranking feedback.\n---\n\n# Linear Calibration Ranking\n\nUse this skill when a recovery or evaluation needs to apply or fit the LPIPS paper's shallow human-judgment calibration over per-layer distances.\n\nDo not use it to train or fine-tune a trunk network. This skill updates only calibration weights.\n\n## Inputs\n\n- Items with `layers0`, `layers1`, and `judge`.\n- `layers0` and `layers1` are equal-length lists of per-layer distances for `ref-p0` and `ref-p1`.\n- `judge = 0` means `p0` should score closer; `judge = 1` means `p1` should score closer.\n- Optional initial weights, step count, and learning rate.\n\n## Outputs\n\n- Non-negative calibrated weights.\n- Loss\u002Faccuracy before and after calibration.\n- `params_before` and `params_after` for recovery validation.\n\n## Workflow\n\n1. Validate layer vectors and labels.\n2. Score each candidate by weighted layer-distance sum.\n3. Compute logistic ranking loss over `score0 - score1`.\n4. Run bounded gradient steps on calibration weights.\n5. Project weights to non-negative values after each step.\n6. Emit a trace with before\u002Fafter loss, accuracy, and weights.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fcalibrate_ranking.py --self-test\npython tests\u002Ftest_calibrate_ranking.py\n```\n\n## Limitations\n\nThe script is intentionally small and deterministic. It is suitable for reduced recovery and unit tests, not full-scale LPIPS training.\n","# Linear Calibration Ranking\n\nUse this skill when a recovery or evaluation needs to apply or fit the LPIPS paper's shallow human-judgment calibration over per-layer distances.\n\nDo not use it to train or fine-tune a trunk network. This skill updates only calibration weights.\n\n## Inputs\n\n- Items with `layers0`, `layers1`, and `judge`.\n- `layers0` and `layers1` are equal-length lists of per-layer distances for `ref-p0` and `ref-p1`.\n- `judge = 0` means `p0` should score closer; `judge = 1` means `p1` should score closer.\n- Optional initial weights, step count, and learning rate.\n\n## Outputs\n\n- Non-negative calibrated weights.\n- Loss\u002Faccuracy before and after calibration.\n- `params_before` and `params_after` for recovery validation.\n\n## Workflow\n\n1. Validate layer vectors and labels.\n2. Score each candidate by weighted layer-distance sum.\n3. Compute logistic ranking loss over `score0 - score1`.\n4. Run bounded gradient steps on calibration weights.\n5. Project weights to non-negative values after each step.\n6. Emit a trace with before\u002Fafter loss, accuracy, and weights.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fcalibrate_ranking.py --self-test\npython tests\u002Ftest_calibrate_ranking.py\n```\n\n## Limitations\n\nThe script is intentionally small and deterministic. It is suitable for reduced recovery and unit tests, not full-scale LPIPS training.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Flpips_perceptual_metric\u002Flinear_calibration_ranking",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 linear_calibration_ranking",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill linear_calibration_ranking",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill linear_calibration_ranking","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Flpips_perceptual_metric\u002Flinear_calibration_ranking\u002FSKILL.md",true,[44,50,54],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fcalibrate_ranking.py","SCRIPT","脚本",4947,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Flpips_perceptual_metric\u002Flinear_calibration_ranking\u002Fscripts\u002Fcalibrate_ranking.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_calibrate_ranking.py",1118,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Flpips_perceptual_metric\u002Flinear_calibration_ranking\u002Ftests\u002Ftest_calibrate_ranking.py",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"tests\u002Ftest_projection_and_trace.py",819,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Flpips_perceptual_metric\u002Flinear_calibration_ranking\u002Ftests\u002Ftest_projection_and_trace.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",[],[]]