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.
Sets up ExecuTorch as a Zephyr RTOS module, adds board support and debugs west build failures such as linker memory overflow on embedded boards.
Install ExecuTorch on Zephyr
$ npx skills add pytorch/executorch --skill zephyr -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pytorch/executorch zephyr --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/zephyr .claude/skills/zephyr && 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 "zephyr" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/zephyr into .claude/skills/zephyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zephyr", 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/zephyrType 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 zephyr -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pytorch/executorch zephyr --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/zephyr .agents/skills/zephyr && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "zephyr" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/zephyr into .agents/skills/zephyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zephyr", 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 zephyr -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pytorch/executorch zephyr --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/zephyr .cursor/skills/zephyr && 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 "zephyr" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/zephyr into .cursor/skills/zephyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zephyr", 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/zephyr--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 zephyr -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pytorch/executorch zephyr --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/zephyr .gemini/skills/zephyr && 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 "zephyr" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/zephyr into .gemini/skills/zephyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zephyr", 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 zephyrInstalls 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 zephyr -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/zephyr .github/skills/zephyr && 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 "zephyr" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/zephyr into .github/skills/zephyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zephyr", 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 zephyr -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 zephyr --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/zephyr .opencode/skills/zephyr && 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 "zephyr" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/zephyr into .opencode/skills/zephyr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zephyr", 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
zephyr- GitHub stars
- 5.1k
- Token cost
- ~1.9k tokens
- SKILL.md length
- 672 words
- Files
- 3
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Sets up ExecuTorch as a Zephyr RTOS module, adds board support and debugs west build failures such as linker memory overflow on embedded boards.
- Works in 5 steps: Create Zephyr workspace → Add ExecuTorch as a module → Install ExecuTorch → …
- Creating a Zephyr workspace that includes ExecuTorch as a module
- SKILL.md covers When to use this skill, When to use a different skill, Advanced Topics and Architecture, plus 5 more sections
- Calls git, python3 and pip
What it does
ExecuTorch plugs into Zephyr as an external module declared in zephyr/module.yml, which exposes its runtime, kernels and backends as CMake targets that a Zephyr application links against. The skill walks through creating a workspace with a Python virtual environment and west, adding an executorch submanifest, running west update, and installing ExecuTorch with its install script.
Further steps cover installing the Zephyr SDK with an Arm toolchain through west sdk install, and running the Ethos-U setup script when the target board has an NPU. For local development it explains symlinking your own ExecuTorch checkout after the update. Sizing allocator pools for a given model and board is also in scope.
Two companion files go deeper: board_bringup.md for writing overlays, conf files and linker snippets for a new board, and memory_debugging.md for region overflows at build time or allocation failures at runtime. Exporting a .pte model, bare-metal Cortex-M, general C++ builds and backend op support are routed to other skills.
When your agent uses it
- Creating a Zephyr workspace that includes ExecuTorch as a module
- Adding overlays, confs and linker settings for a new board
- Diagnosing a west build that fails with a linker region overflow
- Choosing allocator pool sizes for a model on a specific board
Example prompts
- “Set up a Zephyr workspace with ExecuTorch and build the sample for my Cortex-M board.”
- “My west build says a memory region overflowed. Help me find what is using the space.”
- “Add overlay and conf files so the ExecuTorch Zephyr sample runs on our custom board.”
Requirements
- Python 3 with west, ninja, pyelftools and jsonschema
- A Zephyr SDK with an Arm toolchain
- A local ExecuTorch checkout with its git submodules
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- Create Zephyr workspace
- Add ExecuTorch as a module
- Install ExecuTorch
- Install Zephyr SDK
- Install Ethos-U tools (if targeting NPU boards)
What it can do on your machine
Read from SKILL.md and the folder at commit 852b1ff. 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:
gitpython3pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git and pip, which can reach the network depending on how they are called.
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 on Zephyr loads about 1.9k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 672 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 672 words (~1,925 tokens).
“ExecuTorch integrates as a Zephyr external module via zephyr/module.yml. The module exposes ET libraries (runtime, kernels, backends) as Zephyr CMake targets that applications link against.”
- name
- zephyr
Files
SKILL.md and 2 other files in .claude/skills/zephyr of pytorch/executorch.
