[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M796XS7YY52WQVZBFPGF91FV":3,"skill-same:01M796XS7YY52WQVZBFPGF91FV":66},{"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},"01M796XS7YY52WQVZBFPGF91FV","multimodal-generation",null,"Use UniLM Kosmos, TextDiffuser, WavLM, BEATs, SpeechT5, SpeechLM, VALL-E, and LatentLM for safe multimodal generation, OCR\u002Fmarkdown, audio, and latent diffusion workflow planning.","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\u002Funilm\u002Fsub-skills\u002Fmultimodal-generation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: multimodal-generation\ndescription: \"Use UniLM Kosmos, TextDiffuser, WavLM, BEATs, SpeechT5, SpeechLM,\n  VALL-E, and LatentLM for safe multimodal generation, OCR\u002Fmarkdown, audio, and\n  latent diffusion workflow planning.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Multimodal Generation\n\nUse this sub-skill when a task names Kosmos, Kosmos-2.5, TextDiffuser, TextDiffuser-2, WavLM, BEATs, SpeechT5, SpeechLM, VALL-E, or LatentLM, or when the request is about open-ended image\u002Ftext generation, grounded multimodal generation, literate OCR\u002Fmarkdown generation, audio representation extraction, speech generation, or latent diffusion sampling\u002Fevaluation.\n\n## Route Here\n\n- Validate or plan Kosmos-2 grounded image-text generation, phrase grounding, captioning, VQA, GRIT-style data preparation, or fairseq generation commands.\n- Validate or plan Kosmos-2.5 OCR and image-to-markdown inference with `--do_ocr` or `--do_md`, local image\u002Fcheckpoint inputs, optional aspect-ratio preprocessing, and OCR bounding-box visualization.\n- Choose TextDiffuser v1 text-to-image, template-conditioned generation, text inpainting, MARIO-Eval sampling, or TextDiffuser-2 full\u002FLoRA\u002Finpainting command shapes.\n- Plan WavLM, BEATs, SpeechT5, SpeechLM, or VALL-E audio\u002Fspeech workflows, including checkpoint loading, 16 kHz audio assumptions, fairseq manifests, TTS\u002FVC generation, and reference-only zero-shot TTS notes.\n- Validate LatentLM sampling, many-sample generation, training, or FID evaluation inputs, including checkpoint layout, VAE, ImageFolder\u002FHugging Face dataset choices, and reference-stat requirements.\n\n## Route Elsewhere\n\n- Use `vision-document-ai` for LayoutLM, LayoutLMv2\u002Fv3, LayoutXLM, MarkupLM, XDoc, DiT, TrOCR, BEiT, VLMo, or document OCR\u002Flayout tasks unless the request specifically names Kosmos-2.5 literate OCR or image-to-markdown.\n- Use `embeddings-retrieval` for E5, SimLM, dense retrieval, reranking, hard-negative mining, or text embedding evaluation.\n- Use `architectures-training` for architecture-only training mechanics, long-context models, optimizer schedules, TorchScale\u002FDeepNet\u002FMagneto internals, or Deepspeed\u002FApex mechanics not tied to these multimodal workflows.\n\n## Read Or Run\n\n- Read [references\u002Fworkflows.md](references\u002Fworkflows.md) to select the right model family and construct safe command templates for Kosmos, TextDiffuser, audio\u002Fspeech, or LatentLM tasks.\n- Read [references\u002Finput-checklists.md](references\u002Finput-checklists.md) before any native run to confirm required images, prompts, checkpoints, audio manifests, datasets, and outputs.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when checkpoints, tokenizers, CUDA\u002FFlashAttention\u002Fxformers, fairseq, Hugging Face, audio sample rates, or LatentLM FID inputs fail.\n- Run [scripts\u002Fcheck_multimodal_inputs.py](scripts\u002Fcheck_multimodal_inputs.py) to validate mode-specific local arguments and print a safe run checklist without importing heavy frameworks, downloading, or launching generation.\n\n## Safe Default Workflow\n\n1. Classify the request by family: Kosmos grounding\u002FOCR, TextDiffuser text rendering, audio\u002Fspeech representation or generation, or LatentLM latent diffusion.\n2. Use the references to pick the native entry-point shape and required inputs; keep original inference\u002Ftraining scripts reference-only until the user confirms data, checkpoints, dependencies, network access, GPU readiness, and output location.\n3. Run the bundled checker in the closest mode to catch missing local files and unsafe assumptions before constructing a native command.\n4. If the checker passes, present the command as a template to run from a user-provided compatible source checkout and environment, not from this skill directory.\n5. Prefer small validation or `--help` checks before long generation, distributed training, downloads, remote demos, or metric evaluation.\n","# Multimodal Generation\n\nUse this sub-skill when a task names Kosmos, Kosmos-2.5, TextDiffuser, TextDiffuser-2, WavLM, BEATs, SpeechT5, SpeechLM, VALL-E, or LatentLM, or when the request is about open-ended image\u002Ftext generation, grounded multimodal generation, literate OCR\u002Fmarkdown generation, audio representation extraction, speech generation, or latent diffusion sampling\u002Fevaluation.