[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792RCXMYDMEBBAVMQT60ARR":3,"skill-same:01M792RCXMYDMEBBAVMQT60ARR":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},"01M792RCXMYDMEBBAVMQT60ARR","conversion-and-deployment",null,"Plan PINTO_model_zoo model conversion, quantization, and backend deployment workflows from bundled catalog evidence and local script inspection.","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\u002Fpinto-model-zoo\u002Fsub-skills\u002Fconversion-and-deployment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: conversion-and-deployment\ndescription: \"Plan PINTO_model_zoo model conversion, quantization, and backend\n  deployment workflows from bundled catalog evidence and local script\n  inspection.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# conversion-and-deployment\n\nUse this sub-skill when the user asks how to convert, quantize, or deploy a\nPINTO_model_zoo model artifact across ONNX, TensorFlow\u002FSavedModel, TFLite,\nOpenVINO, CoreML, TensorFlow.js, TF-TRT, or EdgeTPU-oriented backends.\n\nTypical triggers:\n\n- \"convert this ONNX model to TFLite\u002FOpenVINO\u002FCoreML\u002FTFJS\"\n- \"make an INT8\u002Ffull-integer\u002FFP16\u002FTFLite\u002FEdgeTPU artifact\"\n- \"understand this quantization or conversion script\"\n- \"deploy this model on Raspberry Pi, OpenVINO CPU, browser TFJS, TF-TRT, or EdgeTPU\"\n- \"why do I need calibration data or a representative dataset?\"\n\n## Route before planning\n\n1. If the user has not selected a model, route model search and format\n   availability to `model-catalog` and the bundled catalog at\n   `..\u002F..\u002Freferences\u002Fmodel-catalog.json`.\n2. If a needed artifact is not present locally, route download\u002Fscript safety and\n   license checks to `model-acquisition` before proposing commands that fetch or\n   unpack files.\n3. If the user wants to run inference, benchmark, or smoke-test an artifact,\n   route execution planning to `inference-demos` after this skill identifies the\n   target backend and artifact constraints.\n4. Stay in this skill for conversion-chain selection, quantization requirements,\n   calibration gates, backend deployment preflight, and conversion-script\n   diagnosis.\n\n## Operating workflow\n\n1. **Pin the source and target.** Record current artifact family, desired target\n   family, precision goal, input shape\u002Flayout\u002Fcolor order, deployment hardware,\n   and whether network\u002Fdataset\u002Fhardware use is approved.\n2. **Prefer an existing zoo artifact.** If the catalog already lists the target\n   format flag for the selected model, advise using that artifact before\n   rebuilding it. Treat catalog flags as availability evidence, not proof that a\n   shallow checkout already contains the files.\n3. **Inspect local scripts without executing them.** Use\n   `scripts\u002Fclassify_conversion_script.py` on candidate `convert*.sh`,\n   `*quant*.py`, `*tflite*.py`, `*openvino*.py`, `*coreml*.py`, or similar files\n   in the selected model directory. The helper reports conversion families,\n   representative-dataset requirements, and dataset\u002Fnetwork\u002Fhardware risks.\n4. **Choose a recipe.** Use `references\u002Fconversion-recipes.md` for format-family\n   constraints, TFLite quantization modes, ONNX\u002FTensorFlow\u002FOpenVINO\u002FCoreML\u002FTFJS\u002F\n   TF-TRT chains, and calibration stop conditions.\n5. **Preflight the backend.** Use `references\u002Fdeployment-backends.md` for\n   Raspberry Pi\u002FTFLite, EdgeTPU, OpenVINO CPU, browser TFJS\u002FWebGL, TF-TRT\u002FGPU,\n   and CoreML deployment gates.\n6. **Stop instead of guessing** when required calibration data, network access,\n   large datasets, proprietary hardware, GPU\u002FEdgeTPU devices, or license approval\n   is absent. Provide the smallest safe next check and mark unverified hardware\n   claims explicitly.\n\n## Expected answer shape\n\nFor user-facing plans, return:\n\n- selected source artifact and target artifact family;\n- whether a catalog artifact already appears available;\n- conversion chain with required tools\u002Fenvironments named only at the family\n  level unless the selected folder supplies exact scripts;\n- calibration or representative-dataset requirements;\n- backend preflight and stop gates;\n- smoke-test handoff to `inference-demos` when execution is requested;\n- open risks from `references\u002Ftroubleshooting.md`.\n\n## Owned failure modes\n\nThis sub-skill owns troubleshooting for conversion, quantization, calibration,\nand backend deployment errors. Use `references\u002Ftroubleshooting.md` when symptoms\ninclude missing converter imports, unsupported TFLite\u002FEdgeTPU ops, representative\nsample mismatch, OpenVINO XML\u002FBIN mismatch, browser TFJS loading issues, TF-TRT\nGPU\u002Fruntime mismatch, or hardware-only verification claims.\n","# conversion-and-deployment\n\nUse this sub-skill when the user asks how to convert, quantize, or deploy a\nPINTO_model_zoo model artifact across ONNX, TensorFlow\u002FSavedModel, TFLite,\nOpenVINO, CoreML, TensorFlow.js, TF-TRT, or EdgeTPU-oriented backends.