[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794VBTCADE4RYEYYG7CVNKQ":3,"skill-same:01M794VBTCADE4RYEYYG7CVNKQ":75},{"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},"01M794VBTCADE4RYEYYG7CVNKQ","onnx-and-browser",null,"Export Segment Anything's prompt encoder and mask decoder to ONNX, quantize it, prepare matching image embeddings, and wire the model into ONNXRuntime or browser workflows.","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\u002Fsegment-anything\u002Fsub-skills\u002Fonnx-and-browser\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: onnx-and-browser\ndescription: \"Export Segment Anything's prompt encoder and mask decoder to ONNX,\n  quantize it, prepare matching image embeddings, and wire the model into\n  ONNXRuntime or browser workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# ONNX and Browser Workflows\n\nUse this sub-skill when the user asks to export SAM to ONNX, quantize a SAM ONNX model, run the mask decoder in ONNXRuntime Web, prepare a `.npy` image embedding for a browser demo, or diagnose ONNX\u002Fbrowser input shape issues.\n\n## Route First\n\n- For prompted Python inference with `SamPredictor.predict`, use `..\u002Fprompted-segmentation\u002F` unless ONNX export or embeddings are part of the request.\n- For full-image automatic mask generation with `SamAutomaticMaskGenerator`, use `..\u002Fautomatic-mask-generation\u002F`.\n- For browser workflows, export both a mask decoder ONNX file and image embeddings produced by the same checkpoint\u002Fmodel type\u002Fimage preprocessing path.\n\n## Fast Paths\n\n- Export ONNX with `python sub-skills\u002Fonnx-and-browser\u002Fscripts\u002Fexport_onnx_model.py --checkpoint sam_vit_h_4b8939.pth --model-type vit_h --output sam_onnx.onnx`.\n- Quantize for browser size\u002Fruntime with `--quantize-out sam_onnx_quantized.onnx`; this requires `onnxruntime` because quantization uses ONNXRuntime tooling.\n- Prepare a matching embedding by adapting `scripts\u002Fprepare_embedding_template.py`; save the `.npy` beside the browser image asset.\n- In browser feeds, use input names `image_embeddings`, `point_coords`, `point_labels`, `mask_input`, `has_mask_input`, and `orig_im_size`.\n\n## References\n\n- `references\u002Fonnx-export.md` explains export flags, tensor contracts, dynamic axes, quantization, and embedding compatibility.\n- `references\u002Fbrowser-demo.md` explains browser asset layout, ONNXRuntime Web feeds, scaling, and SharedArrayBuffer headers.\n- `references\u002Fapi-reference.md` summarizes `SamOnnxModel`, export-script behavior, input\u002Foutput names, and expected shapes.\n- `references\u002Ftroubleshooting.md` maps common export\u002Fruntime\u002Fbrowser errors to concrete fixes.\n\n## Bundled Scripts\n\n- `scripts\u002Fexport_onnx_model.py` is an adapted export helper with safe `--help` behavior and clearer optional-dependency errors.\n- `scripts\u002Fprepare_embedding_template.py` is a template for exporting a `.npy` image embedding from `SamPredictor` for ONNX\u002Fbrowser use.\n","# ONNX and Browser Workflows\n\nUse this sub-skill when the user asks to export SAM to ONNX, quantize a SAM ONNX model, run the mask decoder in ONNXRuntime Web, prepare a `.npy` image embedding for a browser demo, or diagnose ONNX\u002Fbrowser input shape issues.\n\n## Route First\n\n- For prompted Python inference with `SamPredictor.predict`, use `..\u002Fprompted-segmentation\u002F` unless ONNX export or embeddings are part of the request.\n- For full-image automatic mask generation with `SamAutomaticMaskGenerator`, use `..\u002Fautomatic-mask-generation\u002F`.\n- For browser workflows, export both a mask decoder ONNX file and image embeddings produced by the same checkpoint\u002Fmodel type\u002Fimage preprocessing path.\n\n## Fast Paths\n\n- Export ONNX with `python sub-skills\u002Fonnx-and-browser\u002Fscripts\u002Fexport_onnx_model.py --checkpoint sam_vit_h_4b8939.pth --model-type vit_h --output sam_onnx.onnx`.\n- Quantize for browser size\u002Fruntime with `--quantize-out sam_onnx_quantized.onnx`; this requires `onnxruntime` because quantization uses ONNXRuntime tooling.\n- Prepare a matching embedding by adapting `scripts\u002Fprepare_embedding_template.py`; save the `.npy` beside the browser image asset.\n- In browser feeds, use input names `image_embeddings`, `point_coords`, `point_labels`, `mask_input`, `has_mask_input`, and `orig_im_size`.\n\n## References\n\n- `references\u002Fonnx-export.md` explains export flags, tensor contracts, dynamic axes, quantization, and embedding compatibility.\n- `references\u002Fbrowser-demo.md` explains browser asset layout, ONNXRuntime Web feeds, scaling, and SharedArrayBuffer headers.\n- `references\u002Fapi-reference.md` summarizes `SamOnnxModel`, export-script behavior, input\u002Foutput names, and expected shapes.\n- `references\u002Ftroubleshooting.md` maps common export\u002Fruntime\u002Fbrowser errors to concrete fixes.\n\n## Bundled Scripts\n\n- `scripts\u002Fexport_onnx_model.py` is an adapted export helper with safe `--help` behavior and clearer optional-dependency errors.\n- `scripts\u002Fprepare_embedding_template.py` is a template for exporting a `.npy` image embedding from `SamPredictor` for ONNX\u002Fbrowser use.\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\u002Fsegment-anything\u002Fsub-skills\u002Fonnx-and-browser",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 onnx-and-browser",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill onnx-and-browser",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill onnx-and-browser","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fonnx-and-browser\u002FSKILL.md",[47,53,57,61,65,71],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",2696,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fonnx-and-browser\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fbrowser-demo.md",3058,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fonnx-and-browser\u002Freferences\u002Fbrowser-demo.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fonnx-export.md",3529,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fonnx-and-browser\u002Freferences\u002Fonnx-export.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",2986,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fonnx-and-browser\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fexport_onnx_model.py","SCRIPT","脚本",7405,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fonnx-and-browser\u002Fscripts\u002Fexport_onnx_model.py",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fprepare_embedding_template.py",2820,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsegment-anything\u002Fsub-skills\u002Fonnx-and-browser\u002Fscripts\u002Fprepare_embedding_template.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]