Cutlass Skill
slowlyC/agent-gpu-skills
Write, debug, and optimize CUTLASS, CuTe, and CuTeDSL GPU kernels from local upstream source, examples, and headers.
Drive a single-operator optimization campaign per .agents/guidance/OPTIMIZATIONGUIDELINES.md, with a deterministically enforced definition-of-done and versioned MR summary.
Install Optimize Op
$ npx skills add CVCUDA/CV-CUDA --skill optimize-op -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CVCUDA/CV-CUDA optimize-op --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/CVCUDA/CV-CUDA.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/optimize-op .claude/skills/optimize-op && 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 "optimize-op" agent skill from https://github.com/CVCUDA/CV-CUDA/tree/main/.agents/skills/optimize-op into .claude/skills/optimize-op/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "optimize-op", 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/CVCUDA/CV-CUDA/tree/main/.agents/skills/optimize-opType 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 CVCUDA/CV-CUDA --skill optimize-op -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CVCUDA/CV-CUDA optimize-op --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CVCUDA/CV-CUDA.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/optimize-op .agents/skills/optimize-op && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "optimize-op" agent skill from https://github.com/CVCUDA/CV-CUDA/tree/main/.agents/skills/optimize-op into .agents/skills/optimize-op/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "optimize-op", 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 CVCUDA/CV-CUDA --skill optimize-op -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CVCUDA/CV-CUDA optimize-op --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CVCUDA/CV-CUDA.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/optimize-op .cursor/skills/optimize-op && 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 "optimize-op" agent skill from https://github.com/CVCUDA/CV-CUDA/tree/main/.agents/skills/optimize-op into .cursor/skills/optimize-op/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "optimize-op", 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/CVCUDA/CV-CUDA.git --path .agents/skills/optimize-op--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 CVCUDA/CV-CUDA --skill optimize-op -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CVCUDA/CV-CUDA optimize-op --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CVCUDA/CV-CUDA.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/optimize-op .gemini/skills/optimize-op && 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 "optimize-op" agent skill from https://github.com/CVCUDA/CV-CUDA/tree/main/.agents/skills/optimize-op into .gemini/skills/optimize-op/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "optimize-op", 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 CVCUDA/CV-CUDA optimize-opInstalls 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 CVCUDA/CV-CUDA --skill optimize-op -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CVCUDA/CV-CUDA.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/optimize-op .github/skills/optimize-op && 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 "optimize-op" agent skill from https://github.com/CVCUDA/CV-CUDA/tree/main/.agents/skills/optimize-op into .github/skills/optimize-op/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "optimize-op", 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 CVCUDA/CV-CUDA --skill optimize-op -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CVCUDA/CV-CUDA optimize-op --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CVCUDA/CV-CUDA.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/optimize-op .opencode/skills/optimize-op && 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 "optimize-op" agent skill from https://github.com/CVCUDA/CV-CUDA/tree/main/.agents/skills/optimize-op into .opencode/skills/optimize-op/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "optimize-op", 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
optimize-op- GitHub stars
- 2.7k
- Token cost
- ~834 tokens
- SKILL.md length
- 299 words
- Files
- 1
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Drive a single-operator optimization campaign per .agents/guidance/OPTIMIZATIONGUIDELINES.md, with a deterministically enforced definition-of-done and versioned MR summary.
- Works in 5 steps: Run python3 tools/optimize_op.py --phase… → Survey and baseline the full union… → Initialize the concise v1 MR summary… → …
- Asked to optimize an operator
- Calls python3
- Finish a performance campaign
What it does
Optimize Op is an agent skill from CVCUDA/CV-CUDA. Drive a single-operator optimization campaign per .agents/guidance/OPTIMIZATIONGUIDELINES.md, with a deterministically enforced definition-of-done and versioned MR summary. Use when asked to optimize an operator, run or finish a performance campaign, generate or refresh its MR performance summary, or verify that a perf MR satisfies correctness, benchmark, baseline, lead-exhaustion, memory, and API/ABI gates.
Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. It works with Python, NVIDIA AI Platform and CUDA. The repository describes itself as: CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
When your agent uses it
- Asked to optimize an operator
- Finish a performance campaign
- Refresh its MR performance summary
- Verify that a perf MR satisfies correctness
Example prompts
- “/optimize-op”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Run python3 tools/optimize_op.py --phase preflight. Resolve every
- Survey and baseline the full union expanded from all declared basic and
- Initialize the concise v1 MR summary from exact optimized case keys
- Refresh the description with reference-SKU evidence and finalize it
- Run the final gate
What it can do on your machine
Read from SKILL.md and the folder at commit b051f32. 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:
python3
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
Optimize Op loads about 834 tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 299 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 299 words (~834 tokens).
“[//]: # "SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved." [//]: # "SPDX-License-Identifier: Apache-2.0"”
- name
- optimize-op
Files
Just SKILL.md in .agents/skills/optimize-op of CVCUDA/CV-CUDA.
