[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792CMAVYRBFX36ZWVRF2J7K":3,"skill-same:01M792CMAVYRBFX36ZWVRF2J7K":79},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M792CMAVYRBFX36ZWVRF2J7K","paddlevit",null,"Guide PaddleViT computer-vision workflows for transformer and MLP image classification, object detection, semantic segmentation, DINO self-supervision, GANs, configuration, distributed\u002FAMP execution, and Paddle deployment with explicit data, backend, and checkpoint boundaries.","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\u002Frepositories\u002Frepo-skills\u002Fpaddlevit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: paddlevit\ndescription: \"Guide PaddleViT computer-vision workflows for transformer and MLP\n  image classification, object detection, semantic segmentation, DINO\n  self-supervision, GANs, configuration, distributed\u002FAMP execution, and Paddle\n  deployment with explicit data, backend, and checkpoint boundaries.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# PaddleViT\n\nUse this skill when a task names PaddleViT\u002FPPViT, its standalone model\nfolders, PaddlePaddle vision transformers, or a workflow that matches one of\nits classification, detection, segmentation, self-supervised, GAN, or export\nsurfaces. PaddleViT is a collection of source-rooted projects, not one\ninstallable Python package: each model folder commonly has its own `config.py`,\nmodel module, dataset code, and entry script.\n\n## Start with a bounded plan\n\nBefore writing a command, record:\n\n1. task family and exact model directory;\n2. operation: inspect, configure, train, evaluate, predict, export, or port;\n3. YAML config, recursive `BASE` files, data root\u002Fsplit, checkpoint prefix, and\n   output directory;\n4. expected device (`cpu`, one CUDA device, or distributed CUDA), budget, and\n   whether downloads or long training are permitted;\n5. preprocessing (channel order, resize\u002Fcrop, normalization) and expected\n   output shape\u002Fmetric.\n\nRun the read-only environment probe before attributing failures to a model:\n\n```bash\npython scripts\u002Fcheck_paddlevit_environment.py --help\npython scripts\u002Fcheck_paddlevit_environment.py --json\n```\n\nInstall PaddlePaddle using the official wheel that matches the host and CUDA\nruntime. The repository documents PaddlePaddle 2.1-era APIs; current releases\nmay need a per-model smoke or a small compatibility patch. Add `yacs` and\n`pyyaml` for the shared configuration pattern. Segmentation additionally uses\nOpenCV, SciPy, and `cityscapesScripts`; COCO detection uses `pycocotools`; GAN\nLSUN workflows use `lmdb`. Do not install every optional dependency or download\nweights\u002Fdata merely to inspect a config.\n\n## Route by user intent\n\n- [Classification](sub-skills\u002Fclassification\u002FSKILL.md): ViT, DeiT, Swin,\n  VOLO, CSwin, PVTv2, BEiT, mobile\u002FMLP\u002FConv\u002FRep families, MAE fine-tuning,\n  ImageNet-style data, and facial-expression Swin.\n- [Detection](sub-skills\u002Fdetection\u002FSKILL.md): DETR, Swin\u002FPVTv2 detection,\n  COCO layout, transforms, matching, RPN\u002FRoI\u002FFPN, train\u002Feval and post-process.\n- [Segmentation](sub-skills\u002Fsegmentation\u002FSKILL.md): SETR, UperNet, DPT,\n  Segmenter, Trans2Seg, SegFormer, TopFormer, dataset layouts, demo and mIoU\n  validation.\n- [Self-supervised](sub-skills\u002Fself-supervised\u002FSKILL.md): DINO multi-crop\n  teacher\u002Fstudent training, checkpoint\u002Fresume, AMP and multi-GPU boundaries.\n- [Generative](sub-skills\u002Fgenerative\u002FSKILL.md): TransGAN, Styleformer,\n  CIFAR\u002FSTL10\u002FCelebA\u002FLSUN-LMDB data and FID\u002FPSNR\u002FSSIM evaluation.\n- [Deployment and operations](sub-skills\u002Fdeployment-and-operations\u002FSKILL.md):\n  config precedence, environment diagnosis, AMP\u002Fdistributed launch, static\n  export, Paddle Inference, prediction, quantization and optional weight port.\n\nRead [model-catalog.md](references\u002Fmodel-catalog.md) when a request does not\nname a model family. Read [configuration.md](references\u002Fconfiguration.md) when\nYAML, CLI overrides, source-root imports, or checkpoint paths are involved.