[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AJ3F3NXDS7QP76KZ9EX5H":3,"skill-same:01M69AJ3F3NXDS7QP76KZ9EX5H":84},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M69AJ3F3NXDS7QP76KZ9EX5H","webgpu-local-testing",null,"Build and run ONNX Runtime WebGPU provider tests on Linux WITHOUT a real GPU, using a software Vulkan adapter (Mesa lavapipe). Use when you need to exercise WebGPU EP kernels off-Mac — the Linux webgpu CI leg is build-only, so software Vulkan is how you actually run WebGPU correctness tests locally. SCOPE - lavapipe only validates host-side enforce\u002Fshape bugs and MatMul-free kernels; any graph containing MatMul (including the expanded-Attention node tests) crashes lavapipe and runs ONLY on macOS-arm64 Metal, which is the source of truth for those. Covers install (dnf on Azure Linux), the --use_webgpu build flag, the onnxruntime_provider_test target, VK_ICD_FILENAMES, and the lavapipe MatMul crash gotcha.","microsoft\u002Fonnxruntime","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AGY0EW9AJXAH7HK223SQZ",22286,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fwebgpu-local-testing\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"webgpu","webgpu local testing","local","local testing","testing","how","when","which","vk","you","scope","host","free","only","install","node","exercise","ci","run","onnx","test","linux","vulkan","metal","macos","2026-11-10 10:12:30",false,"---\nname: webgpu-local-testing\ndescription: \"Build and run ONNX Runtime WebGPU provider tests on Linux WITHOUT a real GPU, using a software Vulkan adapter (Mesa lavapipe). Use when you need to exercise WebGPU EP kernels off-Mac — the Linux webgpu CI leg is build-only, so software Vulkan is how you actually run WebGPU correctness tests locally. SCOPE - lavapipe only validates host-side enforce\u002Fshape bugs and MatMul-free kernels; any graph containing MatMul (including the expanded-Attention node tests) crashes lavapipe and runs ONLY on macOS-arm64 Metal, which is the source of truth for those. Covers install (dnf on Azure Linux), the --use_webgpu build flag, the onnxruntime_provider_test target, VK_ICD_FILENAMES, and the lavapipe MatMul crash gotcha.\"\n---\n\n# Running ONNX Runtime WebGPU Tests Locally on Linux (No GPU)\n\nReusable knowledge for exercising the **WebGPU execution provider** on a Linux box\nwith no physical GPU.\n\n> **Scope**: Linux ORT WebGPU only. macOS uses the Metal backend and a real GPU;\n> this skill is the off-Mac story for running WebGPU EP kernels in CI-less dev loops.\n\n## 1. Why software Vulkan is enough\n\nOn Linux, ORT's WebGPU EP runs on **Dawn** with the **Vulkan** backend. Vulkan does\nnot require a hardware GPU — **Mesa lavapipe** is a software (CPU) Vulkan adapter that\nDawn enumerates like any other device. For **EP correctness tests** this is sufficient\nbecause:\n\n- Many host-side validation paths (shape\u002Fbroadcast checks, `ORT_ENFORCE`s) fire\n  **before** any shader is dispatched. E.g. the WebGPU broadcast `ORT_ENFORCE` runs\n  host-side, so the failure is observable on a software adapter without ever touching\n  the GPU.\n- Element-wise and broadcasting kernels that do dispatch run correctly (if slowly) on\n  lavapipe, so their numeric output can be validated against the CPU reference.\n\nYou are trading speed for not needing hardware. It is **not** a substitute for a real\nGPU on perf-sensitive or driver-specific paths — but for kernel correctness it is the\npractical local loop.\n\n> **Scope — what lavapipe can and cannot validate.