Repository
CVCUDA/CV-CUDA agent skills
- skills
- 12
- GitHub stars
- 2.7k
GitHub description: “CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.”
- Stars
- 2,728 (264 forks)
- Licence
- Unknown
- Last push
- Sep 2026
- Created
- Aug 2022
- Homepage
- cvcuda.github.io
- gpu
- cloud
- computer-vision
- cpp
- cuda
- image-processing
- machine-learning
- python
- cv-cuda
- bytedance
- nvidia
Install all skills
npx skills add CVCUDA/CV-CUDAAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in CVCUDA/CV-CUDA, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 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). | CVCUDA/ | 2.7k | — | ~1.5k | Automated safety check: Pass | Unknown | 20 days ago |
| 2 | Drive a single-operator optimization campaign per .agents/guidance/OPTIMIZATIONGUIDELINES.md, with a deterministically enforced definition-of-done and versioned MR summary. | CVCUDA/ | 2.7k | — | ~834 | Automated safety check: Pass | Unknown | 20 days ago |
| 3 | Review a CV-CUDA operator end-to-end (support / test / bench / docs coverage). | CVCUDA/ | 2.7k | — | ~481 | Automated safety check: Pass | Unknown | 20 days ago |
| 4 | Verify a CV-CUDA optimization campaign's deterministic definition-of-done and concise versioned MR summary per .agents/guidance/OPTIMIZATIONGUIDELINES.md. | CVCUDA/ | 2.7k | — | ~424 | Automated safety check: Pass | Unknown | 20 days ago |
| 5 | 5.Make Op Add a new CV-CUDA operator end-to-end per .agents/guidance/MAKEOPGUIDELINES.md, with a deterministically-enforced definition-of-done. | CVCUDA/ | 2.7k | — | ~831 | Automated safety check: Pass | Unknown | 20 days ago |
| 6 | Scaffold a new CV-CUDA operator — a complete, wired, building skeleton — and delegate the implementation to a human or another AI. | CVCUDA/ | 2.7k | — | ~306 | Automated safety check: Pass | Unknown | 20 days ago |
| 7 | Verify a new CV-CUDA operator against the deterministic final regression checklist (the /make-op done-gate). | CVCUDA/ | 2.7k | — | ~433 | Automated safety check: Pass | Unknown | 20 days ago |
| 8 | Review a CV-CUDA operator's BENCHMARK coverage — drivers, layout axis, baselines, the basic-tier floor, row counts, and coverage statistics. | CVCUDA/ | 2.7k | — | ~274 | Automated safety check: Pass | Unknown | 20 days ago |
| 9 | Review a CV-CUDA operator's DOCS & API artifacts — operatorlist row, Python autofunction (fn + into), Limitations-table-vs-code consistency, docstrings, and SPDX headers. | CVCUDA/ | 2.7k | — | ~270 | Automated safety check: Pass | Unknown | 20 days ago |
| 10 | Review a CV-CUDA operator's input-type, layout, dtype, and channel support matrix. | CVCUDA/ | 2.7k | — | ~248 | Automated safety check: Pass | Unknown | 20 days ago |
| 11 | Review a CV-CUDA operator's test coverage, including C++ correctness, required cross-layout parity, correctness rigor, and the Python API surface. | CVCUDA/ | 2.7k | — | ~264 | Automated safety check: Pass | Unknown | 20 days ago |
| 12 | Check whether a CV-CUDA operator is READY to optimize (correctness + bench coverage + captured baseline + profiling) per .agents/guidance/OPTIMIZATIONGUIDELINES.md. | CVCUDA/ | 2.7k | — | ~255 | Automated safety check: Pass | Unknown | 20 days ago |
Questions, answered from the data.
What is the best skill in CVCUDA/CV-CUDA?
Refactor Op from CVCUDA/CV-CUDA ranks first of the 12 skills in CVCUDA/CV-CUDA listed here, with the highest score: its repository has 2.7k GitHub stars, its SKILL.md loads about 1.5k tokens and it passes the automated safety check with no findings. Next come Optimize Op and Review Op.
Are the skills in CVCUDA/CV-CUDA official?
None yet. All 12 skills in CVCUDA/CV-CUDA listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from CVCUDA/CV-CUDA?
Run npx skills add CVCUDA/CV-CUDA in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.