[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z6H3QWMHX5AFVB5V83V6S":3,"skill-same:01M78Z6H3QWMHX5AFVB5V83V6S":253},{"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},"01M78Z6H3QWMHX5AFVB5V83V6S","office-benchmarks",null,"Routes LibMTL's Office-31 and Office-Home multi-input classification 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\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: office-benchmarks\ndescription: \"Routes LibMTL's Office-31 and Office-Home multi-input\n  classification workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# office-benchmarks\n\nUse this sub-skill for the Office-31 and Office-Home benchmark workflows.\n\n## Covers\n\n- Office-31 multi-input classification.\n- Office-Home multi-input classification.\n- The bundled office split layout and dataloader recipe.\n- A self-contained Office runtime package under `scripts\u002Foffice_runtime\u002F`.\n- An unpackaged launcher at `scripts\u002Fmain.py` plus the install entry point\n  `scripts\u002Finstall_office_runtime.py`.\n- ResNet-18 based encoders and task-specific linear decoders.\n\n## Does not cover\n\n- NYUv2 or Cityscapes dense prediction.\n- QM9 graph regression.\n- PAWS-X multilingual text classification.\n- Core API or custom method development unless the question is specifically\n  about the office benchmark wiring.\n\n## When to use this sub-skill\n\nChoose this route when the user asks things like:\n\n- \"How do I train Office-31?\"\n- \"What is the Office-Home layout?\"\n- \"Why must `multi_input` be true here?\"\n- \"How do the office dataloaders map tasks to domains?\"\n- \"How do I validate the split files?\"\n\n## Read next\n\n- `..\u002F..\u002Freferences\u002Fconfiguration.md` for the shared flags and method kwargs.\n- `..\u002F..\u002Freferences\u002Ftroubleshooting.md` for cross-cutting install and runtime\n  failures.\n- `references\u002Fworkflows.md` for the command pattern.\n- `references\u002Ftask-contracts.md` for the task dictionary, loader, and\n  encoder\u002Fdecoder shapes.\n- `references\u002Fdata-layouts.md` for the expected split and image trees.\n- `references\u002Ftroubleshooting.md` for office-specific failures.\n\n## Workflow\n\n1. Confirm the dataset family: `office-31` or `office-home`.\n2. Confirm that the user expects multi-input classification.\n3. Validate the split text files and the image root.\n4. Run `scripts\u002Fcheck_office_data.py` to confirm the bundled split files and\n   image root before training.\n5. Install the self-contained runtime package with\n   `scripts\u002Finstall_office_runtime.py` when you need the console entry point.\n6. Launch the benchmark through `scripts\u002Fmain.py` or the installed\n   `libmtl-office` entry point, not through an external checkout.\n7. Allow the pretrained `resnet18` backbone to download or use cache.\n\n## Critical constraints\n\n- `multi_input` must be `True`.\n- The bundled runtime builds one dataloader per domain\u002Ftask from its own split\n  files.\n- The task list depends on the dataset family:\n  - Office-31: `amazon`, `dslr`, `webcam`\n  - Office-Home: `Art`, `Clipart`, `Product`, `Real_World`\n\n## Exit criteria\n\nLeave this sub-skill when the user has the correct dataset family, split files,\nrun command, and failure-recovery notes for the office benchmark.\n","# office-benchmarks\n\nUse this sub-skill for the Office-31 and Office-Home benchmark workflows.\n\n## Covers\n\n- Office-31 multi-input classification.\n- Office-Home multi-input classification.\n- The bundled office split layout and dataloader recipe.\n- A self-contained Office runtime package under `scripts\u002Foffice_runtime\u002F`.\n- An unpackaged launcher at `scripts\u002Fmain.py` plus the install entry point\n  `scripts\u002Finstall_office_runtime.py`.\n- ResNet-18 based encoders and task-specific linear decoders.\n\n## Does not cover\n\n- NYUv2 or Cityscapes dense prediction.\n- QM9 graph regression.\n- PAWS-X multilingual text classification.\n- Core API or custom method development unless the question is specifically\n  about the office benchmark wiring.\n\n## When to use this sub-skill\n\nChoose this route when the user asks things like:\n\n- \"How do I train Office-31?\"\n- \"What is the Office-Home layout?\"\n- \"Why must `multi_input` be true here?\"\n- \"How do the office dataloaders map tasks to domains?\"\n- \"How do I validate the split files?\"\n\n## Read next\n\n- `..\u002F..\u002Freferences\u002Fconfiguration.md` for the shared flags and method kwargs.\n- `..\u002F..\u002Freferences\u002Ftroubleshooting.md` for cross-cutting install and runtime\n  failures.\n- `references\u002Fworkflows.md` for the command pattern.\n- `references\u002Ftask-contracts.md` for the task dictionary, loader, and\n  encoder\u002Fdecoder shapes.\n- `references\u002Fdata-layouts.md` for the expected split and image trees.\n- `references\u002Ftroubleshooting.md` for office-specific failures.\n\n## Workflow\n\n1. Confirm the dataset family: `office-31` or `office-home`.\n2. Confirm that the user expects multi-input classification.\n3. Validate the split text files and the image root.\n4. Run `scripts\u002Fcheck_office_data.py` to confirm the bundled split files and\n   image root before training.\n5. Install the self-contained runtime package with\n   `scripts\u002Finstall_office_runtime.py` when you need the console entry point.\n6. Launch the benchmark through `scripts\u002Fmain.py` or the installed\n   `libmtl-office` entry point, not through an external checkout.\n7. Allow the pretrained `resnet18` backbone to download or use cache.\n\n## Critical constraints\n\n- `multi_input` must be `True`.\n- The bundled runtime builds one dataloader per domain\u002Ftask from its own split\n  files.\n- The task list depends on the dataset family:\n  - Office-31: `amazon`, `dslr`, `webcam`\n  - Office-Home: `Art`, `Clipart`, `Product`, `Real_World`\n\n## Exit criteria\n\nLeave this sub-skill when the user has the correct dataset family, split files,\nrun command, and failure-recovery notes for the office benchmark.