[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795WG4FFRKBYAPMHAAXF8ZM":3,"skill-same:01M795WG4FFRKBYAPMHAAXF8ZM":70},{"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},"01M795WG4FFRKBYAPMHAAXF8ZM","simmim-workflows",null,"Use this repo skill for Swin-Transformer SimMIM masked image modeling pretraining, fine-tuning, evaluation, mask generation, checkpoint remapping, and safe synthetic smoke checks.","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\u002Fswin-transformer\u002Fsub-skills\u002Fsimmim-workflows\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: simmim-workflows\ndescription: \"Use this repo skill for Swin-Transformer SimMIM masked image\n  modeling pretraining, fine-tuning, evaluation, mask generation, checkpoint\n  remapping, and safe synthetic smoke checks.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# simmim-workflows\n\nUse this sub-skill when a task involves SimMIM in the Swin-Transformer repository: masked image modeling pretraining, fine-tuning a SimMIM-pretrained checkpoint, evaluating a SimMIM fine-tuned model, mask generation, or checkpoint remapping.\n\n## Covers\n\n- `main_simmim_pt.py` pretraining command shape.\n- `main_simmim_ft.py` fine-tuning\u002Fevaluation command shape.\n- `MaskGenerator`, `SimMIMTransform`, `SimMIM`, and `build_simmim` behavior.\n- SimMIM config pairs under `configs\u002Fsimmim\u002F`.\n- Safe mask\u002Floss CPU smoke checks.\n\n## Routes elsewhere\n\n- Baseline supervised `main.py` commands: `training-eval-cli`.\n- Generic ImageNet layouts: `data-and-checkpoints`.\n- Swin V1\u002FV2 constructor details: `core-models`.\n- MoE\u002FTutel\u002Ffused CUDA: `moe-and-acceleration`.\n\n## Workflow\n\n1. Decide if the task is pretraining, fine-tuning, or evaluation.\n2. Read `references\u002Fsimmim-workflows.md` for command shape and config pairing.\n3. Read `references\u002Fapi-reference.md` for mask\u002Floss behavior.\n4. Validate the proposed command with `scripts\u002Fvalidate_simmim_command.py`.\n5. Run `scripts\u002Fsmoke_simmim_loss.py` only for a tiny CPU synthetic check; it is not a training substitute.\n\n## Linked files\n\n- `references\u002Fsimmim-workflows.md` - task recipes and config pair guidance.\n- `references\u002Fapi-reference.md` - mask and SimMIM model APIs.\n- `references\u002Ftroubleshooting.md` - common mask, checkpoint, and command mistakes.\n- `scripts\u002Fvalidate_simmim_command.py` - safe command validator.\n- `scripts\u002Fsmoke_simmim_loss.py` - tiny synthetic CPU loss smoke.\n","# simmim-workflows\n\nUse this sub-skill when a task involves SimMIM in the Swin-Transformer repository: masked image modeling pretraining, fine-tuning a SimMIM-pretrained checkpoint, evaluating a SimMIM fine-tuned model, mask generation, or checkpoint remapping.\n\n## Covers\n\n- `main_simmim_pt.py` pretraining command shape.\n- `main_simmim_ft.py` fine-tuning\u002Fevaluation command shape.\n- `MaskGenerator`, `SimMIMTransform`, `SimMIM`, and `build_simmim` behavior.\n- SimMIM config pairs under `configs\u002Fsimmim\u002F`.\n- Safe mask\u002Floss CPU smoke checks.\n\n## Routes elsewhere\n\n- Baseline supervised `main.py` commands: `training-eval-cli`.\n- Generic ImageNet layouts: `data-and-checkpoints`.\n- Swin V1\u002FV2 constructor details: `core-models`.\n- MoE\u002FTutel\u002Ffused CUDA: `moe-and-acceleration`.\n\n## Workflow\n\n1. Decide if the task is pretraining, fine-tuning, or evaluation.\n2. Read `references\u002Fsimmim-workflows.md` for command shape and config pairing.\n3. Read `references\u002Fapi-reference.md` for mask\u002Floss behavior.\n4. Validate the proposed command with `scripts\u002Fvalidate_simmim_command.py`.\n5. Run `scripts\u002Fsmoke_simmim_loss.py` only for a tiny CPU synthetic check; it is not a training substitute.\n\n## Linked files\n\n- `references\u002Fsimmim-workflows.md` - task recipes and config pair guidance.\n- `references\u002Fapi-reference.md` - mask and SimMIM model APIs.\n- `references\u002Ftroubleshooting.md` - common mask, checkpoint, and command mistakes.\n- `scripts\u002Fvalidate_simmim_command.py` - safe command validator.\n- `scripts\u002Fsmoke_simmim_loss.py` - tiny synthetic CPU loss smoke.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fswin-transformer\u002Fsub-skills\u002Fsimmim-workflows",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 simmim-workflows",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill simmim-workflows",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill simmim-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fswin-transformer\u002Fsub-skills\u002Fsimmim-workflows\u002FSKILL.md",[46,52,56,60,66],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-reference.md","REFERENCE","参考文档",1000,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fswin-transformer\u002Fsub-skills\u002Fsimmim-workflows\u002Freferences\u002Fapi-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fsimmim-workflows.md",1487,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fswin-transformer\u002Fsub-skills\u002Fsimmim-workflows\u002Freferences\u002Fsimmim-workflows.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",966,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fswin-transformer\u002Fsub-skills\u002Fsimmim-workflows\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fsmoke_simmim_loss.py","SCRIPT","脚本",1300,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fswin-transformer\u002Fsub-skills\u002Fsimmim-workflows\u002Fscripts\u002Fsmoke_simmim_loss.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fvalidate_simmim_command.py",2295,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fswin-transformer\u002Fsub-skills\u002Fsimmim-workflows\u002Fscripts\u002Fvalidate_simmim_command.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"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.","Apache-2.0","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":75,"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":75,"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":75,"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":75,"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":75,"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",[],[]]