- SKILL.md
- board_bringup.md
- memory_debugging.md
Open the folder on GitHubat commit 852b1ff
Compare with similar skills
ExecuTorch on Zephyr 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 on Zephyr this skillpytorch/executorch | 5.1k | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| The Art of Debuggingstas00/the-art-of-debugging | 1.7k | — | ~6.1k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Quark Torch Debugamd/Quark | 181 | — | ~1.9k | Automated safety check: Notes | MIT | |
| Worktree Env Setupmeta-pytorch/attention-gym | 1.3k | — | ~858 | Automated safety check: Pass | BSD-3-Clause | |
| Celeste Pythonwithceleste/celeste-python | 221 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Debug Sessionai-dynamo/dynamo | 8.2k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Quark Torch Debug
amd/Quark
Diagnose failed Quark installation, PTQ execution, script generation, or export attempts.
Worktree Env Setup
meta-pytorch/attention-gym
Sets up an isolated per-worktree Python environment for attention-gym development using nightly PyTorch and the CI-mirroring uv flow.
Celeste Python
withceleste/celeste-python
A skill your agent uses whenever writing, modifying, reviewing, or debugging code involving Celeste, celeste-ai, celeste-python, import celeste, src/celeste, or withceleste app integrations.
Debug Session
ai-dynamo/dynamo
Sets up a structured debugging session for a Dynamo bug — pull the report from a Linear ticket, GitHub issue, or pasted text, capture the environment, create a persistent worklog markdown file, and…
Ascendc
ascend-ai-coding/awesome-ascend-skills
End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.
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 Cortex-M Backend
pytorch/executorch
Developer guide for the Cortex-M (CMSIS-NN) backend in ExecuTorch: quantization pipeline, pass manager, tests and adding new ops.
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.
Related
Categories
Questions about ExecuTorch on Zephyr
What does ExecuTorch on Zephyr do?
Sets up ExecuTorch as a Zephyr RTOS module, adds board support and debugs west build failures such as linker memory overflow on embedded boards. yml, which exposes its runtime, kernels and backends as CMake targets that a Zephyr application links against. The skill walks through creating a workspace with a Python virtual environment and west, adding an executorch submanifest, running west update, and installing ExecuTorch with its install script.
When should I use ExecuTorch on Zephyr?
ExecuTorch on Zephyr fits situations like: creating a Zephyr workspace that includes ExecuTorch as a module; adding overlays, confs and linker settings for a new board; diagnosing a west build that fails with a linker region overflow; choosing allocator pool sizes for a model on a specific board.
How do I install ExecuTorch on Zephyr in Claude Code?
Run `npx skills add pytorch/executorch --skill zephyr -a claude-code`. Or copy the skill folder (.claude/skills/zephyr in pytorch/executorch) into .claude/skills/zephyr in your project. Claude Code loads it when a task matches its description.
How do I install ExecuTorch on Zephyr in Codex?
Run `npx skills add pytorch/executorch --skill zephyr -a codex`. Or copy the skill folder (.claude/skills/zephyr in pytorch/executorch) into .agents/skills/zephyr in your project. Codex loads it when a task matches its description.
Can I use ExecuTorch on Zephyr 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 zephyr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/zephyr, .gemini/skills/zephyr, .github/skills/zephyr and .opencode/skills/zephyr in your project.
What does ExecuTorch on Zephyr need to run?
Going by SKILL.md and its folder, ExecuTorch on Zephyr needs the command-line tools its instructions call (git, python3 and pip). Our summary lists: Python 3 with west, ninja, pyelftools and jsonschema; A Zephyr SDK with an Arm toolchain; A local ExecuTorch checkout with its git submodules.
Does ExecuTorch on Zephyr access the network?
SKILL.md contains no URLs. Its commands use git and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is ExecuTorch on Zephyr 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 on Zephyr use?
ExecuTorch on Zephyr 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 on Zephyr use?
About 1.9k tokens (SKILL.md is roughly 7.7k 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 on Zephyr?
Skills that share tags, products or a category with ExecuTorch on Zephyr: The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars), Quark Torch Debug (amd/Quark, 181 stars), Worktree Env Setup (meta-pytorch/attention-gym, 1.3k stars) and Celeste Python (withceleste/celeste-python, 221 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains ExecuTorch on Zephyr?
pytorch (a GitHub organization) maintains it in pytorch/executorch, which has 5,082 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 8, 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.