Cuda Cpp Kernel
vipshop/cache-dit
A skill your agent uses when writing, debugging, porting, reviewing, or optimizing CUDA C++ or PTX kernels; investigating CUDA Runtime or Driver API behavior; profiling kernels with Nsight Systems…
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.
Install Qualcomm QNN Backend Development
$ npx skills add pytorch/executorch --skill qualcomm -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pytorch/executorch qualcomm --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/qualcomm .claude/skills/qualcomm && 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 "qualcomm" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/qualcomm into .claude/skills/qualcomm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qualcomm", 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/qualcommType 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 qualcomm -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pytorch/executorch qualcomm --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/qualcomm .agents/skills/qualcomm && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "qualcomm" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/qualcomm into .agents/skills/qualcomm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qualcomm", 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 qualcomm -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pytorch/executorch qualcomm --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/qualcomm .cursor/skills/qualcomm && 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 "qualcomm" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/qualcomm into .cursor/skills/qualcomm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qualcomm", 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/qualcomm--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 qualcomm -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pytorch/executorch qualcomm --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/qualcomm .gemini/skills/qualcomm && 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 "qualcomm" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/qualcomm into .gemini/skills/qualcomm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qualcomm", 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 qualcommInstalls 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 qualcomm -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/qualcomm .github/skills/qualcomm && 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 "qualcomm" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/qualcomm into .github/skills/qualcomm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qualcomm", 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 qualcomm -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 qualcomm --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/qualcomm .opencode/skills/qualcomm && 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 "qualcomm" agent skill from https://github.com/pytorch/executorch/tree/main/.claude/skills/qualcomm into .opencode/skills/qualcomm/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qualcomm", 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
qualcomm- GitHub stars
- 5.1k
- Token cost
- ~1.8k tokens
- SKILL.md length
- 610 words
- Files
- 7
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
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.
- Fixing a red test-qnn-buck-build-linux CI check on a QNN pull request
- SKILL.md covers Slash command argument routing, Advanced Topics, Building and Testing
- Calls python
- Adding a new operator or op builder to the Qualcomm backend
What it does
The skill is for work in backends/qualcomm/: building QNN with the backend's build script, adding ops or passes, running QNN delegate tests and exporting models for Qualcomm HTP or GPU targets. When invoked as /qualcomm with arguments, it first classifies them. Buck-related keywords such as buck-fix, buck-parity or the test-qnn-buck-build-linux CI check go straight to the Buck parity guide, which runs a full iterative-fix loop unless the arguments also say check or diagnose, in which case it runs buck once and only reports.
Other requests use a table that points to topic files: lowering and export with quantization options and pass pipelines, new op development, custom op enablement through QNN op packages (covering HTP and LPAI/eNPU), end-to-end model enablement, Buck and CMake parity before a PR, and a QNN intermediate-output debugger for accuracy problems such as outputs that differ from CPU. A profiling topic file is marked as still to be written.
When your agent uses it
- Fixing a red test-qnn-buck-build-linux CI check on a QNN pull request
- Adding a new operator or op builder to the Qualcomm backend
- Exporting a model for Qualcomm HTP or GPU targets
- Finding which QNN layer diverges from CPU output
- Checking that Buck and CMake files agree before pushing a PR
Example prompts
- “/qualcomm buck-fix”
- “My QNN output doesn't match CPU, so help me find which layer is wrong.”
- “Add a new op builder to backends/qualcomm and its delegate test.”
- “Enable a new model end to end for the HTP target and show me the export steps.”
Requirements
- The ExecuTorch repository with backends/qualcomm
- A build environment for the QNN backend, using backends/qualcomm/scripts/build.sh
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:
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
Qualcomm QNN Backend Development loads about 1.8k tokens when it runs. Until then it costs about 183 tokens; SKILL.md has 610 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 610 words (~1,849 tokens).
“When this skill is invoked with arguments (e.g. /qualcomm ), classify the args FIRST and route before doing anything else:”
- name
- qualcomm
Files
SKILL.md and 6 other files in .claude/skills/qualcomm of pytorch/executorch.
