[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M790X4N0G8STFPM8YG010KP2":3,"skill-same:01M790X4N0G8STFPM8YG010KP2":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},"01M790X4N0G8STFPM8YG010KP2","data-model-customization",null,"Customize ms-swift datasets, registries, plugins, models, and templates safely.","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\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: data-model-customization\ndescription: \"Customize ms-swift datasets, registries, plugins, models, and\n  templates safely.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Data and Model Customization\n\nUse this sub-skill when the task is to prepare or validate custom data, map columns, inspect ms-swift registries, register datasets\u002Fmodels\u002Ftemplates through an external plugin, or reason about model\u002Ftemplate selection before training or inference.\n\n## Read First\n\n- [Data formats](references\u002Fdata-formats.md): standard `messages` rows, `--columns`, SFT\u002FRLHF\u002Fmultimodal\u002Fagent fields, and preprocessor selection.\n- [Registry and plugins](references\u002Fregistry-and-plugins.md): `--custom_dataset_info`, `--external_plugins`, `register_dataset`, `register_model`, `register_template`, and safe plugin structure.\n- [Template reference](references\u002Ftemplate-reference.md): `get_processor`, `get_template`, template\u002Fmodel selection, agent templates, loss scaling, and offline skeleton checks.\n- [Troubleshooting](references\u002Ftroubleshooting.md): row drops, malformed messages, media problems, template mismatch, plugin side effects, and local\u002Foffline loading.\n\n## Bundled Checks\n\n- `scripts\u002Fvalidate_dataset_rows.py`: validate JSONL\u002FJSON\u002FCSV rows for common ms-swift keys before passing them to `swift sft`, `swift pt`, or `swift rlhf`.\n- `scripts\u002Finspect_registries.py`: list installed `DATASET_MAPPING`, `MODEL_MAPPING`, and `TEMPLATE_MAPPING` entries without model downloads.\n- `scripts\u002Finspect_template_encoding.py`: print a safe template-encoding plan by default; optionally attempt an installed ms-swift processor\u002Ftemplate encode without downloading weights.\n\n## Routing Boundaries\n\n- Stay here for `--dataset`, `--columns`, `--custom_dataset_info`, `--external_plugins`, preprocessors, registry inspection, and model\u002Ftemplate registration plans.\n- Route full `swift sft`, `swift pt`, and dataset packing\u002Ftraining execution to the training sub-skill.\n- Route inference engine behavior, deployment servers, and client requests to inference\u002Fdeployment coverage.\n- Route RLHF\u002FGRPO algorithm execution, reward models, rollout workers, Ray, and Megatron execution to advanced distributed\u002FRLHF coverage.\n- Route export and evaluation execution to export\u002Fevaluation coverage.\n\n## Quick Patterns\n\n- Prefer direct data files first: `swift sft --dataset train.jsonl --columns prompt=query answer=response ...`.\n- Use `--custom_dataset_info dataset_info.json` when stable aliases, subsets, splits, or reusable column mappings are needed.\n- Use `--external_plugins plugin.py` only when code must call `register_dataset`, `register_model`, or `register_template`.\n- Inspect support with `python scripts\u002Finspect_registries.py --models --templates --contains qwen2_5` before overriding `--model_type` or `--template`.\n- Validate rows with `python scripts\u002Fvalidate_dataset_rows.py data.jsonl --columns raw_prompt=query raw_answer=response --check-media exists` before long runs.\n","# Data and Model Customization\n\nUse this sub-skill when the task is to prepare or validate custom data, map columns, inspect ms-swift registries, register datasets\u002Fmodels\u002Ftemplates through an external plugin, or reason about model\u002Ftemplate selection before training or inference.\n\n## Read First\n\n- [Data formats](references\u002Fdata-formats.md): standard `messages` rows, `--columns`, SFT\u002FRLHF\u002Fmultimodal\u002Fagent fields, and preprocessor selection.\n- [Registry and plugins](references\u002Fregistry-and-plugins.md): `--custom_dataset_info`, `--external_plugins`, `register_dataset`, `register_model`, `register_template`, and safe plugin structure.\n- [Template reference](references\u002Ftemplate-reference.md): `get_processor`, `get_template`, template\u002Fmodel selection, agent templates, loss scaling, and offline skeleton checks.\n- [Troubleshooting](references\u002Ftroubleshooting.md): row drops, malformed messages, media problems, template mismatch, plugin side effects, and local\u002Foffline loading.\n\n## Bundled Checks\n\n- `scripts\u002Fvalidate_dataset_rows.py`: validate JSONL\u002FJSON\u002FCSV rows for common ms-swift keys before passing them to `swift sft`, `swift pt`, or `swift rlhf`.\n- `scripts\u002Finspect_registries.py`: list installed `DATASET_MAPPING`, `MODEL_MAPPING`, and `TEMPLATE_MAPPING` entries without model downloads.\n- `scripts\u002Finspect_template_encoding.py`: print a safe template-encoding plan by default; optionally attempt an installed ms-swift processor\u002Ftemplate encode without downloading weights.\n\n## Routing Boundaries\n\n- Stay here for `--dataset`, `--columns`, `--custom_dataset_info`, `--external_plugins`, preprocessors, registry inspection, and model\u002Ftemplate registration plans.\n- Route full `swift sft`, `swift pt`, and dataset packing\u002Ftraining execution to the training sub-skill.\n- Route inference engine behavior, deployment servers, and client requests to inference\u002Fdeployment coverage.\n- Route RLHF\u002FGRPO algorithm execution, reward models, rollout workers, Ray, and Megatron execution to advanced distributed\u002FRLHF coverage.\n- Route export and evaluation execution to export\u002Fevaluation coverage.\n\n## Quick Patterns\n\n- Prefer direct data files first: `swift sft --dataset train.jsonl --columns prompt=query answer=response ...`.\n- Use `--custom_dataset_info dataset_info.json` when stable aliases, subsets, splits, or reusable column mappings are needed.\n- Use `--external_plugins plugin.py` only when code must call `register_dataset`, `register_model`, or `register_template`.\n- Inspect support with `python scripts\u002Finspect_registries.py --models --templates --contains qwen2_5` before overriding `--model_type` or `--template`.\n- Validate rows with `python scripts\u002Fvalidate_dataset_rows.py data.jsonl --columns raw_prompt=query raw_answer=response --check-media exists` before long runs.\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\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization",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 data-model-customization",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill data-model-customization",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill data-model-customization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization\u002FSKILL.md",[47,53,57,61,65,71,75],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fdata-formats.md","REFERENCE","参考文档",8153,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization\u002Freferences\u002Fdata-formats.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fregistry-and-plugins.md",9040,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization\u002Freferences\u002Fregistry-and-plugins.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftemplate-reference.md",7724,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization\u002Freferences\u002Ftemplate-reference.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",7978,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_registries.py","SCRIPT","脚本",11952,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization\u002Fscripts\u002Finspect_registries.py",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Finspect_template_encoding.py",8353,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization\u002Fscripts\u002Finspect_template_encoding.py",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fvalidate_dataset_rows.py",24589,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fms-swift\u002Fsub-skills\u002Fdata-model-customization\u002Fscripts\u002Fvalidate_dataset_rows.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",[],[]]