#136136th of 149 in Skills, plugins and rules
skills
Catalog of NVIDIA-maintained agent skills for Claude Code, Codex, Cursor and Kiro
- Stars
- 3.5k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
A mirror of agent skills maintained in NVIDIA product repos, synced daily and installed with `npx skills add nvidia/skills`. The catalog covers cuOpt, cuDF, CUDA-Q, DOCA, Jetson BSP, Holoscan, BioNeMo, Dynamo, DeepStream and others, with many skills per product. Skills can be installed singly or per agent (claude-code, codex, cursor, kiro-cli, cortex).
Who it is for: Developers using coding agents with NVIDIA SDKs, CUDA-X, Jetson or DOCA
Strengths
- Install one skill or several agents in a single `npx skills add` command
- Skills are maintained in product repos and synced daily, so they track upstream
- Wide coverage of NVIDIA software: cuOpt, cuDF, DOCA, Jetson, BioNeMo, Dynamo
- Targets several agents: Claude Code, Codex, Cursor, Kiro, Snowflake CoCo
Weaknesses
- Only useful for NVIDIA software and hardware workflows
- Mirror only; fixes must go to the upstream product repos
- Requires skills CLI v1.5.16 or newer, or skills may not appear in Claude Code
- Skills are renamed or consolidated over time, so local copies need `npx skills update`
What it needs
- Needs Node.js (npx), skills CLI (vercel-labs/skills)
- Models: Claude Code, Codex, Cursor, Kiro, Snowflake CoCo
Also in Skills, plugins and rules
See all 149| Rank | Project | Score |
|---|---|---|
| 1 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| #4 | impeccableDesign skill with 24 commands and a detector for AI-generated frontends | 94 out of 100 |
| #5 | ponytailSkill prompt that makes coding agents write less code and add tests | 92 out of 100 |