- SKILL.md
- buck_parity.md
- custom_op_enablement.md
- lowering_export.md
- model_enablement.md
- new_op_development.md
- qnn_intermediate_debugger.md
Open the folder on GitHubat commit 27d124f
Compare with similar skills
Qualcomm QNN Backend Development 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 |
|---|---|---|---|---|---|---|
| Qualcomm QNN Backend Development this skillpytorch/executorch | 5.1k | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Cuda Cpp Kernelvipshop/cache-dit | 1.3k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Pt2 Bug Basherpytorch/pytorch | 104k | — | ~3.5k | 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 | |
| Fix Issuepytorch/pytorch | 104k | — | ~2.3k | Automated safety check: Pass | Custom licence | |
| Veomni DebugByteDance-Seed/VeOmni | 2.2k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Pt2 Bug Basher
pytorch/pytorch
Debug PyTorch 2 compiler stack failures including Dynamo graph breaks, Inductor codegen errors, AOTAutograd crashes, and accuracy mismatches.
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.
Fix Issue
pytorch/pytorch
Fix bugs reported in PyTorch GitHub issues by reproducing, root-causing, and implementing a fix in the local working tree.
Veomni Debug
ByteDance-Seed/VeOmni
A skill your agent uses for ANY bug, error, crash, wrong output, loss divergence, gradient explosion, test failure, CUDA error, distributed training hang, checkpoint load failure, or unexpected…
Ako4all
TongmingLAIC/AKO4ALL
Drive an agentic loop that iteratively optimizes a GPU kernel for maximum speedup.
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.
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 Qualcomm QNN Backend Development
What does Qualcomm QNN Backend Development do?
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. The skill is for work in backends/qualcomm/: building QNN with the backend's build script, adding ops or passes, running QNN delegate tests and exporting models for Qualcomm HTP or GPU targets. When invoked as /qualcomm with arguments, it first classifies them.
When should I use Qualcomm QNN Backend Development?
Qualcomm QNN Backend Development fits situations like: fixing a red test-qnn-buck-build-linux CI check on a QNN pull request; adding a new operator or op builder to the Qualcomm backend; exporting a model for Qualcomm HTP or GPU targets; finding which QNN layer diverges from CPU output.
How do I install Qualcomm QNN Backend Development in Claude Code?
Run `npx skills add pytorch/executorch --skill qualcomm -a claude-code`. Or copy the skill folder (.claude/skills/qualcomm in pytorch/executorch) into .claude/skills/qualcomm in your project. Claude Code loads it when a task matches its description.
How do I install Qualcomm QNN Backend Development in Codex?
Run `npx skills add pytorch/executorch --skill qualcomm -a codex`. Or copy the skill folder (.claude/skills/qualcomm in pytorch/executorch) into .agents/skills/qualcomm in your project. Codex loads it when a task matches its description.
Can I use Qualcomm QNN Backend Development 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 qualcomm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qualcomm, .gemini/skills/qualcomm, .github/skills/qualcomm and .opencode/skills/qualcomm in your project.
What does Qualcomm QNN Backend Development need to run?
Going by SKILL.md and its folder, Qualcomm QNN Backend Development needs the command-line tools its instructions call (python). Our summary lists: The ExecuTorch repository with backends/qualcomm; A build environment for the QNN backend, using backends/qualcomm/scripts/build.sh.
Does Qualcomm QNN Backend Development 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 Qualcomm QNN Backend Development 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 Qualcomm QNN Backend Development use?
Qualcomm QNN Backend Development 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 Qualcomm QNN Backend Development use?
About 1.8k tokens (SKILL.md is roughly 7.4k 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 Qualcomm QNN Backend Development?
Skills that share tags, products or a category with Qualcomm QNN Backend Development: Cuda Cpp Kernel (vipshop/cache-dit, 1.3k stars), Pt2 Bug Basher (pytorch/pytorch, 104k stars), The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars) and Fix Issue (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Qualcomm QNN Backend Development?
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.