[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZE26JM94CWAJ978J4ZXAS":3,"skill-same:01M78ZE26JM94CWAJ978J4ZXAS":89},{"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},"01M78ZE26JM94CWAJ978J4ZXAS","text-conditional",null,"Router for LlamaGen caption-conditioned training, sampling, prompt batches, and t2i evaluation.","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\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: text-conditional\ndescription: \"Router for LlamaGen caption-conditioned training, sampling, prompt\n  batches, and t2i evaluation.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# Text-Conditional\n\nUse this sub-skill for the text-conditioned LlamaGen path: stage-1 and stage-2 training, prompt sampling, and evaluation of caption-conditioned generations.\n\n## Owns\n- Stage-1 and stage-2 t2i training.\n- COCO and Parti prompt sampling.\n- T5 embedder behavior, padding, and cache layout for the text-conditioning path.\n- t2i evaluation inputs, outputs, and packaging expectations.\n- Checkpoint \u002F precision \u002F `--from-fsdp` guidance for the text-conditioned path.\n\n## Routes out\n- Tokenizer training, finetuning, reconstruction, and code\u002Fimage round trips -> `tokenizers`\n- Precomputed code or T5 feature extraction, OpenImages manifests, and cache prep -> `data-preparation`\n- ImageNet class-conditional generation, serving, and c2i evaluation -> `class-conditional`\n- Remote publishing or upload helpers -> excluded\n\n## Best entry points\n- Training: `scripts\u002Ftrain_t2i_stage1.sh`, `scripts\u002Ftrain_t2i_stage2.sh`\n- Sampling: `scripts\u002Fsample_t2i_coco.sh`, `scripts\u002Fsample_t2i_parti.sh`\n- Evaluation: `scripts\u002Fevaluate_t2i.sh`\n- T5 behavior: `references\u002Ft5.md`\n- Prompt \u002F batch layout: `references\u002Fevaluation.md`\n- Workflow selection: `references\u002Fworkflows.md`\n\n## Read before answering\n- `references\u002Fworkflows.md`\n- `references\u002Fcli-reference.md`\n- `references\u002Ft5.md`\n- `references\u002Fevaluation.md`\n- `references\u002Ftroubleshooting.md`\n\n## Fast routing rules\n- If the user asks to create or refresh text features, route to `data-preparation`.\n- If the user asks for VQ, VQGAN, VAE, or Consistency Decoder reconstruction, route to `tokenizers`.\n- If the user asks for ImageNet c2i training, sampling, serving, or c2i evaluation, route to `class-conditional`.\n- If the user asks about t2i only, stay here and use the bundled wrappers.\n- Keep `--no-left-padding`, prompt CSV\u002FTSV formatting, and evaluation folder layout in mind before running a job.\n","# Text-Conditional\n\nUse this sub-skill for the text-conditioned LlamaGen path: stage-1 and stage-2 training, prompt sampling, and evaluation of caption-conditioned generations.\n\n## Owns\n- Stage-1 and stage-2 t2i training.\n- COCO and Parti prompt sampling.\n- T5 embedder behavior, padding, and cache layout for the text-conditioning path.\n- t2i evaluation inputs, outputs, and packaging expectations.\n- Checkpoint \u002F precision \u002F `--from-fsdp` guidance for the text-conditioned path.\n\n## Routes out\n- Tokenizer training, finetuning, reconstruction, and code\u002Fimage round trips -> `tokenizers`\n- Precomputed code or T5 feature extraction, OpenImages manifests, and cache prep -> `data-preparation`\n- ImageNet class-conditional generation, serving, and c2i evaluation -> `class-conditional`\n- Remote publishing or upload helpers -> excluded\n\n## Best entry points\n- Training: `scripts\u002Ftrain_t2i_stage1.sh`, `scripts\u002Ftrain_t2i_stage2.sh`\n- Sampling: `scripts\u002Fsample_t2i_coco.sh`, `scripts\u002Fsample_t2i_parti.sh`\n- Evaluation: `scripts\u002Fevaluate_t2i.sh`\n- T5 behavior: `references\u002Ft5.md`\n- Prompt \u002F batch layout: `references\u002Fevaluation.md`\n- Workflow selection: `references\u002Fworkflows.md`\n\n## Read before answering\n- `references\u002Fworkflows.md`\n- `references\u002Fcli-reference.md`\n- `references\u002Ft5.md`\n- `references\u002Fevaluation.md`\n- `references\u002Ftroubleshooting.md`\n\n## Fast routing rules\n- If the user asks to create or refresh text features, route to `data-preparation`.\n- If the user asks for VQ, VQGAN, VAE, or Consistency Decoder reconstruction, route to `tokenizers`.\n- If the user asks for ImageNet c2i training, sampling, serving, or c2i evaluation, route to `class-conditional`.\n- If the user asks about t2i only, stay here and use the bundled wrappers.\n- Keep `--no-left-padding`, prompt CSV\u002FTSV formatting, and evaluation folder layout in mind before running a job.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional",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 text-conditional",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill text-conditional",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill text-conditional","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002FSKILL.md",[46,52,56,60,64,68,74,78,81,85],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcli-reference.md","REFERENCE","参考文档",2748,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Freferences\u002Fcli-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fevaluation.md",1069,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Freferences\u002Fevaluation.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ft5.md",1213,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Freferences\u002Ft5.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",2301,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fworkflows.md",2636,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Freferences\u002Fworkflows.md",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fevaluate_t2i.sh","SCRIPT","脚本",213,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Fscripts\u002Fevaluate_t2i.sh",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fsample_t2i_coco.sh",420,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Fscripts\u002Fsample_t2i_coco.sh",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":80},"scripts\u002Fsample_t2i_parti.sh","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Fscripts\u002Fsample_t2i_parti.sh",{"path":82,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Ftrain_t2i_stage1.sh",523,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Fscripts\u002Ftrain_t2i_stage1.sh",{"path":86,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Ftrain_t2i_stage2.sh",601,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fllamagen\u002Fsub-skills\u002Ftext-conditional\u002Fscripts\u002Ftrain_t2i_stage2.sh",[90,98,105,112,119,126],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":94,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"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",[],[]]