[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78YD2MEKP3WYP830ATK7W8D":3,"skill-same:01M78YD2MEKP3WYP830ATK7W8D":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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78YD2MEKP3WYP830ATK7W8D","app-deployment",null,"Install, configure, launch, and sanity-check InternGPT\u002FInternChat services.","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\u002Fintern-gpt\u002Fsub-skills\u002Fapp-deployment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: app-deployment\ndescription: \"Install, configure, launch, and sanity-check InternGPT\u002FInternChat services.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# app-deployment\n\nUse this sub-skill when the task is to install, configure, launch, containerize, or sanity-check an InternGPT\u002FInternChat Gradio service. It owns app-level CLI planning, model-zoo placement, HTTPS\u002FOpenAI setup, Docker GPU deployment, and static validation of `--load`\u002F`--tab` choices.\n\nRoute detailed workflow questions elsewhere:\n\n- Read [..\u002Fvisual-dialogue-tools\u002FSKILL.md](..\u002Fvisual-dialogue-tools\u002FSKILL.md) for detailed image, mask, OCR, SAM, Husky VQA, inpainting, and image-tool behavior after the service is running.\n- Read [..\u002Fcross-modal-generation\u002FSKILL.md](..\u002Fcross-modal-generation\u002FSKILL.md) for detailed ImageBind audio\u002Fthermal\u002Fimage-conditioned generation and DragGAN point-editing usage.\n- Read [..\u002Fvideo-understanding\u002FSKILL.md](..\u002Fvideo-understanding\u002FSKILL.md) for detailed video caption\u002Faction\u002Fdense-caption\u002FTikTok workflows.\n\n## Deployment routing\n\n- For CLI flags, supported `--load` classes, tab names, and launch-plan sanity checks, read [references\u002Fcli-and-config.md](references\u002Fcli-and-config.md).\n- For `model_zoo\u002F`, checkpoints, Husky\u002FLLaMA conversion, SAM, LaMa, Tag2Text, GRiT, StyleGAN, ImageBind, and StableUnCLIP prerequisites, read [references\u002Fmodel-zoo.md](references\u002Fmodel-zoo.md).\n- For basic, full, DragGAN-only, HTTPS, OpenAI, and Docker GPU launch recipes, read [references\u002Fdeployment-recipes.md](references\u002Fdeployment-recipes.md).\n- For common failures such as missing `model_zoo`, bad LLaMA\u002FHusky partial conversion, missing OpenAI key, `OPENAI_API_BASE`, certificate errors, CUDA\u002FVRAM mismatch, Docker placeholder volumes, detectron2\u002FOpenCV pitfalls, and `-e` expectations, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- Run [scripts\u002Fvalidate_load_plan.py](scripts\u002Fvalidate_load_plan.py) before recommending a launch command or compose command when the user asks which `--load` or `--tab` string to use.\n\n## Quick decision guide\n\n1. Choose the smallest tab set that matches the user's task: `DragGAN` for StyleGAN point editing, `Image` for image upload\u002Fclick\u002FOCR\u002Fsegmentation\u002Fdialogue, `Audio` for ImageBind audio input, and `Video` for video upload\u002Fanalysis.\n2. Choose the smallest direct `--load` list that provides those tabs' tools; template tools are auto-created only after their prerequisites load.\n3. Prefer `-e`\u002F`--e-mode` for constrained VRAM, but do not describe it as CPU-only: the app still expects CUDA for normal launches, and the speech model is initialized on `cuda:0`.\n4. Check `model_zoo\u002F`, `certificate\u002F`, and OpenAI configuration before treating a launch failure as a Python bug.\n5. For Docker, replace every placeholder volume with real host directories and keep GPU reservation\u002Fcontainer-toolkit requirements explicit.\n\n## Safe default recipes\n\n- Basic image-dialogue service: `HuskyVQA_cuda:0,SegmentAnything_cuda:0,ImageOCRRecognition_cuda:0` with `-e` on a CUDA machine and a populated `model_zoo\u002F`.\n- Low-memory DragGAN-only HTTPS service: `StyleGAN_cuda:0`, `--tab DragGAN`, `--https`, and `-e`, plus `certificate\u002Fcert.pem`, `certificate\u002Fkey.pem`, and StyleGAN checkpoint readiness.\n- Full multimodal demo: use the long full-feature load string in `references\u002Fdeployment-recipes.md`; warn that it is heavy and requires multiple model families, CUDA, and usually far more setup than a task-specific launch.\n","# app-deployment\n\nUse this sub-skill when the task is to install, configure, launch, containerize, or sanity-check an InternGPT\u002FInternChat Gradio service. It owns app-level CLI planning, model-zoo placement, HTTPS\u002FOpenAI setup, Docker GPU deployment, and static validation of `--load`\u002F`--tab` choices.\n\nRoute detailed workflow questions elsewhere:\n\n- Read [..\u002Fvisual-dialogue-tools\u002FSKILL.md](..\u002Fvisual-dialogue-tools\u002FSKILL.md) for detailed image, mask, OCR, SAM, Husky VQA, inpainting, and image-tool behavior after the service is running.