[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792PYGPQD1VR60ZDBY6D1GA":3,"skill-same:01M792PYGPQD1VR60ZDBY6D1GA":67},{"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},"01M792PYGPQD1VR60ZDBY6D1GA","diffusion-and-generative",null,"Use PhysicsNeMo diffusion APIs and generative-domain workflows without assuming bundled weights or data.","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\u002Fphysicsnemo\u002Fsub-skills\u002Fdiffusion-and-generative\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: diffusion-and-generative\ndescription: \"Use PhysicsNeMo diffusion APIs and generative-domain workflows\n  without assuming bundled weights or data.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# PhysicsNeMo Diffusion and Generative Workflows\n\nUse this sub-skill when the user asks about PhysicsNeMo diffusion models, denoisers, predictors, preconditioners, noise schedulers, samplers, guidance, multi-diffusion\u002Fpatching, CorrDiff\u002FStormCast-style weather diffusion, CFD flow reconstruction diffusion, full-waveform inversion diffusion, TopoDiff, SongUNet, DhariwalUNet, StormCastUNet, DiT, or diffusion-specific losses.\n\n## First decide: API building block or full example workflow?\n\n- **API building block**: the user needs imports, signatures, a minimal adapter, a custom scheduler\u002Fsolver, a tiny sampler smoke, or a loss\u002Fpreconditioner explanation. Read `references\u002Fapi-reference.md` and run `scripts\u002Fdiffusion_api_smoke.py` if an environment check is useful.\n- **Full domain workflow**: the user needs to train\u002Fgenerate with weather, CFD, geophysics, or topology-optimization examples. Read `references\u002Fdiffusion-workflows.md` first, then route data preparation to `..\u002Fdatapipes\u002FSKILL.md`, model-family ambiguity to `..\u002Fmodel-selection\u002FSKILL.md`, and multi-GPU\u002Fdomain-parallel scaling to `..\u002Fdistributed-and-domain-parallel\u002FSKILL.md`.\n- **Failure diagnosis**: if the issue includes missing checkpoints, data paths, shape\u002Fchannel mismatches, sigma\u002Fscheduler settings, patch fusion, guidance gradients, CUDA\u002FFP16, or domain-parallel behavior, read `references\u002Ftroubleshooting.md` before changing code.\n\n## Quick workflow\n\n1. Clarify the task target: training loss, sampling\u002Finference, conditioning\u002Fguidance, patching, or a domain recipe.\n2. State explicitly whether the user has the required **trained weights\u002Fcheckpoints**, **datasets\u002Fstatistics**, and **example-specific optional dependencies**. PhysicsNeMo does not bundle pretrained domain weights or external datasets with this generated skill.\n3. For core API work, assemble the pipeline in this order: `DiffusionModel`\u002Fadapter -> optional preconditioner -> noise scheduler -> loss for training, or predictor -> scheduler `get_denoiser` -> solver\u002Fsample for inference.\n4. For domain workflows, separate safe API smokes from real training\u002Fgeneration. Real CorrDiff, StormCast, CFD, FWI, and TopoDiff runs require user-provided data, checkpoints or long training, and usually CUDA.\n5. For large spatial domains, choose between patch-based multi-diffusion and domain parallelism. Use multi-diffusion for patching a 2D field inside the diffusion stack; route `ShardTensor` and launch details to `..\u002Fdistributed-and-domain-parallel\u002FSKILL.md`.\n6. Prefer tiny local validation before expensive work: run `python scripts\u002Fdiffusion_api_smoke.py --tiny-sampling` from this sub-skill directory, then only run user-authorized full workflow commands after the required data, checkpoints, dependencies, and backend are confirmed.\n\n## Do not do these by default\n\n- Do not imply pretrained weights, CorrDiff\u002FStormCast\u002FTopoDiff datasets, NGC resources, Figshare files, Dropbox files, or FWI data are bundled.\n- Do not run training, dataset downloads, external authentication, model checkpoint downloads, or multi-hour generation as a smoke test.\n- Do not treat source repository examples or tests as runtime dependencies. This sub-skill distills their behavior into bundled references and a safe script.\n- Do not use `torch.inference_mode()` around DPS-style guidance that needs gradients; use the troubleshooting reference for the safe autograd pattern.\n","# PhysicsNeMo Diffusion and Generative Workflows\n\nUse this sub-skill when the user asks about PhysicsNeMo diffusion models, denoisers, predictors, preconditioners, noise schedulers, samplers, guidance, multi-diffusion\u002Fpatching, CorrDiff\u002FStormCast-style weather diffusion, CFD flow reconstruction diffusion, full-waveform inversion diffusion, TopoDiff, SongUNet, DhariwalUNet, StormCastUNet, DiT, or diffusion-specific losses.