Embedded AI Deployment
matlab/agent-skills-playground
Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder).
Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands.
Install ONNX Runtime Source Build
$ npx skills add microsoft/onnxruntime --skill ort-build -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install microsoft/onnxruntime ort-build --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/microsoft/onnxruntime.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/ort-build .claude/skills/ort-build && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ort-build" agent skill from https://github.com/microsoft/onnxruntime/tree/main/.github/skills/ort-build into .claude/skills/ort-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ort-build", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/microsoft/onnxruntime/tree/main/.github/skills/ort-buildType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add microsoft/onnxruntime --skill ort-build -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install microsoft/onnxruntime ort-build --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/onnxruntime.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.github/skills/ort-build .agents/skills/ort-build && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ort-build" agent skill from https://github.com/microsoft/onnxruntime/tree/main/.github/skills/ort-build into .agents/skills/ort-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ort-build", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/onnxruntime --skill ort-build -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install microsoft/onnxruntime ort-build --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/onnxruntime.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.github/skills/ort-build .cursor/skills/ort-build && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ort-build" agent skill from https://github.com/microsoft/onnxruntime/tree/main/.github/skills/ort-build into .cursor/skills/ort-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ort-build", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/microsoft/onnxruntime.git --path .github/skills/ort-build--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add microsoft/onnxruntime --skill ort-build -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install microsoft/onnxruntime ort-build --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/onnxruntime.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.github/skills/ort-build .gemini/skills/ort-build && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ort-build" agent skill from https://github.com/microsoft/onnxruntime/tree/main/.github/skills/ort-build into .gemini/skills/ort-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ort-build", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install microsoft/onnxruntime ort-buildInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add microsoft/onnxruntime --skill ort-build -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/microsoft/onnxruntime.git skills-src && mkdir -p .github/skills && cp -r skills-src/.github/skills/ort-build .github/skills/ort-build && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ort-build" agent skill from https://github.com/microsoft/onnxruntime/tree/main/.github/skills/ort-build into .github/skills/ort-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ort-build", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add microsoft/onnxruntime --skill ort-build -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install microsoft/onnxruntime ort-build --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/microsoft/onnxruntime.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.github/skills/ort-build .opencode/skills/ort-build && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ort-build" agent skill from https://github.com/microsoft/onnxruntime/tree/main/.github/skills/ort-build into .opencode/skills/ort-build/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ort-build", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ort-build- GitHub stars
- 22k
- Token cost
- ~1.4k tokens
- SKILL.md length
- 518 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands.
- Compiling ONNX Runtime from a source checkout
- SKILL.md covers Build phases, Examples, Key flags and Build output path, plus 1 more section
- Calls python
- Regenerating CMake files after adding source files
What it does
The `build.sh` script for Linux and macOS and `build.bat` for Windows both hand off to `tools/ci_build/build.py`. Work is split into three phases set by flags: `--update` generates the CMake build files, `--build` compiles with an optional `--parallel`, and `--test` runs the tests. Native builds run all three by default unless `--skip_tests` is passed, while cross-compiled builds default to update and build only.
Rerunning `--update` is needed for a first build in a new directory, new source files and CMake changes, but not for edits to existing `.cc` and `.h` files. A table of key flags covers the `--config` choices, `--build_wheel`, `--use_cuda` with its CUDA and cuDNN home settings, `--use_webgpu`, building a single CMake `--target`, a quick-build define for faster CUDA builds and `--build_dir`. By default the output goes to a folder under `build/` named for the platform and configuration.
When your agent uses it
- Compiling ONNX Runtime from a source checkout
- Regenerating CMake files after adding source files
- Building a Python wheel or a CUDA-enabled ONNX Runtime
- Rebuilding a single CMake target to speed up iteration
Example prompts
- “Build ONNX Runtime in Release mode with parallel compilation and run the tests.”
- “I only edited a .cc file. What is the quickest way to rebuild?”
- “Build the Python wheel with CUDA enabled using my CUDA_HOME.”
- “Rebuild just the onnxruntime_test_all target.”
Requirements
- An ONNX Runtime source checkout
- CUDA and cuDNN install paths for CUDA builds
What it can do on your machine
Read from SKILL.md and the folder at commit 8420709. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
ONNX Runtime Source Build loads about 1.4k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 518 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from microsoft/onnxruntime at commit 8420709, republished under its MIT licence (© microsoft). 518 words, ~1,382 tokens.
Download SKILL.mdSave it as
.claude/skills/ort-build/SKILL.md (or your agent's skills folder).- name
- ort-build
- description
- Build ONNX Runtime from source. Use this skill when asked to build, compile, or generate CMake files for ONNX Runtime.
Building ONNX Runtime
The build scripts build.sh (Linux/macOS) and build.bat (Windows) delegate to tools/ci_build/build.py.
