Running Tests
brendanhasz/probflow
Run Python unit test suites strictly using the uv package manager and pytest.
Developer guide for the Cortex-M (CMSIS-NN) backend in ExecuTorch: quantization pipeline, pass manager, tests and adding new ops.
Install ExecuTorch Cortex-M Backend
$ npx skills add pytorch/executorch --skill cortex-m -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pytorch/executorch cortex-m --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/pytorch/executorch.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/cortex-m .claude/skills/cortex-m && 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 "cortex-m" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/cortex-m into .claude/skills/cortex-m/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cortex-m", 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/pytorch/executorch/tree/main/.claude/skills/cortex-mType 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 pytorch/executorch --skill cortex-m -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pytorch/executorch cortex-m --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pytorch/executorch.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/cortex-m .agents/skills/cortex-m && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cortex-m" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/cortex-m into .agents/skills/cortex-m/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cortex-m", 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 pytorch/executorch --skill cortex-m -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pytorch/executorch cortex-m --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pytorch/executorch.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/cortex-m .cursor/skills/cortex-m && 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 "cortex-m" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/cortex-m into .cursor/skills/cortex-m/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cortex-m", 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/pytorch/executorch.git --path .claude/skills/cortex-m--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 pytorch/executorch --skill cortex-m -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pytorch/executorch cortex-m --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pytorch/executorch.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/cortex-m .gemini/skills/cortex-m && 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 "cortex-m" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/cortex-m into .gemini/skills/cortex-m/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cortex-m", 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 pytorch/executorch cortex-mInstalls 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 pytorch/executorch --skill cortex-m -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pytorch/executorch.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/cortex-m .github/skills/cortex-m && 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 "cortex-m" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/cortex-m into .github/skills/cortex-m/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cortex-m", 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 pytorch/executorch --skill cortex-m -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pytorch/executorch cortex-m --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pytorch/executorch.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/cortex-m .opencode/skills/cortex-m && 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 "cortex-m" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/cortex-m into .opencode/skills/cortex-m/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cortex-m", 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
cortex-m- GitHub stars
- 5.1k
- Token cost
- ~872 tokens
- SKILL.md length
- 189 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Developer guide for the Cortex-M (CMSIS-NN) backend in ExecuTorch: quantization pipeline, pass manager, tests and adding new ops.
- Works in 5 steps: Define the op schema, meta function, and… → Write the C++ kernel in… → Register the .out kernel in operators.yaml → …
- Working on code under backends/cortex_m/
- SKILL.md covers Architecture, Pipeline, Key Files and Testing, plus 1 more section
- Calls pytest
What it does
The Cortex-M backend is not a delegate and has no partitioner; instead, custom ops and graph passes replace ATen quantized ops with CMSIS-NN equivalents at the graph level. The pipeline uses standard PT2E quantization with `prepare_pt2e` and `convert_pt2e` through `CortexMQuantizer`, then `CortexMPassManager` rewrites quantized ops to `cortex_m::` equivalents. A key-files table lists the quantizer, pass manager, tester, Python op definitions and the YAML that registers C++ kernels.
In tests, `CortexMTester` wraps the pipeline with `test_dialect()` and `test_implementation()`. Dialect tests check graph correctness in pure Python, while implementation tests check numerical accuracy on the Corstone-300 FVP and need the Arm toolchain set up with `examples/arm/setup.sh` and added to the PATH. A baremetal build uses `build_test_runner.sh`. Adding a new op means defining its schema, meta function and reference implementation, writing the C++ kernel against CMSIS-NN, registering the `.out` kernel in `operators.yaml` and adding a pass that rewrites the ATen op.
When your agent uses it
- Working on code under backends/cortex_m/
- Running the Cortex-M tests, including the Corstone-300 simulator ones
- Exporting a model for a Cortex-M target
- Adding a new operator to the Cortex-M backend
Example prompts
- “Run the Cortex-M dialect tests and tell me which ones fail.”
- “Add a CMSIS-NN backed op for average pooling to the Cortex-M backend.”
- “Set up the Arm toolchain so I can run the implementation tests.”
Requirements
- An ExecuTorch checkout with the Arm toolchain from `examples/arm/setup.sh`
- Python with pytest
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Define the op schema, meta function, and reference implementation in operators.py
- Write the C++ kernel in backends/cortex_m/ops/ calling CMSIS-NN APIs
- Register the .out kernel in operators.yaml
- Add a pass to rewrite the ATen op → cortex_m:: op
- Test with CortexMTester.test_dialect() (graph correctness) and test_implementation() (numerical accuracy on FVP)
What it can do on your machine
Read from SKILL.md and the folder at commit 27d124f. 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:
pytest
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
ExecuTorch Cortex-M Backend loads about 872 tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 189 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 189 words (~872 tokens).
“Not a delegate backend — no partitioner. Custom ops and graph passes replace ATen quantized ops with CMSIS-NN equivalents at the graph level.”
- name
- cortex-m
Files
Just SKILL.md in .claude/skills/cortex-m of pytorch/executorch.