** Software Vulkan covers (a)\n> **host-side** failures (shape\u002Fbroadcast `ORT_ENFORCE`s that fire *before* any shader\n> dispatch) and (b) **MatMul-free** kernels that dispatch. It does **NOT** cover any\n> graph that contains a **MatMul** — the MatMul family crashes lavapipe's LLVM JIT (see\n> §5). This explicitly includes the motivating expanded-Attention node tests\n> (`test_attention_4d_softcap_neginf_mask_expanded`): they decompose to\n> `softmax(Q·Kᵀ + bias)·V`, which **contains MatMuls**, so they **cannot run on\n> lavapipe**. For those, **macOS-arm64 Metal is the source of truth**. Concretely, the\n> #28969 WebGPU broadcast-underflow fix was validated on lavapipe via a standalone\n> Add-broadcast `OpTester` proxy (a host-side enforce\u002Fshape path) — **NOT** via the\n> expanded-Attention node test. **Never** run lavapipe green and conclude an\n> Attention\u002FMatMul fix is validated off-Mac.\n\n## 2. Install the software Vulkan stack (Azure Linux — use `dnf`, NOT `apt`)\n\n```bash\ndnf install -y mesa-vulkan-drivers vulkan-loader\n# optional, for sanity-checking the adapter:\ndnf install -y vulkan-tools && vulkaninfo | head\n```\n\n`mesa-vulkan-drivers` provides lavapipe; `vulkan-loader` provides the ICD loader.\nThe lavapipe ICD manifest lands at `\u002Fusr\u002Fshare\u002Fvulkan\u002Ficd.d\u002Flvp_icd.\u003Carch>.json` —\n`lvp_icd.x86_64.json` on x86_64, `lvp_icd.aarch64.json` on arm64. The examples below\nuse the x86_64 name; substitute your arch, or glob it:\n`VK_ICD_FILENAMES=$(echo \u002Fusr\u002Fshare\u002Fvulkan\u002Ficd.d\u002Flvp_icd.*.json)`.\n\n## 3. Build with `--use_webgpu`\n\n```bash\n.\u002Fbuild.sh --config Release --parallel --use_webgpu\n```\n\nSee the `ort-build` skill for general build phases and flags.\n\n## 4. Run the WebGPU provider tests\n\nWebGPU operator\u002Fkernel tests are **provider op tests** — they build into the\n`onnxruntime_provider_test` target (**NOT** `onnxruntime_test_all`; see the `ort-test`\nskill for the executable taxonomy). Point the Vulkan loader at the lavapipe ICD and\nselect a subset with `--gtest_filter`:\n\n```bash\ncd build\u002FLinux\u002FRelease\nVK_ICD_FILENAMES=\u002Fusr\u002Fshare\u002Fvulkan\u002Ficd.d\u002Flvp_icd.x86_64.json \\\n  .\u002Fonnxruntime_provider_test --gtest_filter=\"*WebGPU*\"\n```\n\n`VK_ICD_FILENAMES` forces Vulkan to load **only** lavapipe, so the run is\ndeterministic regardless of what else is installed.\n\n## 5. Gotcha: lavapipe crashes on the MatMul family\n\n`MathOpTest.MatMulFloatType` (and other MatMul-family tests) crash lavapipe with:\n\n```\nLLVM ERROR: Instruction Combining did not reach a fixpoint after 1 iterations\n```\n\nThis is a **pre-existing limitation of software Vulkan (Mesa lavapipe's LLVM JIT)**,\nnot an ORT bug. **Exclude the MatMul family** from broad lavapipe runs:\n\n```bash\nVK_ICD_FILENAMES=\u002Fusr\u002Fshare\u002Fvulkan\u002Ficd.d\u002Flvp_icd.x86_64.json \\\n  .\u002Fonnxruntime_provider_test --gtest_filter=\"*WebGPU*:-*MatMul*\"\n```\n\n## 6. Why this matters: the Linux webgpu CI leg is build-only\n\nThe Linux webgpu CI leg (`.github\u002Fworkflows\u002Flinux_webgpu.yml`) **only builds** — it does not run\nWebGPU kernels. A green Linux webgpu leg therefore does **not** mean any WebGPU test\nactually executed. The macOS-arm64 webgpu leg is the only CI leg that runs WebGPU\nbackend node tests. So a local lavapipe run is the practical way to **actually exercise\nWebGPU kernels off-Mac** before you push.\n\nBut mind the §1 scope: lavapipe covers host-side enforce\u002Fshape paths and **MatMul-free**\nkernels only. Any **MatMul-containing** graph — including the expanded-Attention node\ntests (`test_attention_4d_softcap_neginf_mask_expanded`) — crashes lavapipe and runs\n**only** on the macOS-arm64 Metal leg, which is the source of truth for those. A green\nlavapipe run never validates a MatMul\u002FAttention fix off-Mac.