Repository
pytorch/executorch agent skills
- skills
- 10
- GitHub stars
- 5.1k
GitHub description: “On-device AI across mobile, embedded and edge for PyTorch”
- Stars
- 5,081 (1,189 forks)
- Licence
- Unknown
- Last push
- Oct 2026
- Created
- Feb 2022
- Homepage
- executorch.ai
- deep-learning
- embedded
- machine-learning
- mobile
- neural-network
- tensor
- gpu
Install all skills
npx skills add pytorch/executorchAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in pytorch/executorch, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 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. | pytorch/ | 5.1k | — | ~793 | Automated safety check: Pass | Unknown | today |
| 2 | Builds ExecuTorch from source: the Python package, C++ runtime, model runners, Android and iOS cross-compilation and backend-specific builds, with environment checks. | pytorch/ | 5.1k | — | ~2.3k | Automated safety check: Notes | Unknown | today |
| 3 | Developer guide for the Cortex-M (CMSIS-NN) backend in ExecuTorch: quantization pipeline, pass manager, tests and adding new ops. | pytorch/ | 5.1k | — | ~872 | Automated safety check: Pass | Unknown | today |
| 4 | Answers ExecuTorch questions from a local wiki on backends, export pitfalls, quantization recipes, runtime errors and SoC compatibility. | pytorch/ | 5.1k | — | ~1.3k | Automated safety check: Pass | Unknown | today |
| 5 | Reviews ExecuTorch pull requests or local branches for what CI cannot check, using a checklist, with an optional detailed line-by-line mode. | pytorch/ | 5.1k | — | ~2.9k | Automated safety check: Pass | Unknown | today |
| 6 | 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. | pytorch/ | 5.1k | — | ~1.8k | Automated safety check: Pass | Unknown | today |
| 7 | Sets up ExecuTorch as a Zephyr RTOS module, adds board support and debugs west build failures such as linker memory overflow on embedded boards. | pytorch/ | 5.1k | — | ~1.9k | Automated safety check: Pass | Unknown | today |
| 8 | Export a PyTorch model to .pte format for ExecuTorch. Use when converting models, lowering to edge, or generating .pte files. | pytorch/ | 5.1k | — | ~238 | Automated safety check: Pass | Unknown | today |
| 9 | Profile ExecuTorch model execution. Use when measuring performance, analyzing operator timing, or debugging slow models. | pytorch/ | 5.1k | — | ~165 | Automated safety check: Pass | Unknown | today |
| 10 | 10.Setup Set up ExecuTorch development environment. An agent skill from pytorch/executorch. | pytorch/ | 5.1k | — | ~142 | Automated safety check: Pass | Unknown | today |
Questions, answered from the data.
What is the best skill in pytorch/executorch?
ExecuTorch Binary Size Reduction from pytorch/executorch ranks first of the 10 skills in pytorch/executorch listed here, with the highest score: its repository has 5.1k GitHub stars, its SKILL.md loads about 793 tokens and it passes the automated safety check with no findings. Next come ExecuTorch Build Guide and ExecuTorch Cortex-M Backend.
Are the skills in pytorch/executorch official?
None yet. All 10 skills in pytorch/executorch listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from pytorch/executorch?
Run npx skills add pytorch/executorch 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.