Aoti Debug
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
Optimize MATLAB design files for GPU Coder to generate faster CUDA code.
Install Matlab Optimize GPU Codegen
$ npx skills add matlab/matlab-agentic-toolkit --skill matlab-optimize-gpu-codegen -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install matlab/matlab-agentic-toolkit matlab-optimize-gpu-codegen --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/matlab/matlab-agentic-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills-catalog/code-generation/matlab-optimize-gpu-codegen .claude/skills/matlab-optimize-gpu-codegen && 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 "matlab-optimize-gpu-codegen" agent skill from https://github.com/matlab/matlab-agentic-toolkit/tree/main/skills-catalog/code-generation/matlab-optimize-gpu-codegen into .claude/skills/matlab-optimize-gpu-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matlab-optimize-gpu-codegen", 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/matlab/matlab-agentic-toolkit/tree/main/skills-catalog/code-generation/matlab-optimize-gpu-codegenType 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 matlab/matlab-agentic-toolkit --skill matlab-optimize-gpu-codegen -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install matlab/matlab-agentic-toolkit matlab-optimize-gpu-codegen --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/matlab/matlab-agentic-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills-catalog/code-generation/matlab-optimize-gpu-codegen .agents/skills/matlab-optimize-gpu-codegen && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "matlab-optimize-gpu-codegen" agent skill from https://github.com/matlab/matlab-agentic-toolkit/tree/main/skills-catalog/code-generation/matlab-optimize-gpu-codegen into .agents/skills/matlab-optimize-gpu-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matlab-optimize-gpu-codegen", 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 matlab/matlab-agentic-toolkit --skill matlab-optimize-gpu-codegen -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install matlab/matlab-agentic-toolkit matlab-optimize-gpu-codegen --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/matlab/matlab-agentic-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills-catalog/code-generation/matlab-optimize-gpu-codegen .cursor/skills/matlab-optimize-gpu-codegen && 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 "matlab-optimize-gpu-codegen" agent skill from https://github.com/matlab/matlab-agentic-toolkit/tree/main/skills-catalog/code-generation/matlab-optimize-gpu-codegen into .cursor/skills/matlab-optimize-gpu-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matlab-optimize-gpu-codegen", 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/matlab/matlab-agentic-toolkit.git --path skills-catalog/code-generation/matlab-optimize-gpu-codegen--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 matlab/matlab-agentic-toolkit --skill matlab-optimize-gpu-codegen -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install matlab/matlab-agentic-toolkit matlab-optimize-gpu-codegen --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/matlab/matlab-agentic-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills-catalog/code-generation/matlab-optimize-gpu-codegen .gemini/skills/matlab-optimize-gpu-codegen && 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 "matlab-optimize-gpu-codegen" agent skill from https://github.com/matlab/matlab-agentic-toolkit/tree/main/skills-catalog/code-generation/matlab-optimize-gpu-codegen into .gemini/skills/matlab-optimize-gpu-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matlab-optimize-gpu-codegen", 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 matlab/matlab-agentic-toolkit matlab-optimize-gpu-codegenInstalls 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 matlab/matlab-agentic-toolkit --skill matlab-optimize-gpu-codegen -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/matlab/matlab-agentic-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills-catalog/code-generation/matlab-optimize-gpu-codegen .github/skills/matlab-optimize-gpu-codegen && 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 "matlab-optimize-gpu-codegen" agent skill from https://github.com/matlab/matlab-agentic-toolkit/tree/main/skills-catalog/code-generation/matlab-optimize-gpu-codegen into .github/skills/matlab-optimize-gpu-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matlab-optimize-gpu-codegen", 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 matlab/matlab-agentic-toolkit --skill matlab-optimize-gpu-codegen -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install matlab/matlab-agentic-toolkit matlab-optimize-gpu-codegen --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/matlab/matlab-agentic-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills-catalog/code-generation/matlab-optimize-gpu-codegen .opencode/skills/matlab-optimize-gpu-codegen && 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 "matlab-optimize-gpu-codegen" agent skill from https://github.com/matlab/matlab-agentic-toolkit/tree/main/skills-catalog/code-generation/matlab-optimize-gpu-codegen into .opencode/skills/matlab-optimize-gpu-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "matlab-optimize-gpu-codegen", 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
matlab-optimize-gpu-codegen- GitHub stars
- 1.1k
- Token cost
- ~4.7k tokens
- SKILL.md length
- 1,992 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 144
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Optimize MATLAB design files for GPU Coder to generate faster CUDA code.
