[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AHSKXBSERP5NGAJB5E6XD":3,"skill-same:01M69AHSKXBSERP5NGAJB5E6XD":76},{"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":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M69AHSKXBSERP5NGAJB5E6XD","ort-release-notes",null,"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.","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\u002Fort-release-notes\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"notes","ort release notes","release notes","release","contributors","when","contributor","scoped","for","path","links","runtime","full","human","releases","component","compiling","compile","pr","onnx","preset","2026-11-10 10:12:30",false,"---\nname: ort-release-notes\ndescription: 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.\nargument-hint: \"preset base_ref target_ref [version] [output_dir]\"\n---\n\n# ONNX Runtime Release Notes\n\nUse this skill to produce a consistent release-note draft from commit history and contributor metadata.\n\n## When To Use\n\nUse this skill when you need to:\n\n- Draft release notes for a full ONNX Runtime release\n- Draft release notes for a scoped component (e.g., in-tree plugin EP) release\n- Select a release profile by preset name instead of manually supplying path\u002Fversion files\n- Add PR links to highlight bullets\n- Build a human-only contributor acknowledgment list from contributor metadata\n\n## Required Inputs\n\nCollect these inputs from the user or infer from context:\n\n1. `preset`: release profile name (for example, `ort`, `webgpu-plugin-ep`, `cuda-plugin-ep`)\n2. `base_ref`: previous release tag\n3. `target_ref`: release commit\u002Ftag\u002Fbranch tip\n\nOptional inputs:\n\n- `version` override\n- `output_dir` override\n\n## Presets\n\nRead preset definitions from [presets.json](.\u002Fpresets.json).\n\nThe config defines shared output defaults:\n\n1. `outputDirPattern`\n2. `draftFileName`\n\nEach preset defines:\n\n1. `displayName`: reader-facing product or component name\n2. `versionFile`\n3. `pathsFile` (nullable): file of git pathspecs to filter to, one per line. Use `:(top)` to anchor an entry at repo root.\n\nExample presets:\n\n1. `ort` (full ONNX Runtime)\n2. `webgpu-plugin-ep` (scoped WebGPU Plugin EP)\n3. `cuda-plugin-ep` (scoped CUDA Plugin EP)\n\n### CUDA Plugin EP Scope\n\nThe `cuda-plugin-ep` preset uses the pathspecs in `plugin-ep-cuda\u002Fpaths.txt` to scope release-note changes.\n\n## Workflow\n\n1. Determine release mode.\n   - Select preset and load configuration from [presets.json](.\u002Fpresets.json).\n   - Use the preset's `displayName` whenever the release-note content names the product or component. The preset\n     key is internal and must not appear in published content.\n   - If preset has `pathsFile`, run in scoped mode. Otherwise run full mode.\n2. Resolve version, in this order:\n   1. explicit `version` input\n   2. value from preset `versionFile`\n3. Resolve output directory, referred to as `resolved_output_dir` after this step.\n   The output directory contains contributor artifacts and the release notes draft.\n   Resolve it in this order:\n   1. explicit `output_dir` input\n   2. shared `outputDirPattern` rendered with preset name and resolved version\n4. Gather metadata.\n   - If the output directory is missing or lacks contributor artifacts, generate them with\n     `tools\u002Fpython\u002Fcompile_contributors.py`.\n   - Generation can take a while because it scans commit history and fetches PR metadata.\n   - Use `--paths-file` only when preset has a `pathsFile`.\n   - If existing contributor artifacts are reused, verify `resolved_output_dir\u002Flogs.txt` matches base\u002Ftarget before trusting them.\n5. Read `resolved_output_dir\u002Fdetail.csv` as the primary source for PR numbers, titles, authors, target commits, and cherry-pick mapping.\n   - Use `resolved_output_dir\u002Flogs.txt` for contributor summary context and base\u002Ftarget verification.\n   - Use `git log` only as a fallback sanity check when artifacts are present but incomplete or suspect.