Build phases
Three phases, controlled by flags:
--update— generate CMake build files--build— compile (add--parallelto speed this up)--test— run tests
For native builds, if none are specified (and --skip_tests is not passed), all three run by default. For cross-compiled builds, the default is --update + --build only.
When to use --update
You need --update when:
- First build in a new build directory
- New source files are added (some CMake targets use glob patterns, others use explicit file lists — re-run to pick up new files either way)
- CMake configuration changes (new flags, updated CMakeLists.txt)
You do not need --update when only modifying existing .cc/.h files — just use --build. Skipping it saves time.
Examples
# Full build (update + build + test)
./build.sh --config Release --parallel
.\build.bat --config Release --parallel # Windows
# Just regenerate CMake files
./build.sh --config Release --update
# Just compile (skip CMake regeneration and tests)
./build.sh --config Release --build --parallel
# Just run tests (after a prior build)
./build.sh --config Release --test
# Build with CUDA execution provider
./build.sh --config Release --parallel --use_cuda --cuda_home /usr/local/cuda --cudnn_home /usr/local/cuda
# Configure and build the WebGPU execution provider as a shared library (Windows)
.\build.bat --config RelWithDebInfo --build_dir .\build\WGPU --use_webgpu --build_shared_lib --update --build --parallel
# Incrementally rebuild the same WebGPU configuration after changing existing source files
.\build.bat --config RelWithDebInfo --build_dir .\build\WGPU --use_webgpu --build_shared_lib --build --parallel
# Build Python wheel
./build.sh --config Release --parallel --build_wheel
# Build a specific CMake target (much faster than a full build)
./build.sh --config Release --build --parallel --target onnxruntime_common
# Load flags from an option file (one flag per line)
./build.sh "@./custom_options.opt" --build --parallelKey flags
| Flag | Description |
|---|---|
--config | Debug, MinSizeRel, Release, or RelWithDebInfo |
--parallel | Enable parallel compilation (recommended) |
--skip_tests | Skip running tests after build |
--build_wheel | Build the Python wheel package |
--use_cuda | Enable CUDA EP. Requires --cuda_home/--cudnn_home or CUDA_HOME/CUDNN_HOME env vars. On Windows, only cuda_home/CUDA_HOME is validated. |
--target T | Build a specific CMake target (requires --build; e.g., onnxruntime_common, onnxruntime_test_all) |
--use_webgpu | Enable WebGPU EP. To run its tests locally on Linux without a GPU, see the webgpu-local-testing skill. |
--cmake_extra_defines onnxruntime_QUICK_BUILD=ON | Faster CUDA build: instantiates a reduced kernel set. Side effect: Flash is compiled for head_dim 128 only, so most attention shapes fall back to MEA (changes which attention kernel is compiled/dispatched). Don't use it to characterize Flash-vs-arch behavior. |
--build_dir | Build output directory |
Build output path
Default: build/<Platform>/<Config>/ where Platform is Linux, MacOS, or Windows.
With Visual Studio multi-config generators, the config name appears twice (e.g., build/Windows/Release/Release/).
It may be customized with --build_dir.
For example, --build_dir .\build\WGPU --config RelWithDebInfo creates the CMake build tree at
build/WGPU/RelWithDebInfo/; Visual Studio places final binaries in its RelWithDebInfo/ subdirectory.
The --build_shared_lib flag in the WebGPU example is optional and is only needed when building the ONNX Runtime DLL.
Show full SKILL.md (202 more words)Show less
Agent tips
- Activate a Python virtual environment before building. See "Python > Virtual environment" in
AGENTS.md. - Build flags can silently reroute which kernel/code path executes. A build option can
change which kernel is compiled, and therefore which code path actually runs — so a CI
failure can live in a different code path than your local build exercises. Before
hypothesizing a hardware- or algorithm-specific cause (e.g. "this GPU arch miscomputes"),
first identify which kernel actually ran for the failing configuration (see the
ort-testskill → "Verify which path/kernel actually executed"). Concrete instance:onnxruntime_QUICK_BUILD=ONcompiles FlashAttention for head_dim 128 only, so most attention shapes silently dispatch to Memory-Efficient Attention instead of Flash — details in thecuda-attention-kernel-patternsskill. - Prefer
python tools/ci_build/build.pydirectly overbuild.bat/build.shwhen redirecting output. The.batwrapper runs incmd.exe, which breaks PowerShell redirection. - Redirect output to a file (e.g.,
> build_log.txt 2>&1). Build output is large and will overflow terminal buffers. - Run builds in the background — a full build can take tens of minutes to over an hour. Poll the log for
"Build complete"or errors. - Use
--parallelby default unless the user says otherwise. - Ask the user what they want to build (config, execution providers, wheel, etc.) if not clear from their prompt.
© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .github/skills/ort-build of microsoft/onnxruntime.