Open the folder on GitHubat commit 27d124f
Compare with similar skills
ExecuTorch Cortex-M Backend 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 |
|---|---|---|---|---|---|---|
| ExecuTorch Cortex-M Backend this skillpytorch/executorch | 5.1k | — | ~872 | Automated safety check: Pass | Custom licence | |
| Running Testsbrendanhasz/probflow | 175 | — | ~657 | Automated safety check: Pass | MIT | |
| Formattingbrendanhasz/probflow | 175 | — | ~381 | Automated safety check: Pass | MIT | |
| Torch Performance Optimizationalbumentations-team/albucore | 123 | — | ~895 | Automated safety check: Pass | MIT | |
| Benchmark Pyreflyfacebook/pyrefly | 7.1k | — | ~1.8k | Automated safety check: Pass | MIT | |
| Document Public APIspytorch/pytorch | 104k | — | ~4.2k | Automated safety check: Pass | Custom licence |
Similar skills
Formatting
brendanhasz/probflow
Ensure consistent code formatting using the uv package manager and pre-commit.
Torch Performance Optimization
albumentations-team/albucore
Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.
- Official
Benchmark Pyrefly
facebook/pyrefly
Run Pyrefly benchmarks locally via Buck or Cargo, including PyTorch real-world LSP benchmarks.
Document Public APIs
pytorch/pytorch
Document undocumented public APIs in PyTorch by removing functions from coverageignorefunctions and coverageignoreclasses in docs/source/conf.py, running Sphinx coverage, and adding the appropriate…
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.
More from pytorch/executorch
All 10 skills in this repoExecuTorch Binary Size Reduction
pytorch/executorch
Measures and shrinks the ExecuTorch runtime binary by building a size test, analyzing it with bloaty and landing each reduction as its own pull request.
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.
ExecuTorch Knowledge Base
pytorch/executorch
Answers ExecuTorch questions from a local wiki on backends, export pitfalls, quantization recipes, runtime errors and SoC compatibility.
ExecuTorch PR Review
pytorch/executorch
Reviews ExecuTorch pull requests or local branches for what CI cannot check, using a checklist, with an optional detailed line-by-line mode.
Qualcomm QNN Backend Development
pytorch/executorch
Helps build, test and extend the Qualcomm AI Engine Direct (QNN) backend in ExecuTorch, with routes for new ops, model export, Buck-vs-CMake parity fixes and per-layer accuracy debugging.
ExecuTorch on Zephyr
pytorch/executorch
Sets up ExecuTorch as a Zephyr RTOS module, adds board support and debugs west build failures such as linker memory overflow on embedded boards.
Related
Categories
Questions about ExecuTorch Cortex-M Backend
What does ExecuTorch Cortex-M Backend do?
Developer guide for the Cortex-M (CMSIS-NN) backend in ExecuTorch: quantization pipeline, pass manager, tests and adding new ops. The Cortex-M backend is not a delegate and has no partitioner; instead, custom ops and graph passes replace ATen quantized ops with CMSIS-NN equivalents at the graph level. The pipeline uses standard PT2E quantization with `prepare_pt2e` and `convert_pt2e` through `CortexMQuantizer`, then `CortexMPassManager` rewrites quantized ops to `cortex_m::` equivalents.
When should I use ExecuTorch Cortex-M Backend?
ExecuTorch Cortex-M Backend fits situations like: working on code under backends/cortex_m/; running the Cortex-M tests, including the Corstone-300 simulator ones; exporting a model for a Cortex-M target; adding a new operator to the Cortex-M backend.
How do I install ExecuTorch Cortex-M Backend in Claude Code?
Run `npx skills add pytorch/executorch --skill cortex-m -a claude-code`. Or copy the skill folder (.claude/skills/cortex-m in pytorch/executorch) into .claude/skills/cortex-m in your project. Claude Code loads it when a task matches its description.
How do I install ExecuTorch Cortex-M Backend in Codex?
Run `npx skills add pytorch/executorch --skill cortex-m -a codex`. Or copy the skill folder (.claude/skills/cortex-m in pytorch/executorch) into .agents/skills/cortex-m in your project. Codex loads it when a task matches its description.
Can I use ExecuTorch Cortex-M Backend 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 pytorch/executorch --skill cortex-m -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cortex-m, .gemini/skills/cortex-m, .github/skills/cortex-m and .opencode/skills/cortex-m in your project.
What does ExecuTorch Cortex-M Backend need to run?
Going by SKILL.md and its folder, ExecuTorch Cortex-M Backend needs the command-line tools its instructions call (pytest). Our summary lists: An ExecuTorch checkout with the Arm toolchain from `examples/arm/setup.sh`; Python with pytest.
Does ExecuTorch Cortex-M Backend 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 ExecuTorch Cortex-M Backend 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 ExecuTorch Cortex-M Backend use?
ExecuTorch Cortex-M Backend has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does ExecuTorch Cortex-M Backend use?
About 872 tokens (SKILL.md is roughly 3.5k 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 ExecuTorch Cortex-M Backend?
Skills that share tags, products or a category with ExecuTorch Cortex-M Backend: Running Tests (brendanhasz/probflow, 175 stars), Formatting (brendanhasz/probflow, 175 stars), Torch Performance Optimization (albumentations-team/albucore, 123 stars) and Benchmark Pyrefly (facebook/pyrefly, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains ExecuTorch Cortex-M Backend?
pytorch (a GitHub organization) maintains it in pytorch/executorch, which has 5,081 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.
Source: pytorch/executorch on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.