\n\n## First decide: API building block or full example workflow?\n\n- **API building block**: the user needs imports, signatures, a minimal adapter, a custom scheduler\u002Fsolver, a tiny sampler smoke, or a loss\u002Fpreconditioner explanation. Read `references\u002Fapi-reference.md` and run `scripts\u002Fdiffusion_api_smoke.py` if an environment check is useful.\n- **Full domain workflow**: the user needs to train\u002Fgenerate with weather, CFD, geophysics, or topology-optimization examples. Read `references\u002Fdiffusion-workflows.md` first, then route data preparation to `..\u002Fdatapipes\u002FSKILL.md`, model-family ambiguity to `..\u002Fmodel-selection\u002FSKILL.md`, and multi-GPU\u002Fdomain-parallel scaling to `..\u002Fdistributed-and-domain-parallel\u002FSKILL.md`.\n- **Failure diagnosis**: if the issue includes missing checkpoints, data paths, shape\u002Fchannel mismatches, sigma\u002Fscheduler settings, patch fusion, guidance gradients, CUDA\u002FFP16, or domain-parallel behavior, read `references\u002Ftroubleshooting.md` before changing code.\n\n## Quick workflow\n\n1. Clarify the task target: training loss, sampling\u002Finference, conditioning\u002Fguidance, patching, or a domain recipe.\n2. State explicitly whether the user has the required **trained weights\u002Fcheckpoints**, **datasets\u002Fstatistics**, and **example-specific optional dependencies**. PhysicsNeMo does not bundle pretrained domain weights or external datasets with this generated skill.\n3. For core API work, assemble the pipeline in this order: `DiffusionModel`\u002Fadapter -> optional preconditioner -> noise scheduler -> loss for training, or predictor -> scheduler `get_denoiser` -> solver\u002Fsample for inference.\n4. For domain workflows, separate safe API smokes from real training\u002Fgeneration. Real CorrDiff, StormCast, CFD, FWI, and TopoDiff runs require user-provided data, checkpoints or long training, and usually CUDA.\n5. For large spatial domains, choose between patch-based multi-diffusion and domain parallelism. Use multi-diffusion for patching a 2D field inside the diffusion stack; route `ShardTensor` and launch details to `..\u002Fdistributed-and-domain-parallel\u002FSKILL.md`.\n6. Prefer tiny local validation before expensive work: run `python scripts\u002Fdiffusion_api_smoke.py --tiny-sampling` from this sub-skill directory, then only run user-authorized full workflow commands after the required data, checkpoints, dependencies, and backend are confirmed.\n\n## Do not do these by default\n\n- Do not imply pretrained weights, CorrDiff\u002FStormCast\u002FTopoDiff datasets, NGC resources, Figshare files, Dropbox files, or FWI data are bundled.\n- Do not run training, dataset downloads, external authentication, model checkpoint downloads, or multi-hour generation as a smoke test.\n- Do not treat source repository examples or tests as runtime dependencies. This sub-skill distills their behavior into bundled references and a safe script.\n- Do not use `torch.inference_mode()` around DPS-style guidance that needs gradients; use the troubleshooting reference for the safe autograd pattern.\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\u002Fphysicsnemo\u002Fsub-skills\u002Fdiffusion-and-generative",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 diffusion-and-generative",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill diffusion-and-generative",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill diffusion-and-generative","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphysicsnemo\u002Fsub-skills\u002Fdiffusion-and-generative\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",1426,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphysicsnemo\u002Fsub-skills\u002Fdiffusion-and-generative\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdiffusion-workflows.md",1316,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphysicsnemo\u002Fsub-skills\u002Fdiffusion-and-generative\u002Freferences\u002Fdiffusion-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",1519,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphysicsnemo\u002Fsub-skills\u002Fdiffusion-and-generative\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fdiffusion_api_smoke.py","SCRIPT","脚本",2182,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fphysicsnemo\u002Fsub-skills\u002Fdiffusion-and-generative\u002Fscripts\u002Fdiffusion_api_smoke.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]