- Works in 6 steps: Codegen on Original → Baseline Benchmark → Structural Optimization Loop → …
- Asked to: optimize for GPU Coder
- SKILL.md covers When to Use, When NOT to Use, Workflow and Conventions
- Improve GPU codegen performance
What it does
Matlab Optimize GPU Codegen is an agent skill from matlab/matlab-agentic-toolkit. Optimize MATLAB design files for GPU Coder to generate faster CUDA code. Iteratively profiles, rewrites, and benchmarks until performance targets are met or diagnostics are resolved. Use when asked to: optimize for GPU Coder, improve GPU codegen performance, profile generated GPU/CUDA code, profile GPU MEX, fix gpuPerformanceAnalyzer diagnostics, speed up GPU MEX, reduce GPU memory transfers, improve kernel parallelism, rewrite MATLAB for CUDA, or run gpuPerformanceAnalyzer.
Its SKILL.md is about 4.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `manifest.yaml` and `references/gpu-codegen-functions.md`).
It sits in Development, covering Project scaffolding. It works with CUDA. The repository describes itself as: The MATLAB Agentic Toolkit brings proven MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.
When your agent uses it
- Asked to: optimize for GPU Coder
- Improve GPU codegen performance
- Profile generated GPU/CUDA code
- Profile GPU MEX
Example prompts
- “/matlab-optimize-gpu-codegen”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- Codegen on Original
- Baseline Benchmark
- Structural Optimization Loop
- Profile with gpuPerformanceAnalyzer
- Fix Diagnostics
- Final Report
What it can do on your machine
Read from SKILL.md and the folder at commit 3303f05. 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
Ships 2 files in scripts/, which the agent can run.
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
Matlab Optimize GPU Codegen loads about 4.7k tokens when it runs, and up to ~6.3k if it reads all its reference files. Until then it costs about 127 tokens; SKILL.md has 1,992 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); the scripts in this folder 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 1,992 words (~4,677 tokens).
“Iteratively optimize a MATLAB design file for GPU Coder: compile, benchmark, apply structural optimizations, profile with gpuPerformanceAnalyzer, fix diagnostics, and verify numerical equivalence at every step.”
- name
- matlab-optimize-gpu-codegen
- license
- https://www.mathworks.com/content/dam/mathworks/license/pmrl/license.md
- metadata.author
- MathWorks
- metadata.version
- 1.1
Files
SKILL.md and 4 other files (scripts, references) in skills-catalog/code-generation/matlab-optimize-gpu-codegen of matlab/matlab-agentic-toolkit.
- SKILL.md
- manifest.yaml
- references/gpu-codegen-functions.md
- scripts/benchmarkMex.m
- scripts/extractDiagnostics.p
Open the folder on GitHubat commit 3303f05
Compare with similar skills
Matlab Optimize GPU Codegen 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 |
|---|---|---|---|---|---|---|
| Matlab Optimize GPU Codegen this skillmatlab/matlab-agentic-toolkit | 1.1k | — | ~4.7k | Automated safety check: Pass | Custom licence | |
| Aoti Debugpytorch/pytorch | 104k | 1 repos | ~1.7k | Automated safety check: Pass | Custom licence | |
| Nx Generatenomcopter/react-mosaic | 4.8k | 6 repos | ~1.9k | Automated safety check: Pass | Custom licence | |
| PonytailDavidObando/gsharp | 564 | 8 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Run Nx Generatornrwl/nx | 29k | 2 repos | ~592 | Automated safety check: Notes | MIT | |
| Debug Distributed Hangsgl-project/sglang | 37k | 2 repos | ~2.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Nx Generate
nomcopter/react-mosaic
Generate code using nx generators. An agent skill from nomcopter/react-mosaic.
Ponytail
DavidObando/gsharp
Forces the laziest solution that actually works, simplest, shortest, most minimal.
Run Nx Generator
nrwl/nx
Run Nx generators with prioritization for workspace-plugin generators.
Debug Distributed Hang
sgl-project/sglang
Debug hanging issues in SGLang distributed inference (TP/PP/DP/EP).
Conductor Setup
gemini-cli-extensions/conductor
Scaffolds the project and sets up the Conductor environment.