\n    - Check PRs with unexpectedly large author lists for rebased history that imported unrelated commits. Replace those\n       authors with the actual PR author or authors before building contributor acknowledgments; do not credit authors\n       solely because they authored an unrelated imported commit. For example, PR #28299, the rebased history contains unrelated commits and co-author metadata.\n6. Build highlight categories.\n   - Full ORT example categories: performance, model\u002Foperator support, execution providers, API\u002Flanguages,\n     reliability\u002Fsecurity, build\u002Fpackaging\u002Ftooling, docs\u002Fdev workflow.\n   - Scoped mode: narrow categories to the component domain.\n7. Draft markdown.\n   - Write the release-note draft to `resolved_output_dir\u002F\u003CdraftFileName>`.\n   - Contents:\n     - Intro sentence\n     - `## Highlights`\n     - Inline PR links on every highlight bullet\n     - `## Contributors`\n     - Optional scope note for scoped-component releases\n       - Use the preset's reader-facing `displayName`, not the internal preset key.\n       - Describe the scope in reader-facing terms, such as \"commits affecting WebGPU Plugin EP code and\n         packaging.\"\n     - AI disclaimer if AI drafted\n   - Do not mention presets, `pathsFile`, configuration files, or other release-note-generation implementation\n     details in the release-note content.\n   - Do not refer to the release notes as a \"draft\" in their content. \"Draft\" is only an internal workflow\n     and file-naming concept.\n8. Build contributors section.\n   - Start from `detail.csv` output\n   - Include humans only\n   - Exclude bots\u002Fagents (for example: `github-actions[bot]`, `app\u002Fcopilot-swe-agent`, `claude`)\n   - Sort alphabetically\n9. Validate draft quality.\n   - Every highlight bullet has at least one PR link\n   - PRs are traceable to metadata or git history\n   - Contributor list is human-only and alphabetical\n   - Scope is correct for full vs component release\n\n## PowerShell Command Patterns\n\n### compile_contributors.py\n\nFull ORT metadata:\n\n```powershell\npython .\\tools\\python\\compile_contributors.py \\\n  --base \u003Cprevious_tag> \\\n  --target \u003Ctarget_ref> \\\n  --dir \u003Cresolved_output_dir>\n```\n\nScoped metadata:\n\n```powershell\npython .\\tools\\python\\compile_contributors.py \\\n   --base \u003Cprevious_tag> \\\n   --target \u003Ctarget_ref> \\\n   --dir \u003Cresolved_output_dir> \\\n   --paths-file \u003Cpaths_file>\n```\n\n## Style and Policy\n\nDefault policy unless release owners override:\n\n1. Treat the range as changes since the previous release.\n2. Keep PR links inline with highlight claims.\n3. Keep contributor acknowledgments human-only and best effort.\n4. Include an AI disclaimer when highlights are AI drafted.\n5. Use GitHub Releases pages as preferred style references.\n   E.g., [ORT 1.28 release page](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Freleases\u002Ftag\u002Fv1.28.0).\n6. Prefer preset-driven configuration over ad-hoc path\u002Fversion arguments.\n7. Use a single `output_dir` for contributor artifacts, logs, and the release-note draft.\n","# ONNX Runtime Release Notes\n\nUse this skill to produce a consistent release-note draft from commit history and contributor metadata.\n\n## When To Use\n\nUse this skill when you need to:\n\n- Draft release notes for a full ONNX Runtime release\n- Draft release notes for a scoped component (e.g., in-tree plugin EP) release\n- Select a release profile by preset name instead of manually supplying path\u002Fversion files\n- Add PR links to highlight bullets\n- Build a human-only contributor acknowledgment list from contributor metadata\n\n## Required Inputs\n\nCollect these inputs from the user or infer from context:\n\n1. `preset`: release profile name (for example, `ort`, `webgpu-plugin-ep`, `cuda-plugin-ep`)\n2. `base_ref`: previous release tag\n3. `target_ref`: release commit\u002Ftag\u002Fbranch tip\n\nOptional inputs:\n\n- `version` override\n- `output_dir` override\n\n## Presets\n\nRead preset definitions from [presets.json](.\u002Fpresets.json).\n\nThe config defines shared output defaults:\n\n1. `outputDirPattern`\n2. `draftFileName`\n\nEach preset defines:\n\n1. `displayName`: reader-facing product or component name\n2. `versionFile`\n3. `pathsFile` (nullable): file of git pathspecs to filter to, one per line. Use `:(top)` to anchor an entry at repo root.