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks",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 office-benchmarks",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill office-benchmarks",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill office-benchmarks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002FSKILL.md",[46,52,56,60,64,68,72,76,80,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148,154,158,162,166,170,174,178,182,186,189,192,195,198,201,204,207,210,213,216,219,222,225,228,231,234,237,240,243,246,249],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdata_txt\u002Foffice-31\u002Famazon_test.txt","REFERENCE","参考文档",24303,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-31\u002Famazon_test.txt",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdata_txt\u002Foffice-31\u002Famazon_train.txt",69795,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-31\u002Famazon_train.txt",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fdata_txt\u002Foffice-31\u002Famazon_val.txt",22938,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-31\u002Famazon_val.txt",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fdata_txt\u002Foffice-31\u002Fdslr_test.txt",4843,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-31\u002Fdslr_test.txt",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fdata_txt\u002Foffice-31\u002Fdslr_train.txt",11445,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-31\u002Fdslr_train.txt",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fdata_txt\u002Foffice-31\u002Fdslr_val.txt",3551,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-31\u002Fdslr_val.txt",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fdata_txt\u002Foffice-31\u002Fwebcam_test.txt",7489,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-31\u002Fwebcam_test.txt",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fdata_txt\u002Foffice-31\u002Fwebcam_train.txt",19373,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-31\u002Fwebcam_train.txt",{"path":81,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fdata_txt\u002Foffice-31\u002Fwebcam_val.txt",6193,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-31\u002Fwebcam_val.txt",{"path":85,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fdata_txt\u002Foffice-home\u002FArt_test.txt",12945,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FArt_test.txt",{"path":89,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fdata_txt\u002Foffice-home\u002FArt_train.txt",35145,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FArt_train.txt",{"path":93,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fdata_txt\u002Foffice-home\u002FArt_val.txt",11374,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FArt_val.txt",{"path":97,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fdata_txt\u002Foffice-home\u002FClipart_test.txt",26099,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FClipart_test.txt",{"path":101,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fdata_txt\u002Foffice-home\u002FClipart_train.txt",73418,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FClipart_train.txt",{"path":105,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fdata_txt\u002Foffice-home\u002FClipart_val.txt",23931,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FClipart_val.txt",{"path":109,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fdata_txt\u002Foffice-home\u002FProduct_test.txt",27071,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FProduct_test.txt",{"path":113,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fdata_txt\u002Foffice-home\u002FProduct_train.txt",75560,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FProduct_train.txt",{"path":117,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Fdata_txt\u002Foffice-home\u002FProduct_val.txt",24654,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FProduct_val.txt",{"path":121,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Fdata_txt\u002Foffice-home\u002FReal_World_test.txt",29329,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FReal_World_test.txt",{"path":125,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fdata_txt\u002Foffice-home\u002FReal_World_train.txt",82029,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FReal_World_train.txt",{"path":129,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Fdata_txt\u002Foffice-home\u002FReal_World_val.txt",26840,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata_txt\u002Foffice-home\u002FReal_World_val.txt",{"path":133,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Fdata-layouts.md",1134,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fdata-layouts.md",{"path":137,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Ftask-contracts.md",1366,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Ftask-contracts.md",{"path":141,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":142,"sourceHtmlUrl":143},"references\u002Ftroubleshooting.md",1613,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Ftroubleshooting.md",{"path":145,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":146,"sourceHtmlUrl":147},"references\u002Fworkflows.md",3579,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Freferences\u002Fworkflows.md",{"path":149,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":152,"sourceHtmlUrl":153},"scripts\u002Fcheck_office_data.py","SCRIPT","脚本",3122,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Fcheck_office_data.py",{"path":155,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":156,"sourceHtmlUrl":157},"scripts\u002Finstall_office_runtime.py",2033,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Finstall_office_runtime.py",{"path":159,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":160,"sourceHtmlUrl":161},"scripts\u002Fmain.py",592,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Fmain.py",{"path":163,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":164,"sourceHtmlUrl":165},"scripts\u002Foffice_runtime\u002Fmain.py",538,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fmain.py",{"path":167,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":168,"sourceHtmlUrl":169},"scripts\u002Foffice_runtime\u002FMANIFEST.in",61,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002FMANIFEST.in",{"path":171,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":172,"sourceHtmlUrl":173},"scripts\u002Foffice_runtime\u002Fpyproject.toml",601,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fpyproject.toml",{"path":175,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":176,"sourceHtmlUrl":177},"scripts\u002Foffice_runtime\u002FREADME.md",621,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002FREADME.md",{"path":179,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":180,"sourceHtmlUrl":181},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002F__init__.py",191,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002F__init__.py",{"path":183,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":184,"sourceHtmlUrl":185},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fcreate_dataset.py",2624,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fcreate_dataset.py",{"path":187,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":50,"sourceHtmlUrl":188},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Famazon_test.