\n- Read [..\u002Fcross-modal-generation\u002FSKILL.md](..\u002Fcross-modal-generation\u002FSKILL.md) for detailed ImageBind audio\u002Fthermal\u002Fimage-conditioned generation and DragGAN point-editing usage.\n- Read [..\u002Fvideo-understanding\u002FSKILL.md](..\u002Fvideo-understanding\u002FSKILL.md) for detailed video caption\u002Faction\u002Fdense-caption\u002FTikTok workflows.\n\n## Deployment routing\n\n- For CLI flags, supported `--load` classes, tab names, and launch-plan sanity checks, read [references\u002Fcli-and-config.md](references\u002Fcli-and-config.md).\n- For `model_zoo\u002F`, checkpoints, Husky\u002FLLaMA conversion, SAM, LaMa, Tag2Text, GRiT, StyleGAN, ImageBind, and StableUnCLIP prerequisites, read [references\u002Fmodel-zoo.md](references\u002Fmodel-zoo.md).\n- For basic, full, DragGAN-only, HTTPS, OpenAI, and Docker GPU launch recipes, read [references\u002Fdeployment-recipes.md](references\u002Fdeployment-recipes.md).\n- For common failures such as missing `model_zoo`, bad LLaMA\u002FHusky partial conversion, missing OpenAI key, `OPENAI_API_BASE`, certificate errors, CUDA\u002FVRAM mismatch, Docker placeholder volumes, detectron2\u002FOpenCV pitfalls, and `-e` expectations, read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- Run [scripts\u002Fvalidate_load_plan.py](scripts\u002Fvalidate_load_plan.py) before recommending a launch command or compose command when the user asks which `--load` or `--tab` string to use.\n\n## Quick decision guide\n\n1. Choose the smallest tab set that matches the user's task: `DragGAN` for StyleGAN point editing, `Image` for image upload\u002Fclick\u002FOCR\u002Fsegmentation\u002Fdialogue, `Audio` for ImageBind audio input, and `Video` for video upload\u002Fanalysis.\n2. Choose the smallest direct `--load` list that provides those tabs' tools; template tools are auto-created only after their prerequisites load.\n3. Prefer `-e`\u002F`--e-mode` for constrained VRAM, but do not describe it as CPU-only: the app still expects CUDA for normal launches, and the speech model is initialized on `cuda:0`.\n4. Check `model_zoo\u002F`, `certificate\u002F`, and OpenAI configuration before treating a launch failure as a Python bug.\n5. For Docker, replace every placeholder volume with real host directories and keep GPU reservation\u002Fcontainer-toolkit requirements explicit.\n\n## Safe default recipes\n\n- Basic image-dialogue service: `HuskyVQA_cuda:0,SegmentAnything_cuda:0,ImageOCRRecognition_cuda:0` with `-e` on a CUDA machine and a populated `model_zoo\u002F`.\n- Low-memory DragGAN-only HTTPS service: `StyleGAN_cuda:0`, `--tab DragGAN`, `--https`, and `-e`, plus `certificate\u002Fcert.pem`, `certificate\u002Fkey.pem`, and StyleGAN checkpoint readiness.\n- Full multimodal demo: use the long full-feature load string in `references\u002Fdeployment-recipes.md`; warn that it is heavy and requires multiple model families, CUDA, and usually far more setup than a task-specific launch.\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\u002Fintern-gpt\u002Fsub-skills\u002Fapp-deployment",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 app-deployment",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill app-deployment",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill app-deployment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fintern-gpt\u002Fsub-skills\u002Fapp-deployment\u002FSKILL.md",[47,53,57,60,64],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcli-and-config.md","REFERENCE","参考文档",5749,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fintern-gpt\u002Fsub-skills\u002Fapp-deployment\u002Freferences\u002Fcli-and-config.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fdeployment-recipes.md",5748,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fintern-gpt\u002Fsub-skills\u002Fapp-deployment\u002Freferences\u002Fdeployment-recipes.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":59},"references\u002Fmodel-zoo.md","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fintern-gpt\u002Fsub-skills\u002Fapp-deployment\u002Freferences\u002Fmodel-zoo.md",{"path":61,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",6996,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fintern-gpt\u002Fsub-skills\u002Fapp-deployment\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fvalidate_load_plan.py","SCRIPT","脚本",13128,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fintern-gpt\u002Fsub-skills\u002Fapp-deployment\u002Fscripts\u002Fvalidate_load_plan.py",[71,78,85,92,99,106],{"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":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"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",[],[]]