\n\nExample presets:\n\n1. `ort` (full ONNX Runtime)\n2. `webgpu-plugin-ep` (scoped WebGPU Plugin EP)\n3. `cuda-plugin-ep` (scoped CUDA Plugin EP)\n\n### CUDA Plugin EP Scope\n\nThe `cuda-plugin-ep` preset uses the pathspecs in `plugin-ep-cuda\u002Fpaths.txt` to scope release-note changes.\n\n## Workflow\n\n1. Determine release mode.\n   - Select preset and load configuration from [presets.json](.\u002Fpresets.json).\n   - Use the preset's `displayName` whenever the release-note content names the product or component. The preset\n     key is internal and must not appear in published content.\n   - If preset has `pathsFile`, run in scoped mode. Otherwise run full mode.\n2. Resolve version, in this order:\n   1. explicit `version` input\n   2. value from preset `versionFile`\n3. Resolve output directory, referred to as `resolved_output_dir` after this step.\n   The output directory contains contributor artifacts and the release notes draft.\n   Resolve it in this order:\n   1. explicit `output_dir` input\n   2. shared `outputDirPattern` rendered with preset name and resolved version\n4. Gather metadata.\n   - If the output directory is missing or lacks contributor artifacts, generate them with\n     `tools\u002Fpython\u002Fcompile_contributors.py`.\n   - Generation can take a while because it scans commit history and fetches PR metadata.\n   - Use `--paths-file` only when preset has a `pathsFile`.\n   - If existing contributor artifacts are reused, verify `resolved_output_dir\u002Flogs.txt` matches base\u002Ftarget before trusting them.\n5. Read `resolved_output_dir\u002Fdetail.csv` as the primary source for PR numbers, titles, authors, target commits, and cherry-pick mapping.\n   - Use `resolved_output_dir\u002Flogs.txt` for contributor summary context and base\u002Ftarget verification.\n   - Use `git log` only as a fallback sanity check when artifacts are present but incomplete or suspect.\n    - Check PRs with unexpectedly large author lists for rebased history that imported unrelated commits. Replace those\n       authors with the actual PR author or authors before building contributor acknowledgments; do not credit authors\n       solely because they authored an unrelated imported commit. For example, PR #28299, the rebased history contains unrelated commits and co-author metadata.\n6. Build highlight categories.\n   - Full ORT example categories: performance, model\u002Foperator support, execution providers, API\u002Flanguages,\n     reliability\u002Fsecurity, build\u002Fpackaging\u002Ftooling, docs\u002Fdev workflow.\n   - Scoped mode: narrow categories to the component domain.\n7. Draft markdown.\n   - Write the release-note draft to `resolved_output_dir\u002F\u003CdraftFileName>`.\n   - Contents:\n     - Intro sentence\n     - `## Highlights`\n     - Inline PR links on every highlight bullet\n     - `## Contributors`\n     - Optional scope note for scoped-component releases\n       - Use the preset's reader-facing `displayName`, not the internal preset key.\n       - Describe the scope in reader-facing terms, such as \"commits affecting WebGPU Plugin EP code and\n         packaging.\"\n     - AI disclaimer if AI drafted\n   - Do not mention presets, `pathsFile`, configuration files, or other release-note-generation implementation\n     details in the release-note content.\n   - Do not refer to the release notes as a \"draft\" in their content. \"Draft\" is only an internal workflow\n     and file-naming concept.\n8. Build contributors section.\n   - Start from `detail.csv` output\n   - Include humans only\n   - Exclude bots\u002Fagents (for example: `github-actions[bot]`, `app\u002Fcopilot-swe-agent`, `claude`)\n   - Sort alphabetically\n9. Validate draft quality.\n   - Every highlight bullet has at least one PR link\n   - PRs are traceable to metadata or git history\n   - Contributor list is human-only and alphabetical\n   - Scope is correct for full vs component release\n\n## PowerShell Command Patterns\n\n### compile_contributors.py\n\nFull ORT metadata:\n\n```powershell\npython .\\tools\\python\\compile_contributors.py \\\n  --base \u003Cprevious_tag> \\\n  --target \u003Ctarget_ref> \\\n  --dir \u003Cresolved_output_dir>\n```\n\nScoped metadata:\n\n```powershell\npython .