\nRead [troubleshooting.md](references\u002Ftroubleshooting.md) before retrying an\nimport, backend, data, export, or checkpoint failure.\n\n## Source-root discipline\n\nRun one family in one fresh process. Put only the selected model directory (and\nits documented sibling utilities) on `PYTHONPATH`; many folders contain bare\nmodules named `config`, `datasets`, `utils`, or `models`. Never combine several\nmodel directories in one interpreter and assume imports are unambiguous.\nGenerated helper scripts are source-independent and must not be used as proof\nthat a source model's current API is compatible.\n\n## Evidence and safety gates\n\nA config parse, dependency import, or tiny CPU forward does not prove CUDA,\nAMP, distributed, dataset, checkpoint, or benchmark behavior. For GPU claims,\nrun a tiny operation on the requested CUDA device. For a real metric, require a\nreal compatible split and checkpoint. Treat training, multi-scale\u002Fslide\nsegmentation, COCO evaluation, DINO ImageNet pretraining, GAN FID, multi-GPU\nlaunch, export, quantization, and cross-framework porting as explicit\noperations with an approved output path and stop condition.\n\nDo not overwrite checkpoints, delete demo output trees, mutate a dataset, or\nfetch external weights\u002Fdata without explicit authorization. Prefer a new output\nprefix and read-only preflight. Record the source commit and effective config\nin any downstream experiment handoff; consult\n[repo-provenance.md](references\u002Frepo-provenance.md) before deciding whether a\ncheckout is stale.\n","# PaddleViT\n\nUse this skill when a task names PaddleViT\u002FPPViT, its standalone model\nfolders, PaddlePaddle vision transformers, or a workflow that matches one of\nits classification, detection, segmentation, self-supervised, GAN, or export\nsurfaces. PaddleViT is a collection of source-rooted projects, not one\ninstallable Python package: each model folder commonly has its own `config.py`,\nmodel module, dataset code, and entry script.\n\n## Start with a bounded plan\n\nBefore writing a command, record:\n\n1. task family and exact model directory;\n2. operation: inspect, configure, train, evaluate, predict, export, or port;\n3. YAML config, recursive `BASE` files, data root\u002Fsplit, checkpoint prefix, and\n   output directory;\n4. expected device (`cpu`, one CUDA device, or distributed CUDA), budget, and\n   whether downloads or long training are permitted;\n5. preprocessing (channel order, resize\u002Fcrop, normalization) and expected\n   output shape\u002Fmetric.\n\nRun the read-only environment probe before attributing failures to a model:\n\n```bash\npython scripts\u002Fcheck_paddlevit_environment.py --help\npython scripts\u002Fcheck_paddlevit_environment.py --json\n```\n\nInstall PaddlePaddle using the official wheel that matches the host and CUDA\nruntime. The repository documents PaddlePaddle 2.1-era APIs; current releases\nmay need a per-model smoke or a small compatibility patch. Add `yacs` and\n`pyyaml` for the shared configuration pattern. Segmentation additionally uses\nOpenCV, SciPy, and `cityscapesScripts`; COCO detection uses `pycocotools`; GAN\nLSUN workflows use `lmdb`. Do not install every optional dependency or download\nweights\u002Fdata merely to inspect a config.\n\n## Route by user intent\n\n- [Classification](sub-skills\u002Fclassification\u002FSKILL.md): ViT, DeiT, Swin,\n  VOLO, CSwin, PVTv2, BEiT, mobile\u002FMLP\u002FConv\u002FRep families, MAE fine-tuning,\n  ImageNet-style data, and facial-expression Swin.\n- [Detection](sub-skills\u002Fdetection\u002FSKILL.md): DETR, Swin\u002FPVTv2 detection,\n  COCO layout, transforms, matching, RPN\u002FRoI\u002FFPN, train\u002Feval and post-process.\n- [Segmentation](sub-skills\u002Fsegmentation\u002FSKILL.md): SETR, UperNet, DPT,\n  Segmenter, Trans2Seg, SegFormer, TopFormer, dataset layouts, demo and mIoU\n  validation.\n- [Self-supervised](sub-skills\u002Fself-supervised\u002FSKILL.md): DINO multi-crop\n  teacher\u002Fstudent training, checkpoint\u002Fresume, AMP and multi-GPU boundaries.\n- [Generative](sub-skills\u002Fgenerative\u002FSKILL.md): TransGAN, Styleformer,\n  CIFAR\u002FSTL10\u002FCelebA\u002FLSUN-LMDB data and FID\u002FPSNR\u002FSSIM evaluation.