[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TF1KDBAWRST0086W4VCAS":3,"skill-same:01M78TF1KDBAWRST0086W4VCAS":66},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78TF1KDBAWRST0086W4VCAS","evaluation",null,"Evaluate and summarize Boltz prediction outputs, benchmark result tables, and legacy OpenStructure-based evaluation workflows.","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\u002Fboltz\u002Fsub-skills\u002Fevaluation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: evaluation\ndescription: \"Evaluate and summarize Boltz prediction outputs, benchmark result\n  tables, and legacy OpenStructure-based evaluation workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Evaluation\n\nUse this sub-skill when the task is to interpret Boltz output metrics, summarize prediction result files, diagnose benchmark\u002Fevaluation folder layout, or reason about legacy CASP\u002FPDB evaluation workflows.\n\n## Start Here\n\n- For local prediction-output summaries, use the bundled script: [`scripts\u002Fboltz_evaluation_summary.py`](scripts\u002Fboltz_evaluation_summary.py).\n- For benchmark reproduction planning, read [`references\u002Fevaluation-workflows.md`](references\u002Fevaluation-workflows.md) before running anything external.\n- For confidence, affinity, structural, ligand, and physical-validity metric meanings, read [`references\u002Fmetrics-and-outputs.md`](references\u002Fmetrics-and-outputs.md).\n- For missing dependencies, unavailable Boltz-2 evaluation assets, folder mismatches, metric mismatches, overlap caveats, and affinity interpretation traps, read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md).\n\n## Routing Boundaries\n\n- Use this sub-skill for: evaluating Boltz outputs, aggregating evaluation CSVs, interpreting affinity\u002Fconfidence metrics, CASP\u002FPDB benchmark layout, OpenStructure requirements, and top-1 versus oracle summaries.\n- Route raw `boltz predict` setup, YAML\u002FFASTA input authoring, MSA server use, model checkpoints, and inference options to the prediction sub-skill.\n- Route training\u002Fevaluation jobs launched through PyTorch Lightning or Hydra training configs to the training sub-skill.\n- Route CCD, MSA, mmCIF preprocessing, dataset split construction, and benchmark input layout preparation to the data-preparation sub-skill.\n\n## Safe Defaults\n\n- Treat Boltz-2 benchmark evaluation files, setup, and scripts as not yet published when using the documented repository state.\n- Treat the available evaluation scripts as legacy Boltz-1 benchmark references unless newer Boltz-2 assets are supplied by the user.\n- Do not claim a local confidence or affinity JSON summary is a reproduced structural benchmark; structural benchmark metrics need targets, aligned benchmark folders, and OpenStructure.\n","# Evaluation\n\nUse this sub-skill when the task is to interpret Boltz output metrics, summarize prediction result files, diagnose benchmark\u002Fevaluation folder layout, or reason about legacy CASP\u002FPDB evaluation workflows.\n\n## Start Here\n\n- For local prediction-output summaries, use the bundled script: [`scripts\u002Fboltz_evaluation_summary.py`](scripts\u002Fboltz_evaluation_summary.py).\n- For benchmark reproduction planning, read [`references\u002Fevaluation-workflows.md`](references\u002Fevaluation-workflows.md) before running anything external.\n- For confidence, affinity, structural, ligand, and physical-validity metric meanings, read [`references\u002Fmetrics-and-outputs.md`](references\u002Fmetrics-and-outputs.md).\n- For missing dependencies, unavailable Boltz-2 evaluation assets, folder mismatches, metric mismatches, overlap caveats, and affinity interpretation traps, read [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md).\n\n## Routing Boundaries\n\n- Use this sub-skill for: evaluating Boltz outputs, aggregating evaluation CSVs, interpreting affinity\u002Fconfidence metrics, CASP\u002FPDB benchmark layout, OpenStructure requirements, and top-1 versus oracle summaries.\n- Route raw `boltz predict` setup, YAML\u002FFASTA input authoring, MSA server use, model checkpoints, and inference options to the prediction sub-skill.\n- Route training\u002Fevaluation jobs launched through PyTorch Lightning or Hydra training configs to the training sub-skill.\n- Route CCD, MSA, mmCIF preprocessing, dataset split construction, and benchmark input layout preparation to the data-preparation sub-skill.\n\n## Safe Defaults\n\n- Treat Boltz-2 benchmark evaluation files, setup, and scripts as not yet published when using the documented repository state.\n- Treat the available evaluation scripts as legacy Boltz-1 benchmark references unless newer Boltz-2 assets are supplied by the user.\n- Do not claim a local confidence or affinity JSON summary is a reproduced structural benchmark; structural benchmark metrics need targets, aligned benchmark folders, and OpenStructure.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fboltz\u002Fsub-skills\u002Fevaluation",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill evaluation",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill evaluation",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill evaluation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fboltz\u002Fsub-skills\u002Fevaluation\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fevaluation-workflows.md","REFERENCE","参考文档",5250,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fboltz\u002Fsub-skills\u002Fevaluation\u002Freferences\u002Fevaluation-workflows.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmetrics-and-outputs.md",5315,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fboltz\u002Fsub-skills\u002Fevaluation\u002Freferences\u002Fmetrics-and-outputs.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4324,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fboltz\u002Fsub-skills\u002Fevaluation\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fboltz_evaluation_summary.py","SCRIPT","脚本",14812,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fboltz\u002Fsub-skills\u002Fevaluation\u002Fscripts\u002Fboltz_evaluation_summary.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]