\\tools\\python\\compile_contributors.py \\\n   --base \u003Cprevious_tag> \\\n   --target \u003Ctarget_ref> \\\n   --dir \u003Cresolved_output_dir> \\\n   --paths-file \u003Cpaths_file>\n```\n\n## Style and Policy\n\nDefault policy unless release owners override:\n\n1. Treat the range as changes since the previous release.\n2. Keep PR links inline with highlight claims.\n3. Keep contributor acknowledgments human-only and best effort.\n4. Include an AI disclaimer when highlights are AI drafted.\n5. Use GitHub Releases pages as preferred style references.\n   E.g., [ORT 1.28 release page](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Freleases\u002Ftag\u002Fv1.28.0).\n6. Prefer preset-driven configuration over ad-hoc path\u002Fversion arguments.\n7. Use a single `output_dir` for contributor artifacts, logs, and the release-note draft.\n",{"name":5,"description":7,"argument-hint":45},"preset base_ref target_ref [version] [output_dir]","main","4edd78a847b9d7755f32d6c99aa60cab2addd39b",".github\u002Fskills\u002Fort-release-notes",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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add microsoft\u002Fonnxruntime --skill ort-release-notes",{"tool":62,"command":63},"bunx","bunx skills add microsoft\u002Fonnxruntime --skill ort-release-notes",{"tool":65,"command":66},"pnpm","pnpm dlx skills add microsoft\u002Fonnxruntime --skill ort-release-notes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fort-release-notes\u002FSKILL.md",true,[70],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"presets.json","REFERENCE","参考文档",652,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fort-release-notes\u002Fpresets.json",[77,107,141,164,183,199],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":88,"publishedAt":40},"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",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[89,90,91,92,93,37,94,95,96,97,98,99,100,101,102,103,104,105,106,24],"workspace estimation shared header","workspace","estimation","shared","safe","code","framework","graph","parsing","node","math","bridge","roadmap","Wrapper","issue","tree","implementing","phase",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":118,"publishedAt":40},"01M69AJ3F3NXDS7QP76KZ9EX5H","webgpu-local-testing","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.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fonnxruntime\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fwebgpu-local-testing\u002FSKILL.md",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[119,120,121,122,123,124,125,126,127,128,38,129,130,131,132,98,133,134,135,136,137,138,139,140,24],"testing","webgpu","webgpu local testing","local testing","local","macos","metal","vulkan","linux","test","run","ci","exercise","how","install","only","free","host","scope","you","vk","which",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":40},"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",[],[148,149,150,38,94,151,152,153,154,155,156,157,30,158,159,160,161,162,163,24],"python","security","python kwargs setattr security","file","access","configure","use","objects","pattern","c++","extension","via","with","attacks","python code","apply",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":170,"publishedAt":40},"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",[],[171,172,173,174,148,128,38,129,175,99,154,176,30,177,178,138,179,180,181,182,24],"ort transformers gpu pytest","gpu","Transformers","pytest","flash","back","tests","SDPA","errors","load","prove","decode",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":190,"publishedAt":40},"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",[189],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},[128,191,192,193,194,38,195,129,196,197,154,30,177,198,24],"ort test","run tests","debug","debug test","debug test failures","find","execute","test cases",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":208,"publishedAt":40},"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",[205],{"categoryNo":206,"categoryName":207,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000007","代码审查",[209,210,148,211,38,94,212,213,154,214,157,30,215,27,24],"ort lint","lint","code style","format","check","files","style"]