\n","# Running ONNX Runtime WebGPU Tests Locally on Linux (No GPU)\n\nReusable knowledge for exercising the **WebGPU execution provider** on a Linux box\nwith no physical GPU.\n\n> **Scope**: Linux ORT WebGPU only. macOS uses the Metal backend and a real GPU;\n> this skill is the off-Mac story for running WebGPU EP kernels in CI-less dev loops.\n\n## 1. Why software Vulkan is enough\n\nOn Linux, ORT's WebGPU EP runs on **Dawn** with the **Vulkan** backend. Vulkan does\nnot require a hardware GPU — **Mesa lavapipe** is a software (CPU) Vulkan adapter that\nDawn enumerates like any other device. For **EP correctness tests** this is sufficient\nbecause:\n\n- Many host-side validation paths (shape\u002Fbroadcast checks, `ORT_ENFORCE`s) fire\n  **before** any shader is dispatched. E.g. the WebGPU broadcast `ORT_ENFORCE` runs\n  host-side, so the failure is observable on a software adapter without ever touching\n  the GPU.\n- Element-wise and broadcasting kernels that do dispatch run correctly (if slowly) on\n  lavapipe, so their numeric output can be validated against the CPU reference.\n\nYou are trading speed for not needing hardware. It is **not** a substitute for a real\nGPU on perf-sensitive or driver-specific paths — but for kernel correctness it is the\npractical local loop.\n\n> **Scope — what lavapipe can and cannot validate.** Software Vulkan covers (a)\n> **host-side** failures (shape\u002Fbroadcast `ORT_ENFORCE`s that fire *before* any shader\n> dispatch) and (b) **MatMul-free** kernels that dispatch. It does **NOT** cover any\n> graph that contains a **MatMul** — the MatMul family crashes lavapipe's LLVM JIT (see\n> §5). This explicitly includes the motivating expanded-Attention node tests\n> (`test_attention_4d_softcap_neginf_mask_expanded`): they decompose to\n> `softmax(Q·Kᵀ + bias)·V`, which **contains MatMuls**, so they **cannot run on\n> lavapipe**. For those, **macOS-arm64 Metal is the source of truth**. Concretely, the\n> #28969 WebGPU broadcast-underflow fix was validated on lavapipe via a standalone\n> Add-broadcast `OpTester` proxy (a host-side enforce\u002Fshape path) — **NOT** via the\n> expanded-Attention node test. **Never** run lavapipe green and conclude an\n> Attention\u002FMatMul fix is validated off-Mac.\n\n## 2. Install the software Vulkan stack (Azure Linux — use `dnf`, NOT `apt`)\n\n```bash\ndnf install -y mesa-vulkan-drivers vulkan-loader\n# optional, for sanity-checking the adapter:\ndnf install -y vulkan-tools && vulkaninfo | head\n```\n\n`mesa-vulkan-drivers` provides lavapipe; `vulkan-loader` provides the ICD loader.\nThe lavapipe ICD manifest lands at `\u002Fusr\u002Fshare\u002Fvulkan\u002Ficd.d\u002Flvp_icd.\u003Carch>.json` —\n`lvp_icd.x86_64.json` on x86_64, `lvp_icd.aarch64.json` on arm64. The examples below\nuse the x86_64 name; substitute your arch, or glob it:\n`VK_ICD_FILENAMES=$(echo \u002Fusr\u002Fshare\u002Fvulkan\u002Ficd.d\u002Flvp_icd.*.json)`.\n\n## 3. Build with `--use_webgpu`\n\n```bash\n.\u002Fbuild.sh --config Release --parallel --use_webgpu\n```\n\nSee the `ort-build` skill for general build phases and flags.\n\n## 4. Run the WebGPU provider tests\n\nWebGPU operator\u002Fkernel tests are **provider op tests** — they build into the\n`onnxruntime_provider_test` target (**NOT** `onnxruntime_test_all`; see the `ort-test`\nskill for the executable taxonomy). Point the Vulkan loader at the lavapipe ICD and\nselect a subset with `--gtest_filter`:\n\n```bash\ncd build\u002FLinux\u002FRelease\nVK_ICD_FILENAMES=\u002Fusr\u002Fshare\u002Fvulkan\u002Ficd.d\u002Flvp_icd.x86_64.json \\\n  .