\n\n## Route Here\n\n- Validate or plan Kosmos-2 grounded image-text generation, phrase grounding, captioning, VQA, GRIT-style data preparation, or fairseq generation commands.\n- Validate or plan Kosmos-2.5 OCR and image-to-markdown inference with `--do_ocr` or `--do_md`, local image\u002Fcheckpoint inputs, optional aspect-ratio preprocessing, and OCR bounding-box visualization.\n- Choose TextDiffuser v1 text-to-image, template-conditioned generation, text inpainting, MARIO-Eval sampling, or TextDiffuser-2 full\u002FLoRA\u002Finpainting command shapes.\n- Plan WavLM, BEATs, SpeechT5, SpeechLM, or VALL-E audio\u002Fspeech workflows, including checkpoint loading, 16 kHz audio assumptions, fairseq manifests, TTS\u002FVC generation, and reference-only zero-shot TTS notes.\n- Validate LatentLM sampling, many-sample generation, training, or FID evaluation inputs, including checkpoint layout, VAE, ImageFolder\u002FHugging Face dataset choices, and reference-stat requirements.\n\n## Route Elsewhere\n\n- Use `vision-document-ai` for LayoutLM, LayoutLMv2\u002Fv3, LayoutXLM, MarkupLM, XDoc, DiT, TrOCR, BEiT, VLMo, or document OCR\u002Flayout tasks unless the request specifically names Kosmos-2.5 literate OCR or image-to-markdown.\n- Use `embeddings-retrieval` for E5, SimLM, dense retrieval, reranking, hard-negative mining, or text embedding evaluation.\n- Use `architectures-training` for architecture-only training mechanics, long-context models, optimizer schedules, TorchScale\u002FDeepNet\u002FMagneto internals, or Deepspeed\u002FApex mechanics not tied to these multimodal workflows.\n\n## Read Or Run\n\n- Read [references\u002Fworkflows.md](references\u002Fworkflows.md) to select the right model family and construct safe command templates for Kosmos, TextDiffuser, audio\u002Fspeech, or LatentLM tasks.\n- Read [references\u002Finput-checklists.md](references\u002Finput-checklists.md) before any native run to confirm required images, prompts, checkpoints, audio manifests, datasets, and outputs.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when checkpoints, tokenizers, CUDA\u002FFlashAttention\u002Fxformers, fairseq, Hugging Face, audio sample rates, or LatentLM FID inputs fail.\n- Run [scripts\u002Fcheck_multimodal_inputs.py](scripts\u002Fcheck_multimodal_inputs.py) to validate mode-specific local arguments and print a safe run checklist without importing heavy frameworks, downloading, or launching generation.\n\n## Safe Default Workflow\n\n1. Classify the request by family: Kosmos grounding\u002FOCR, TextDiffuser text rendering, audio\u002Fspeech representation or generation, or LatentLM latent diffusion.\n2. Use the references to pick the native entry-point shape and required inputs; keep original inference\u002Ftraining scripts reference-only until the user confirms data, checkpoints, dependencies, network access, GPU readiness, and output location.\n3. Run the bundled checker in the closest mode to catch missing local files and unsafe assumptions before constructing a native command.\n4. If the checker passes, present the command as a template to run from a user-provided compatible source checkout and environment, not from this skill directory.\n5. Prefer small validation or `--help` checks before long generation, distributed training, downloads, remote demos, or metric evaluation.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fmultimodal-generation",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 multimodal-generation",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill multimodal-generation",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill multimodal-generation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fmultimodal-generation\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finput-checklists.md","REFERENCE","参考文档",10623,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fmultimodal-generation\u002Freferences\u002Finput-checklists.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftroubleshooting.md",11556,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fmultimodal-generation\u002Freferences\u002Ftroubleshooting.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fworkflows.md",16911,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fmultimodal-generation\u002Freferences\u002Fworkflows.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fcheck_multimodal_inputs.py","SCRIPT","脚本",22531,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Funilm\u002Fsub-skills\u002Fmultimodal-generation\u002Fscripts\u002Fcheck_multimodal_inputs.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"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.","Apache-2.0","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":71,"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":71,"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":71,"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":71,"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":71,"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",[],[]]