\n\nTypical triggers:\n\n- \"convert this ONNX model to TFLite\u002FOpenVINO\u002FCoreML\u002FTFJS\"\n- \"make an INT8\u002Ffull-integer\u002FFP16\u002FTFLite\u002FEdgeTPU artifact\"\n- \"understand this quantization or conversion script\"\n- \"deploy this model on Raspberry Pi, OpenVINO CPU, browser TFJS, TF-TRT, or EdgeTPU\"\n- \"why do I need calibration data or a representative dataset?\"\n\n## Route before planning\n\n1. If the user has not selected a model, route model search and format\n   availability to `model-catalog` and the bundled catalog at\n   `..\u002F..\u002Freferences\u002Fmodel-catalog.json`.\n2. If a needed artifact is not present locally, route download\u002Fscript safety and\n   license checks to `model-acquisition` before proposing commands that fetch or\n   unpack files.\n3. If the user wants to run inference, benchmark, or smoke-test an artifact,\n   route execution planning to `inference-demos` after this skill identifies the\n   target backend and artifact constraints.\n4. Stay in this skill for conversion-chain selection, quantization requirements,\n   calibration gates, backend deployment preflight, and conversion-script\n   diagnosis.\n\n## Operating workflow\n\n1. **Pin the source and target.** Record current artifact family, desired target\n   family, precision goal, input shape\u002Flayout\u002Fcolor order, deployment hardware,\n   and whether network\u002Fdataset\u002Fhardware use is approved.\n2. **Prefer an existing zoo artifact.** If the catalog already lists the target\n   format flag for the selected model, advise using that artifact before\n   rebuilding it. Treat catalog flags as availability evidence, not proof that a\n   shallow checkout already contains the files.\n3. **Inspect local scripts without executing them.** Use\n   `scripts\u002Fclassify_conversion_script.py` on candidate `convert*.sh`,\n   `*quant*.py`, `*tflite*.py`, `*openvino*.py`, `*coreml*.py`, or similar files\n   in the selected model directory. The helper reports conversion families,\n   representative-dataset requirements, and dataset\u002Fnetwork\u002Fhardware risks.\n4. **Choose a recipe.** Use `references\u002Fconversion-recipes.md` for format-family\n   constraints, TFLite quantization modes, ONNX\u002FTensorFlow\u002FOpenVINO\u002FCoreML\u002FTFJS\u002F\n   TF-TRT chains, and calibration stop conditions.\n5. **Preflight the backend.** Use `references\u002Fdeployment-backends.md` for\n   Raspberry Pi\u002FTFLite, EdgeTPU, OpenVINO CPU, browser TFJS\u002FWebGL, TF-TRT\u002FGPU,\n   and CoreML deployment gates.\n6. **Stop instead of guessing** when required calibration data, network access,\n   large datasets, proprietary hardware, GPU\u002FEdgeTPU devices, or license approval\n   is absent. Provide the smallest safe next check and mark unverified hardware\n   claims explicitly.\n\n## Expected answer shape\n\nFor user-facing plans, return:\n\n- selected source artifact and target artifact family;\n- whether a catalog artifact already appears available;\n- conversion chain with required tools\u002Fenvironments named only at the family\n  level unless the selected folder supplies exact scripts;\n- calibration or representative-dataset requirements;\n- backend preflight and stop gates;\n- smoke-test handoff to `inference-demos` when execution is requested;\n- open risks from `references\u002Ftroubleshooting.md`.\n\n## Owned failure modes\n\nThis sub-skill owns troubleshooting for conversion, quantization, calibration,\nand backend deployment errors. Use `references\u002Ftroubleshooting.md` when symptoms\ninclude missing converter imports, unsupported TFLite\u002FEdgeTPU ops, representative\nsample mismatch, OpenVINO XML\u002FBIN mismatch, browser TFJS loading issues, TF-TRT\nGPU\u002Fruntime mismatch, or hardware-only verification claims.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fconversion-and-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":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill conversion-and-deployment",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill conversion-and-deployment",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill conversion-and-deployment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fconversion-and-deployment\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fconversion-recipes.md","REFERENCE","参考文档",10347,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fconversion-and-deployment\u002Freferences\u002Fconversion-recipes.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdeployment-backends.md",5779,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fconversion-and-deployment\u002Freferences\u002Fdeployment-backends.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",5953,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fconversion-and-deployment\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fclassify_conversion_script.py","SCRIPT","脚本",11889,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fpinto-model-zoo\u002Fsub-skills\u002Fconversion-and-deployment\u002Fscripts\u002Fclassify_conversion_script.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",[],[]]