[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794RVBK49C976ZVJ5JP68C8":3,"skill-same:01M794RVBK49C976ZVJ5JP68C8":71},{"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},"01M794RVBK49C976ZVJ5JP68C8","sd-scripts",null,"Use sd-scripts for Stable Diffusion and image-model training, dataset preparation, image generation, LoRA\u002Fmodel utilities, and troubleshooting across SD1\u002F2, SDXL, SD3, FLUX, Lumina, HunyuanImage, and Anima workflows.","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\u002Fsd-scripts\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sd-scripts\ndescription: \"Use sd-scripts for Stable Diffusion and image-model training,\n  dataset preparation, image generation, LoRA\u002Fmodel utilities, and\n  troubleshooting across SD1\u002F2, SDXL, SD3, FLUX, Lumina, HunyuanImage, and Anima\n  workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# sd-scripts\n\nUse this skill when a user asks for help with `sd-scripts`, Kohya-style Stable Diffusion training scripts, LoRA\u002Fadditional-network training, dataset TOML preparation, image generation, or model\u002FLoRA utility workflows.\n\nThis skill is self-contained for planning, validation, troubleshooting, and command construction. Heavyweight sd-scripts training\u002Fgeneration\u002Fmerge commands still require the user to run them in an sd-scripts installation that contains the project scripts, model files, and required ML dependencies.\n\n## Route by Task\n\n- Use `sub-skills\u002Fdata-preparation` for dataset TOML, DreamBooth\u002Ffine-tuning subsets, metadata JSON\u002FJSONL, captions\u002Ftags, validation splits, bucketing, masked loss, inpainting data, and safe input validation.\n- Use `sub-skills\u002Ftraining` for LoRA\u002Fadditional-network training, full fine-tuning, Textual Inversion, LECO, ControlNet-LLLite, validation loss, memory flags, optimizer choices, and model-family training commands.\n- Use `sub-skills\u002Fgeneration` for image generation, txt2img\u002Fimg2img\u002Finpainting inference, prompt-file validation, SDXL conditioning, LoRA application during inference, ControlNet\u002FLLLite generation, and minimal inference scripts.\n- Use `sub-skills\u002Fmodel-utilities` for LoRA merge\u002Fextract\u002Fresize\u002Fconvert planning, checkpoint or Diffusers conversion, safetensors metadata inspection, model-spec metadata, and safe handling of write-heavy utilities.\n\n## Before Suggesting a Runnable Command\n\n1. Confirm the user has an sd-scripts checkout or installed copy with the relevant root scripts available.\n2. Confirm Python dependencies are installed for the chosen workflow. Training and generation usually need PyTorch, Accelerate, Diffusers, Transformers, Safetensors, and model-family-specific optional packages.\n3. Confirm model files, text encoders, VAE\u002FAE files, datasets, and output directories exist.\n4. Confirm whether execution is safe: full training, generation, caching, merging, extraction, and conversion can use GPU, download\u002Fload large weights, write large files, or run for a long time.\n5. Use bundled helper scripts for read-only validation or command construction before running heavyweight sd-scripts commands.\n\n## Installation and Environment Notes\n\nsd-scripts is normally used from a cloned checkout with Python 3.10-3.12 and a workflow-specific PyTorch install. PyTorch is intentionally not pinned in the project requirements because CUDA, driver, GPU architecture, and platform determine the correct wheel.\n\nA typical setup pattern is:\n\n```bash\npython -m venv venv\nsource venv\u002Fbin\u002Factivate\npython -m pip install torch torchvision --index-url \u003Cmatching-pytorch-wheel-index>\npython -m pip install --upgrade -r requirements.txt\naccelerate config\n```\n\nOn Windows, use the venv activation command for PowerShell or cmd, and match the PyTorch CUDA wheel to the installed NVIDIA driver. For RTX 50-series or other new GPUs, use a recent PyTorch\u002FCUDA wheel that supports the architecture.\n\n## Safe Bundled Helpers\n\n- `scripts\u002Fcheck_sd_scripts_environment.py` checks the active Python for common dependencies and optional backend availability without importing or running training scripts.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fvalidate_dataset_inputs.py` validates dataset config and metadata files without loading models.\n- `sub-skills\u002Ftraining\u002Fscripts\u002Fbuild_training_command.py` prints command templates and never launches training.\n- `sub-skills\u002Fgeneration\u002Fscripts\u002Fvalidate_prompt_file.py` validates prompt files without loading models.\n- `sub-skills\u002Fmodel-utilities\u002Fscripts\u002Finspect_safetensors_metadata.py` reads safetensors metadata without loading tensor payloads.\n\n## Shared References\n\n- `references\u002Frepo-provenance.md`: source snapshot used to generate this skill; read before deciding whether to refresh the skill.\n- `references\u002Ftroubleshooting.md`: cross-cutting install, dependency, hardware, and execution-safety failures.\n- `references\u002Fdeveloper-notes.md`: repo-specific conventions for coding agents and maintainers.\n\n## Safety Defaults\n\n- Do not run training, generation, caching, merging, extraction, or conversion just because a command can be built.\n- Prefer read-only validators, `--help`, metadata inspection, and dry-run planning first.\n- Do not use the same file as both input and output for model utilities.\n- Treat network downloads, model downloads, external credentials, and long GPU jobs as explicit user-approved operations.\n- When dependencies are missing, explain the minimal dependency group for the requested workflow instead of installing every optional package.