665,000+ skills indexed

pytorchOfficial·8 Agent Skills Included

executorch

Deploy PyTorch AI models on phones, chips, and embedded devices

Exports PyTorch models into compact .pte files that run directly on phones, microcontrollers, and edge hardware. Removes manual C++ rewrites, format conversions, and vendor lock-in when moving AI models to devices. Includes skills for building backends, profiling speed, shrinking binary size, and debugging hardware-specific issues.

npx skills add pytorch/executorch --all -g -y

Available:

Routes the AI agent to the right skill for setup, model export, building, profiling, or backend debugging, and points it to a knowledge base of known issues and fixes.

All Skills in This Repository (8)

Pure Emerald Level Indicators

pytorch

setup

Automate local ExecuTorch environment setup with conda and dependencies.

pytorch

profile

Profile ExecuTorch model execution with etdump and Inspector for operator timing.

pytorch

cortex-m

Quantize and export PyTorch models for Cortex-M CMSIS-NN targets using PT2E flow and CortexMPassManager.

pytorch

export

Convert PyTorch models to .pte format for ExecuTorch deployment.

pytorch

binary-size

Analyze and reduce ExecuTorch runtime binary size using bloaty and size test builds.

pytorch

executorch-kb

Searches a curated ExecuTorch knowledge base covering backends, quantization, export pitfalls, and runtime errors.

pytorch

zephyr

Build and configure ExecuTorch as a Zephyr RTOS module for embedded boards.

pytorch

building

Builds ExecuTorch Python packages, C++ runtimes, model runners, and cross-compiled mobile libraries from source.

Frequently Asked Questions

FAQPage Schema

How to install ExecuTorch?▼

Run `npx skills add pytorch/executorch --all -g -y` in your terminal to install all skills in this suite globally.

What does ExecuTorch do?▼

It converts PyTorch models into a small portable format that runs on-device, from smartphones to microcontrollers, without cloud servers.

Can I run Llama on my phone with ExecuTorch?▼

Yes. The export skill converts Llama and other LLMs into .pte files, and ready-made runners execute them on iOS and Android.

Which hardware backends does ExecuTorch support?▼

It supports over 12 backends including Qualcomm, Apple CoreML, ARM, Vulkan, and XNNPACK, switchable with a single line change.

Do I need embedded experience to use these skills?▼

No. The skills guide your AI agent through setup, export, building, and debugging steps using plain-English requests.

Related Repositories in Software Engineering

View All in Software Engineering→

openclaw

openclaw

Run a personal AI assistant across your devices and chat apps

Official📦 120 Skills

obra

superpowers

Gives coding agents a disciplined workflow from idea to merged code

Community📦 15 Skills

react

AI agent skills for building, testing, and porting React core

Official📦 14 Skills