\u002Fonnxruntime_provider_test --gtest_filter=\"*WebGPU*\"\n```\n\n`VK_ICD_FILENAMES` forces Vulkan to load **only** lavapipe, so the run is\ndeterministic regardless of what else is installed.\n\n## 5. Gotcha: lavapipe crashes on the MatMul family\n\n`MathOpTest.MatMulFloatType` (and other MatMul-family tests) crash lavapipe with:\n\n```\nLLVM ERROR: Instruction Combining did not reach a fixpoint after 1 iterations\n```\n\nThis is a **pre-existing limitation of software Vulkan (Mesa lavapipe's LLVM JIT)**,\nnot an ORT bug. **Exclude the MatMul family** from broad lavapipe runs:\n\n```bash\nVK_ICD_FILENAMES=\u002Fusr\u002Fshare\u002Fvulkan\u002Ficd.d\u002Flvp_icd.x86_64.json \\\n  .\u002Fonnxruntime_provider_test --gtest_filter=\"*WebGPU*:-*MatMul*\"\n```\n\n## 6. Why this matters: the Linux webgpu CI leg is build-only\n\nThe Linux webgpu CI leg (`.github\u002Fworkflows\u002Flinux_webgpu.yml`) **only builds** — it does not run\nWebGPU kernels. A green Linux webgpu leg therefore does **not** mean any WebGPU test\nactually executed. The macOS-arm64 webgpu leg is the only CI leg that runs WebGPU\nbackend node tests. So a local lavapipe run is the practical way to **actually exercise\nWebGPU kernels off-Mac** before you push.\n\nBut mind the §1 scope: lavapipe covers host-side enforce\u002Fshape paths and **MatMul-free**\nkernels only. Any **MatMul-containing** graph — including the expanded-Attention node\ntests (`test_attention_4d_softcap_neginf_mask_expanded`) — crashes lavapipe and runs\n**only** on the macOS-arm64 Metal leg, which is the source of truth for those. A green\nlavapipe run never validates a MatMul\u002FAttention fix off-Mac.\n",{"name":5,"description":7},"main","4edd78a847b9d7755f32d6c99aa60cab2addd39b",".github\u002Fskills\u002Fwebgpu-local-testing",4439,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime","https:\u002F\u002Fonnxruntime.ai","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-12 03:12:39",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add microsoft\u002Fonnxruntime --skill webgpu-local-testing",{"tool":70,"command":71},"bunx","bunx skills add microsoft\u002Fonnxruntime --skill webgpu-local-testing",{"tool":73,"command":74},"pnpm","pnpm dlx skills add microsoft\u002Fonnxruntime --skill webgpu-local-testing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fwebgpu-local-testing\u002FSKILL.md",true,[78],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"resolve-canvas-launch.mjs","SCRIPT","脚本",2379,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-dev-tools\u002Fblob\u002Fmain\u002Fcanvases\u002Fazure-functions-hosted-skills\u002Fskills\u002Fazure-functions-hosted-skills-github-daily-digest\u002Fresolve-canvas-launch.mjs",[85,115,139,158,174,198],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":96,"publishedAt":49},"01M69AJ65WPPT5DS4JA8YWN37B","workspace-estimation-shared-header","Use when editing a boundary-safe shared header meant to be included by both in-tree and shared-provider\u002Fplugin-bridge code (e.g. include\u002Fonnxruntime\u002Fcore\u002Fframework\u002Fworkspace_requirement.h, or any future header supporting OrtKernelWorkspaceEstimateFunc \u002F DeclareWorkspaceRequirements per issue #29775's Phase-A workspace-estimation roadmap), or when a workspace-estimation math helper needs to be callable from a future plugin EP DLL. Covers a Node forward-declaration ODR trap and the math-helper vs. graph-parsing-wrapper reuse boundary discovered while implementing PR #29811 (MatMulNBits pilot).