Open the folder on GitHubat commit 8420709
Compare with similar skills
ONNX Runtime Source Build next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| ONNX Runtime Source Build this skillmicrosoft/onnxruntime | 22k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Embedded AI Deploymentmatlab/agent-skills-playground | 181 | 1 repos | ~3.4k | Automated safety check: Pass | Custom licence | |
| Holoscan Install CondaNVIDIA/skills | 3.5k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Matlab Deploy Embedded AImajiayu000/claude-skill-registry | 666 | 1 repos | ~4.6k | Automated safety check: Pass | MIT | |
| The Art of Debuggingstas00/the-art-of-debugging | 1.7k | — | ~6.1k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| ExecuTorch Build Guidepytorch/executorch | 5.1k | — | ~2.3k | Automated safety check: Notes | Custom licence |
Similar skills
- Official
Holoscan Install Conda
NVIDIA/skills
Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment.
Matlab Deploy Embedded AI
majiayu000/claude-skill-registry
Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder).
The Art of Debugging
stas00/the-art-of-debugging
Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.
ExecuTorch Build Guide
pytorch/executorch
Builds ExecuTorch from source: the Python package, C++ runtime, model runners, Android and iOS cross-compilation and backend-specific builds, with environment checks.
Cutlass Cpp Kernel
vipshop/cache-dit
A skill your agent uses when writing, debugging, porting, reviewing, or optimizing CUTLASS or CuTe C++ kernels and templates; navigating CUTLASS examples, collectives, epilogues, pipelines, GEMM…
More from microsoft/onnxruntime
All 14 skills in this repo- Official
ONNX Runtime Shape Inference Safety Audit
microsoft/onnxruntime
Finds and fixes out-of-range output writes in ONNX Runtime operator shape-inference functions where a getNumOutputs guard admits too few outputs.
- Official
CUTLASS FMHA Incremental Rebuild
microsoft/onnxruntime
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.
- Official
ONNX Runtime CI Management
microsoft/onnxruntime
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.
- Official
ONNX Runtime Release Notes
microsoft/onnxruntime
Drafts ONNX Runtime release notes from commit history and contributor metadata using named presets for the full runtime or a scoped component.
- Official
ONNX Runtime Test Runner
microsoft/onnxruntime
Runs and debugs ONNX Runtime tests: Google Test executables for C++ and unittest or pytest for Python, with filters and build-directory guidance.
- Official
ONNX Runtime GPU Transformers Tests
microsoft/onnxruntime
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.
Related
Categories
Questions about ONNX Runtime Source Build
What does ONNX Runtime Source Build do?
Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands. py`. Work is split into three phases set by flags: `--update` generates the CMake build files, `--build` compiles with an optional `--parallel`, and `--test` runs the tests.
When should I use ONNX Runtime Source Build?
ONNX Runtime Source Build fits situations like: compiling ONNX Runtime from a source checkout; regenerating CMake files after adding source files; building a Python wheel or a CUDA-enabled ONNX Runtime; rebuilding a single CMake target to speed up iteration.
How do I install ONNX Runtime Source Build in Claude Code?
Run `npx skills add microsoft/onnxruntime --skill ort-build -a claude-code`. Or copy the skill folder (.github/skills/ort-build in microsoft/onnxruntime) into .claude/skills/ort-build in your project. Claude Code loads it when a task matches its description.
How do I install ONNX Runtime Source Build in Codex?
Run `npx skills add microsoft/onnxruntime --skill ort-build -a codex`. Or copy the skill folder (.github/skills/ort-build in microsoft/onnxruntime) into .agents/skills/ort-build in your project. Codex loads it when a task matches its description.
Can I use ONNX Runtime Source Build in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add microsoft/onnxruntime --skill ort-build -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ort-build, .gemini/skills/ort-build, .github/skills/ort-build and .opencode/skills/ort-build in your project.
What does ONNX Runtime Source Build need to run?
Going by SKILL.md and its folder, ONNX Runtime Source Build needs the command-line tools its instructions call (python). Our summary lists: An ONNX Runtime source checkout; CUDA and cuDNN install paths for CUDA builds.
Does ONNX Runtime Source Build access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is ONNX Runtime Source Build safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does ONNX Runtime Source Build use?
ONNX Runtime Source Build is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does ONNX Runtime Source Build use?
About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to ONNX Runtime Source Build?
Skills that share tags, products or a category with ONNX Runtime Source Build: Embedded AI Deployment (matlab/agent-skills-playground, 181 stars), Holoscan Install Conda (NVIDIA/skills, 3.5k stars), Matlab Deploy Embedded AI (majiayu000/claude-skill-registry, 666 stars) and The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains ONNX Runtime Source Build?
microsoft (a GitHub organization, an official publisher) maintains it in microsoft/onnxruntime, which has 22,029 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.
Source: microsoft/onnxruntime on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.