# Cudf query engine builder

> Cudf query engine builder is an open-source agent skill. Build the first native, single-GPU cuDF path in a query engine, or complete its initial adapter. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/NVIDIA/skills/tree/main/skills/cudf-query-engine-builder
- **Repository:** https://github.com/nvidia/skills
- **GitHub stars:** 4,037
- **License:** Apache-2.0
- **Skill name:** cudf-query-engine-builder
- **Collection:** https://github.com/NVIDIA/skills
- **Listing updated:** 2026-11-17

## About

Build the first native, single-GPU cuDF path in a query engine, or complete its initial adapter. Use for libcudf C++ or cuDF Java implementation, buffer ownership, worker readiness and CPU/reference comparison, including identifying missing POC inputs. Excludes standalone dataframe analysis, cuDF mainline changes, production integration and distributed or multi-GPU execution. Bundled maintainer evaluations use CPU simulations and source review; they do not run CUDA.

## When your agent uses it

> Build the first native, single-GPU cuDF path in a query engine, or complete its initial adapter. Use for libcudf C++ or cuDF Java implementation, buffer ownership, worker readiness and CPU/reference comparison, including identifying missing POC inputs. Excludes standalone dataframe analysis, cuDF mainline changes, production integration and distributed or multi-GPU execution. Bundled maintainer evaluations use CPU simulations and source review; they do not run CUDA.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Runs Python scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/cudf-query-engine-builder)
- [No network calls found in its scripts](https://github.com/NVIDIA/skills/tree/HEAD/skills/cudf-query-engine-builder)
- [License: Apache-2.0](https://github.com/NVIDIA/skills/tree/HEAD/skills/cudf-query-engine-builder)

## Install

### Claude Code

Copy the skill folder to `~/.claude/skills/cudf-query-engine-builder` to use it in all your projects:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/cudf-query-engine-builder &&
cp -R "$tmp/skills/cudf-query-engine-builder" ~/.claude/skills/cudf-query-engine-builder &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/cudf-query-engine-builder` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/cudf-query-engine-builder` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/cudf-query-engine-builder &&
cp -R "$tmp/skills/cudf-query-engine-builder" ~/.agents/skills/cudf-query-engine-builder &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/cudf-query-engine-builder` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/cudf-query-engine-builder` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/cudf-query-engine-builder &&
cp -R "$tmp/skills/cudf-query-engine-builder" ~/.cursor/skills/cudf-query-engine-builder &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/cudf-query-engine-builder` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/NVIDIA/skills.git --path skills/cudf-query-engine-builder
```

Or copy the folder to `~/.gemini/skills/cudf-query-engine-builder` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/cudf-query-engine-builder`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/cudf-query-engine-builder &&
cp -R "$tmp/skills/cudf-query-engine-builder" ~/.copilot/skills/cudf-query-engine-builder &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/cudf-query-engine-builder` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/NVIDIA/skills.git
```

Then copy `skills/skills/cudf-query-engine-builder` into your agent's skills folder as `cudf-query-engine-builder`. Agents that support SKILL.md read one folder per skill.

## FAQ

### How do I install Cudf query engine builder in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/cudf-query-engine-builder to use it in all your projects, or to .claude/skills/cudf-query-engine-builder in one project.

### Does Cudf query engine builder run scripts?

Yes. It runs Python scripts. No network calls were found in its scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use Cudf query engine builder?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

---
Source: https://ai-powered.com/skills/cudf-query-engine-builder