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fworkspace-estimation-shared-header\u002FSKILL.md",[91],{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[97,98,99,100,101,102,103,104,105,106,39,107,108,109,110,111,112,113,114,30],"workspace estimation shared header","workspace","estimation","shared","safe","pr","code","framework","graph","parsing","math","bridge","roadmap","Wrapper","issue","tree","implementing","phase",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":49},"01M69AJ1ASRSCJ90HDWN05TW82","python-kwargs-setattr-security","When reviewing or fixing Python code that uses setattr() with user-controlled kwargs to configure C++ extension objects (SessionOptions, RunOptions, etc.) in ONNX Runtime. Use this to apply the allowlist pattern that prevents arbitrary file writes and other attacks via reflected property access.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpython-kwargs-setattr-security\u002FSKILL.md",[],[122,123,124,43,103,125,126,127,128,129,130,131,132,133,134,135,136,137,138,30],"python","security","python kwargs setattr security","file","access","configure","use","objects","pattern","c++","runtime","extension","via","with","attacks","python code","apply",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":49},"01M69AHZ0M0Q90TP0KYMZ10HEP","ort-transformers-gpu-pytest","Run the ONNX Runtime transformers Python tests (onnxruntime\u002Ftest\u002Fpython\u002Ftransformers) against a GPU wheel, and confirm real cuDNN\u002Fflash SDPA dispatch. Use when a transformers pytest fails with ModuleNotFoundError onnxruntime.capi, when torch's bundled CUDA\u002FcuDNN libs shadow the ORT-built ones (wrong-version dispatch or load errors), or when you must PROVE a test exercised the cuDNN SDPA decode tier instead of silently skipping\u002Ffalling back to MATH.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fort-transformers-gpu-pytest\u002FSKILL.md",[],[146,147,148,149,122,44,43,42,150,107,128,151,132,152,153,33,154,155,156,157,30],"ort transformers gpu pytest","gpu","Transformers","pytest","flash","back","tests","SDPA","errors","load","prove","decode",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":165,"publishedAt":49},"01M69AHW3EFVHBHB2S7103YA21","ort-test","Run ONNX Runtime tests. Use this skill when asked to run tests, debug test failures, or find and execute specific test cases in ONNX Runtime.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fort-test\u002FSKILL.md",[164],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[44,166,167,168,169,43,170,42,171,172,128,132,152,173,30],"ort test","run tests","debug","debug test","debug test failures","find","execute","test cases",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":49},"01M69AHSKXBSERP5NGAJB5E6XD","ort-release-notes","Draft ONNX Runtime release notes using preset configurations for full ORT or scoped component releases. Use when generating highlights with PR links, compiling human contributor acknowledgments from compile_contributors.py output, and applying preset path filtering.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fort-release-notes\u002FSKILL.md",[],[181,182,183,184,185,186,43,102,187,188,189,190,191,192,132,193,194,195,196,197,30],"notes","ort release notes","release notes","release","component","preset","compile","compiling","contributors","releases","human","full","links","path","for","scoped","contributor",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":207,"publishedAt":49},"01M69AHQAPER0CRAZ0FTX0G2FT","ort-lint","Lint and format ONNX Runtime code. Use this skill when asked to lint, format, or check code style for C++ or Python files in ONNX Runtime.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fort-lint\u002FSKILL.md",[204],{"categoryNo":205,"categoryName":206,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",[208,209,122,210,43,103,211,212,128,213,131,132,214,195,30],"ort lint","lint","code style","format","check","files","style"]