\n","# sd-scripts\n\nUse this skill when a user asks for help with `sd-scripts`, Kohya-style Stable Diffusion training scripts, LoRA\u002Fadditional-network training, dataset TOML preparation, image generation, or model\u002FLoRA utility workflows.\n\nThis skill is self-contained for planning, validation, troubleshooting, and command construction. Heavyweight sd-scripts training\u002Fgeneration\u002Fmerge commands still require the user to run them in an sd-scripts installation that contains the project scripts, model files, and required ML dependencies.\n\n## Route by Task\n\n- Use `sub-skills\u002Fdata-preparation` for dataset TOML, DreamBooth\u002Ffine-tuning subsets, metadata JSON\u002FJSONL, captions\u002Ftags, validation splits, bucketing, masked loss, inpainting data, and safe input validation.\n- Use `sub-skills\u002Ftraining` for LoRA\u002Fadditional-network training, full fine-tuning, Textual Inversion, LECO, ControlNet-LLLite, validation loss, memory flags, optimizer choices, and model-family training commands.\n- Use `sub-skills\u002Fgeneration` for image generation, txt2img\u002Fimg2img\u002Finpainting inference, prompt-file validation, SDXL conditioning, LoRA application during inference, ControlNet\u002FLLLite generation, and minimal inference scripts.\n- Use `sub-skills\u002Fmodel-utilities` for LoRA merge\u002Fextract\u002Fresize\u002Fconvert planning, checkpoint or Diffusers conversion, safetensors metadata inspection, model-spec metadata, and safe handling of write-heavy utilities.\n\n## Before Suggesting a Runnable Command\n\n1. Confirm the user has an sd-scripts checkout or installed copy with the relevant root scripts available.\n2. Confirm Python dependencies are installed for the chosen workflow. Training and generation usually need PyTorch, Accelerate, Diffusers, Transformers, Safetensors, and model-family-specific optional packages.\n3. Confirm model files, text encoders, VAE\u002FAE files, datasets, and output directories exist.\n4. Confirm whether execution is safe: full training, generation, caching, merging, extraction, and conversion can use GPU, download\u002Fload large weights, write large files, or run for a long time.\n5. Use bundled helper scripts for read-only validation or command construction before running heavyweight sd-scripts commands.\n\n## Installation and Environment Notes\n\nsd-scripts is normally used from a cloned checkout with Python 3.10-3.12 and a workflow-specific PyTorch install. PyTorch is intentionally not pinned in the project requirements because CUDA, driver, GPU architecture, and platform determine the correct wheel.\n\nA typical setup pattern is:\n\n```bash\npython -m venv venv\nsource venv\u002Fbin\u002Factivate\npython -m pip install torch torchvision --index-url \u003Cmatching-pytorch-wheel-index>\npython -m pip install --upgrade -r requirements.txt\naccelerate config\n```\n\nOn Windows, use the venv activation command for PowerShell or cmd, and match the PyTorch CUDA wheel to the installed NVIDIA driver. For RTX 50-series or other new GPUs, use a recent PyTorch\u002FCUDA wheel that supports the architecture.\n\n## Safe Bundled Helpers\n\n- `scripts\u002Fcheck_sd_scripts_environment.py` checks the active Python for common dependencies and optional backend availability without importing or running training scripts.\n- `sub-skills\u002Fdata-preparation\u002Fscripts\u002Fvalidate_dataset_inputs.py` validates dataset config and metadata files without loading models.\n- `sub-skills\u002Ftraining\u002Fscripts\u002Fbuild_training_command.py` prints command templates and never launches training.\n- `sub-skills\u002Fgeneration\u002Fscripts\u002Fvalidate_prompt_file.py` validates prompt files without loading models.\n- `sub-skills\u002Fmodel-utilities\u002Fscripts\u002Finspect_safetensors_metadata.py` reads safetensors metadata without loading tensor payloads.\n\n## Shared References\n\n- `references\u002Frepo-provenance.md`: source snapshot used to generate this skill; read before deciding whether to refresh the skill.\n- `references\u002Ftroubleshooting.md`: cross-cutting install, dependency, hardware, and execution-safety failures.\n- `references\u002Fdeveloper-notes.md`: repo-specific conventions for coding agents and maintainers.\n\n## Safety Defaults\n\n- Do not run training, generation, caching, merging, extraction, or conversion just because a command can be built.\n- Prefer read-only validators, `--help`, metadata inspection, and dry-run planning first.\n- Do not use the same file as both input and output for model utilities.\n- Treat network downloads, model downloads, external credentials, and long GPU jobs as explicit user-approved operations.\n- When dependencies are missing, explain the minimal dependency group for the requested workflow instead of installing every optional package.\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\u002Fsd-scripts",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 sd-scripts",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill sd-scripts",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill sd-scripts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdeveloper-notes.md","REFERENCE","参考文档",1925,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Freferences\u002Fdeveloper-notes.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",1998,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",502,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",3360,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_sd_scripts_environment.py","SCRIPT","脚本",3392,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Fscripts\u002Fcheck_sd_scripts_environment.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]