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Famazon_test.txt",{"path":190,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":54,"sourceHtmlUrl":191},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Famazon_train.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Famazon_train.txt",{"path":193,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":58,"sourceHtmlUrl":194},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Famazon_val.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Famazon_val.txt",{"path":196,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":62,"sourceHtmlUrl":197},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fdslr_test.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fdslr_test.txt",{"path":199,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":66,"sourceHtmlUrl":200},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fdslr_train.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fdslr_train.txt",{"path":202,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":70,"sourceHtmlUrl":203},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fdslr_val.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fdslr_val.txt",{"path":205,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":74,"sourceHtmlUrl":206},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fwebcam_test.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fwebcam_test.txt",{"path":208,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":78,"sourceHtmlUrl":209},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fwebcam_train.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fwebcam_train.txt",{"path":211,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":82,"sourceHtmlUrl":212},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fwebcam_val.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-31\u002Fwebcam_val.txt",{"path":214,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":86,"sourceHtmlUrl":215},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FArt_test.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FArt_test.txt",{"path":217,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":90,"sourceHtmlUrl":218},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FArt_train.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FArt_train.txt",{"path":220,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":94,"sourceHtmlUrl":221},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FArt_val.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FArt_val.txt",{"path":223,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":98,"sourceHtmlUrl":224},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FClipart_test.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FClipart_test.txt",{"path":226,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":102,"sourceHtmlUrl":227},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FClipart_train.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FClipart_train.txt",{"path":229,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":106,"sourceHtmlUrl":230},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FClipart_val.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FClipart_val.txt",{"path":232,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":110,"sourceHtmlUrl":233},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FProduct_test.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FProduct_test.txt",{"path":235,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":114,"sourceHtmlUrl":236},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FProduct_train.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FProduct_train.txt",{"path":238,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":118,"sourceHtmlUrl":239},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FProduct_val.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FProduct_val.txt",{"path":241,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":122,"sourceHtmlUrl":242},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FReal_World_test.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FReal_World_test.txt",{"path":244,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":126,"sourceHtmlUrl":245},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FReal_World_train.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FReal_World_train.txt",{"path":247,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":130,"sourceHtmlUrl":248},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FReal_World_val.txt","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fdata_txt\u002Foffice-home\u002FReal_World_val.txt",{"path":250,"resourceType":150,"resourceTypeDesc":151,"sizeBytes":251,"sourceHtmlUrl":252},"scripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fmain.py",4222,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flibmtl\u002Fsub-skills\u002Foffice-benchmarks\u002Fscripts\u002Foffice_runtime\u002Fsrc\u002Flibmtl_office_benchmark\u002Fmain.py",[254,262,269,276,283,290],{"skillNo":255,"name":256,"nameZh":6,"description":257,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":258,"licenseFileUrl":6,"sourceHtmlUrl":259,"categories":260,"keywords":261,"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":263,"name":264,"nameZh":6,"description":265,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":258,"licenseFileUrl":6,"sourceHtmlUrl":266,"categories":267,"keywords":268,"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":270,"name":271,"nameZh":6,"description":272,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":258,"licenseFileUrl":6,"sourceHtmlUrl":273,"categories":274,"keywords":275,"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":277,"name":278,"nameZh":6,"description":279,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":258,"licenseFileUrl":6,"sourceHtmlUrl":280,"categories":281,"keywords":282,"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":284,"name":285,"nameZh":6,"description":286,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":258,"licenseFileUrl":6,"sourceHtmlUrl":287,"categories":288,"keywords":289,"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":291,"name":292,"nameZh":6,"description":293,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":258,"licenseFileUrl":6,"sourceHtmlUrl":294,"categories":295,"keywords":296,"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",[],[]]