\n- [Deployment and operations](sub-skills\u002Fdeployment-and-operations\u002FSKILL.md):\n  config precedence, environment diagnosis, AMP\u002Fdistributed launch, static\n  export, Paddle Inference, prediction, quantization and optional weight port.\n\nRead [model-catalog.md](references\u002Fmodel-catalog.md) when a request does not\nname a model family. Read [configuration.md](references\u002Fconfiguration.md) when\nYAML, CLI overrides, source-root imports, or checkpoint paths are involved.\nRead [troubleshooting.md](references\u002Ftroubleshooting.md) before retrying an\nimport, backend, data, export, or checkpoint failure.\n\n## Source-root discipline\n\nRun one family in one fresh process. Put only the selected model directory (and\nits documented sibling utilities) on `PYTHONPATH`; many folders contain bare\nmodules named `config`, `datasets`, `utils`, or `models`. Never combine several\nmodel directories in one interpreter and assume imports are unambiguous.\nGenerated helper scripts are source-independent and must not be used as proof\nthat a source model's current API is compatible.\n\n## Evidence and safety gates\n\nA config parse, dependency import, or tiny CPU forward does not prove CUDA,\nAMP, distributed, dataset, checkpoint, or benchmark behavior. For GPU claims,\nrun a tiny operation on the requested CUDA device. For a real metric, require a\nreal compatible split and checkpoint. Treat training, multi-scale\u002Fslide\nsegmentation, COCO evaluation, DINO ImageNet pretraining, GAN FID, multi-GPU\nlaunch, export, quantization, and cross-framework porting as explicit\noperations with an approved output path and stop condition.\n\nDo not overwrite checkpoints, delete demo output trees, mutate a dataset, or\nfetch external weights\u002Fdata without explicit authorization. Prefer a new output\nprefix and read-only preflight. Record the source commit and effective config\nin any downstream experiment handoff; consult\n[repo-provenance.md](references\u002Frepo-provenance.md) before deciding whether a\ncheckout is stale.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpaddlevit",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill paddlevit",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill paddlevit",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill paddlevit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlevit\u002FSKILL.md",[47,53,57,61,65,69,75],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fconfiguration.md","REFERENCE","参考文档",2915,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlevit\u002Freferences\u002Fconfiguration.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmodel-catalog.md",2794,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlevit\u002Freferences\u002Fmodel-catalog.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-provenance.md",2925,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlevit\u002Freferences\u002Frepo-provenance.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frepo-routing-metadata.json",494,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlevit\u002Freferences\u002Frepo-routing-metadata.json",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",3736,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlevit\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fcheck_paddlevit_environment.py","SCRIPT","脚本",2611,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlevit\u002Fscripts\u002Fcheck_paddlevit_environment.py",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fvalidate_checkpoint_manifest.py",1830,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpaddlevit\u002Fscripts\u002Fvalidate_checkpoint_manifest.py",[80,87,94,101,108,115],{"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},"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":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},"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":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},"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"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":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"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":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"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",[],[]]