Open the folder on GitHubat commit b051f32
Compare with similar skills
Optimize Op 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 |
|---|---|---|---|---|---|---|
| Optimize Op this skillCVCUDA/CV-CUDA | 2.7k | — | ~834 | Automated safety check: Pass | Custom licence | |
| Cutlass SkillslowlyC/agent-gpu-skills | 169 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Triton SkillslowlyC/agent-gpu-skills | 169 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Vllm Deploy Simplevllm-project/vllm-skills | 103 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Hyperpod Version Checkerawslabs/agent-plugins | 915 | 1 repos | ~910 | Automated safety check: Pass | Apache-2.0 | |
| Quark Env Preflightamd/Quark | 181 | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Triton Skill
slowlyC/agent-gpu-skills
Write, debug, and optimize Triton and Gluon GPU kernels from local upstream tutorials, production kernels, language definitions, and compiler source.
Vllm Deploy Simple
vllm-project/vllm-skills
Quick install and deploy vLLM, start serving with a simple LLM, and test OpenAI API.
- Official
Hyperpod Version Checker
awslabs/agent-plugins
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia)…
Quark Env Preflight
amd/Quark
Collect and normalize environment facts (OS, Python, GPU, CUDA/ROCm, container state) before Quark installation or PTQ planning.
- Official
Nv Segment Ct
NVIDIA/skills
Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.
More from CVCUDA/CV-CUDA
All 12 skills in this repoRefactor Op
CVCUDA/CV-CUDA
Find and safely apply per-operator refactoring / redundancy-reduction opportunities in a CV-CUDA operator (near-duplicate Tensor/VarShape kernels, reinvented shared utilities, dead code).
Review Op
CVCUDA/CV-CUDA
Review a CV-CUDA operator end-to-end (support / test / bench / docs coverage).
Optimize Op Verify
CVCUDA/CV-CUDA
Verify a CV-CUDA optimization campaign's deterministic definition-of-done and concise versioned MR summary per .agents/guidance/OPTIMIZATIONGUIDELINES.md.
Make Op
CVCUDA/CV-CUDA
Add a new CV-CUDA operator end-to-end per .agents/guidance/MAKEOPGUIDELINES.md, with a deterministically-enforced definition-of-done.
Make Op Scaffold
CVCUDA/CV-CUDA
Scaffold a new CV-CUDA operator — a complete, wired, building skeleton — and delegate the implementation to a human or another AI.
Make Op Verify
CVCUDA/CV-CUDA
Verify a new CV-CUDA operator against the deterministic final regression checklist (the /make-op done-gate).
Related
Works with
Categories
Questions about Optimize Op
What does Optimize Op do?
Drive a single-operator optimization campaign per .agents/guidance/OPTIMIZATIONGUIDELINES.md, with a deterministically enforced definition-of-done and versioned MR summary. Optimize Op is an agent skill from CVCUDA/CV-CUDA.md, with a deterministically enforced definition-of-done and versioned MR summary.
When should I use Optimize Op?
Optimize Op fits situations like: asked to optimize an operator; finish a performance campaign; refresh its MR performance summary; verify that a perf MR satisfies correctness.
How do I install Optimize Op in Claude Code?
Run `npx skills add CVCUDA/CV-CUDA --skill optimize-op -a claude-code`. Or copy the skill folder (.agents/skills/optimize-op in CVCUDA/CV-CUDA) into .claude/skills/optimize-op in your project. Claude Code loads it when a task matches its description.
How do I install Optimize Op in Codex?
Run `npx skills add CVCUDA/CV-CUDA --skill optimize-op -a codex`. Or copy the skill folder (.agents/skills/optimize-op in CVCUDA/CV-CUDA) into .agents/skills/optimize-op in your project. Codex loads it when a task matches its description.
Can I use Optimize Op 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 CVCUDA/CV-CUDA --skill optimize-op -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/optimize-op, .gemini/skills/optimize-op, .github/skills/optimize-op and .opencode/skills/optimize-op in your project.
What does Optimize Op need to run?
Going by SKILL.md and its folder, Optimize Op needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Optimize Op 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 Optimize Op 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 Optimize Op use?
Optimize Op 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 Optimize Op use?
About 834 tokens (SKILL.md is roughly 3.3k 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 Optimize Op?
Skills that share tags, products or a category with Optimize Op: Cutlass Skill (slowlyC/agent-gpu-skills, 169 stars), Triton Skill (slowlyC/agent-gpu-skills, 169 stars), Vllm Deploy Simple (vllm-project/vllm-skills, 103 stars) and Hyperpod Version Checker (awslabs/agent-plugins, 915 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Optimize Op?
CVCUDA (a GitHub organization) maintains it in CVCUDA/CV-CUDA, which has 2,728 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 16, 2026.
Source: CVCUDA/CV-CUDA on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.