Repository
microsoft/onnxruntime agent skills
- skills
- 14
- official
- 14
- GitHub stars
- 22k
GitHub description: “ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator”
- Stars
- 22,029 (4,282 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Nov 2018
- Homepage
- onnxruntime.ai
- deep-learning
- onnx
- neural-networks
- machine-learning
- ai-framework
- hardware-acceleration
- pytorch
- tensorflow
- scikit-learn
Install all skills
npx skills add microsoft/onnxruntimeAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in microsoft/onnxruntime, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Finds and fixes out-of-range output writes in ONNX Runtime operator shape-inference functions where a getNumOutputs guard admits too few outputs. | microsoft/ | 22k | — | ~3.3k | Automated safety check: Pass | MIT | today |
| 2 | Explains why editing CUTLASS fused-MHA headers in ONNX Runtime can leave stale CUDA kernels after an incremental build, and how to force and verify a real rebuild. | microsoft/ | 22k | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 3 | Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands. | microsoft/ | 22k | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 4 | Triggers, re-runs and unblocks the CI checks on an ONNX Runtime pull request, after diagnosing whether a failure is transient or needs a code change. | microsoft/ | 22k | — | ~4.1k | Automated safety check: Pass | MIT | today |
| 5 | Drafts ONNX Runtime release notes from commit history and contributor metadata using named presets for the full runtime or a scoped component. | microsoft/ | 22k | — | ~1.6k | Automated safety check: Pass | MIT | today |
| 6 | Runs and debugs ONNX Runtime tests: Google Test executables for C++ and unittest or pytest for Python, with filters and build-directory guidance. | microsoft/ | 22k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 7 | Runs the ONNX Runtime transformers Python tests against a GPU wheel and proves the cuDNN flash attention path was used rather than a silent fallback. | microsoft/ | 22k | — | ~2.9k | Automated safety check: Pass | MIT | today |
| 8 | Shows how to replace unsafe hasattr and setattr loops over user-controlled kwargs with an explicit allowlist when configuring ONNX Runtime option objects. | microsoft/ | 22k | — | ~737 | Automated safety check: Pass | MIT | today |
| 9 | Shows how to build and run ONNX Runtime WebGPU provider tests on Linux with no GPU, using the Mesa lavapipe software Vulkan adapter, and where that approach falls short. | microsoft/ | 22k | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 10 | Patterns and pitfalls for the ONNX-domain Attention operator's CUDA implementation in ONNX Runtime: dispatch cascade, eligibility limits, mask and bias kernels, and test routing. | microsoft/ | 22k | — | ~6.5k | Automated safety check: Pass | MIT | today |
| 11 | A checklist for upgrading the pinned ONNX version and opset in ONNX Runtime, covering the files to change, archive hashes, patch rebasing and release-candidate handling. | microsoft/ | 22k | — | ~12k | Automated safety check: Pass | MIT | today |
| 12 | Lints and formats C++ and Python code in the ONNX Runtime repository with lintrunner, clang-format and ruff, preferring a pass over only the changed files. | microsoft/ | 22k | — | ~392 | Automated safety check: Pass | MIT | today |
| 13 | Pitfalls for editing an ONNX Runtime header shared by in-tree and plugin-bridge code: the Node forward-declaration trap and keeping workspace math free of graph types. | microsoft/ | 22k | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 14 | Review ONNX Runtime pull requests, branches, commits, patches, and working-tree changes for actionable findings and missing tests. | microsoft/ | 22k | — | ~486 | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill in microsoft/onnxruntime?
ONNX Runtime Shape Inference Safety Audit (official) from microsoft/onnxruntime ranks first of the 14 skills in microsoft/onnxruntime listed here, with the highest score: its repository has 22k GitHub stars, its SKILL.md loads about 3.3k tokens and it passes the automated safety check with no findings. Next come CUTLASS FMHA Incremental Rebuild and ONNX Runtime Source Build.
Are the skills in microsoft/onnxruntime official?
14 of the 14 skills in microsoft/onnxruntime are official, published by the vendor's own GitHub organization: ONNX Runtime Shape Inference Safety Audit, CUTLASS FMHA Incremental Rebuild, ONNX Runtime Source Build, ONNX Runtime CI Management, ONNX Runtime Release Notes and 9 more.
How do I install all skills from microsoft/onnxruntime?
Run npx skills add microsoft/onnxruntime in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.