More from matlab/matlab-agentic-toolkit
All 144 skills in this repoMatlab Analyze Time Frequency Content
matlab/matlab-agentic-toolkit
Perform time-frequency analysis in MATLAB using CWT, STFT, synchrosqueezing, reassignment, wavelet coherence, cross spectrogram, EMD/VMD, multiresolution analysis, and time-frequency filtering.
Matlab Design Radar
matlab/matlab-agentic-toolkit
Launch and control the MATLAB Radar Designer app programmatically via MCP.
Matlab Enhance Camera Image
matlab/matlab-agentic-toolkit
Read BEFORE troubleshooting or enhancing camera image quality.
Matlab Import External AI Model
matlab/matlab-agentic-toolkit
Import PyTorch, ONNX, or Keras 3 / TensorFlow 2.16+ deep learning models into MATLAB as dlnetwork objects.
Matlab Modernize Daq
matlab/matlab-agentic-toolkit
Port MATLAB Data Acquisition Toolbox code from the discouraged (legacy) session-based interface (daq.createSession, addAnalogInputChannel, startBackground, DataAvailable listeners, queueOutputData…
Matlab Package Toolbox
matlab/matlab-agentic-toolkit
Turn raw MATLAB code into a published .mltbx toolbox — full pipeline from scope definition through packaging and release.
Related
Works with
Categories
Questions about Matlab Optimize GPU Codegen
What does Matlab Optimize GPU Codegen do?
Optimize MATLAB design files for GPU Coder to generate faster CUDA code. Matlab Optimize GPU Codegen is an agent skill from matlab/matlab-agentic-toolkit. Optimize MATLAB design files for GPU Coder to generate faster CUDA code.
When should I use Matlab Optimize GPU Codegen?
Matlab Optimize GPU Codegen fits situations like: asked to: optimize for GPU Coder; improve GPU codegen performance; profile generated GPU/CUDA code; profile GPU MEX.
How do I install Matlab Optimize GPU Codegen in Claude Code?
Run `npx skills add matlab/matlab-agentic-toolkit --skill matlab-optimize-gpu-codegen -a claude-code`. Or copy the skill folder (skills-catalog/code-generation/matlab-optimize-gpu-codegen in matlab/matlab-agentic-toolkit) into .claude/skills/matlab-optimize-gpu-codegen in your project. Claude Code loads it when a task matches its description.
How do I install Matlab Optimize GPU Codegen in Codex?
Run `npx skills add matlab/matlab-agentic-toolkit --skill matlab-optimize-gpu-codegen -a codex`. Or copy the skill folder (skills-catalog/code-generation/matlab-optimize-gpu-codegen in matlab/matlab-agentic-toolkit) into .agents/skills/matlab-optimize-gpu-codegen in your project. Codex loads it when a task matches its description.
Can I use Matlab Optimize GPU Codegen 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 matlab/matlab-agentic-toolkit --skill matlab-optimize-gpu-codegen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/matlab-optimize-gpu-codegen, .gemini/skills/matlab-optimize-gpu-codegen, .github/skills/matlab-optimize-gpu-codegen and .opencode/skills/matlab-optimize-gpu-codegen in your project.
What does Matlab Optimize GPU Codegen need to run?
SKILL.md names no scripts, command-line tools or credentials: Matlab Optimize GPU Codegen is instructions for the agent only.
Does Matlab Optimize GPU Codegen 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 Matlab Optimize GPU Codegen 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Matlab Optimize GPU Codegen use?
Matlab Optimize GPU Codegen 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 Matlab Optimize GPU Codegen use?
About 4.7k tokens (SKILL.md is roughly 19k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.
What are the alternatives to Matlab Optimize GPU Codegen?
Skills that share tags, products or a category with Matlab Optimize GPU Codegen: Aoti Debug (pytorch/pytorch, 104k stars), Nx Generate (nomcopter/react-mosaic, 4.8k stars), Ponytail (DavidObando/gsharp, 564 stars) and Run Nx Generator (nrwl/nx, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Matlab Optimize GPU Codegen?
matlab (a GitHub organization) maintains it in matlab/matlab-agentic-toolkit, which has 1,134 GitHub stars. The repository holds 144 skills in this directory. The repository was last updated on September 30, 2026.
Source: matlab/matlab-agentic-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.