Skip to main content
affpapa.org
RU EN
skill CX Codex

accelerated-computing-cudf — Claude Code skill for GPU DataFrames

Guidance for using cuDF and dask-cuDF to move pandas-style data work onto GPUs and check that results keep the expected semantics.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add NVIDIA/skills --skill accelerated-computing-cudf -a claude-code
Open on GitHub

What accelerated-computing-cudf does

The skill selects a cuDF approach based on the task: cudf.pandas when keeping pandas code mostly intact matters, explicit cuDF for targeted migrations and control, and dask-cuDF when a dataset exceeds GPU memory. Its guidance covers CSV and Parquet input, joins, grouped calculations, and missing-value handling.

It also walks through version compatibility, comparisons against pandas, and GPU memory choices. For distributed work, the examples configure enable_cudf_spill=True; running cuDF requires a supported NVIDIA GPU and a compatible driver. Small workloads can spend more time on GPU transfer and launch overhead than on computation, so benchmark representative data before judging performance.

What it helps with

  • move pandas DataFrame operations to a GPU
  • read CSV or Parquet data with cuDF
  • compare pandas and cuDF results for nulls and row ordering
  • process data larger than GPU memory with dask-cuDF

Example prompts for the agent

  • Convert this pandas code to cuDF and compare the outputs on a small sample.
  • Set up Parquet input and a groupby in cuDF while keeping intermediate data on the GPU.
  • Show how to handle a dataset larger than GPU memory with dask-cuDF and enable_cudf_spill=True.

How to install accelerated-computing-cudf

1Skills CLI (Vercel)

npx skills add NVIDIA/skills --skill accelerated-computing-cudf -a claude-code

2Manually: put the files in place

~/.claude/skills/accelerated-computing-cudf/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/accelerated-computing-cudf/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about accelerated-computing-cudf

How do I install accelerated-computing-cudf in Claude Code?

Run npx skills add NVIDIA/skills --skill accelerated-computing-cudf -a claude-code. The skill file is installed at ~/.claude/skills/accelerated-computing-cudf/SKILL.md.

What does accelerated-computing-cudf do?

It guides an agent through cuDF and dask-cuDF implementation, including data loading, ETL operations, and checks against pandas results.

What is required to run cuDF?

A supported NVIDIA GPU and a compatible driver are required. Check the selected cuDF release against the CUDA version in use.

Similar skills

All skills for Data and databases →
xlsx official anthropics Creates, reads, edits, and converts spreadsheet files. Use it when the requested deliverable is an Excel workbook or another tabular file. 187,223installs google-agents-cli-observability official Google This skill guides you through tracing and monitoring AI agents, including ADK agents. Use it when you need to inspect agent execution or monitor a deployed agent. CX Codex +1 511,300installs caveman-evidence-review JuliusBrussee A read-only skill reviews Caveman Cloud evidence on LLM spend, traces, and routing. Use it to see where a project’s model budget goes. CX Codex +1 104,500installs migration JuliusBrussee Enforces reversible, compatibility-safe transitions for schema, data, and API updates. Useful whenever data loss or rollout downtime is unacceptable. CX Codex +1 103,900installs performance-optimization addyosmani An agent skill that measures before it changes code: Core Web Vitals budgets, N+1 queries, missing indexes and slow endpoints. CX Codex +1 65,200installs supabase official supabase Guides the agent through database configuration and strict RLS policies in Supabase. CX Codex GP ChatGPT 8installs

From the same set178

rag-blueprint This skill deploys, configures, troubleshoots, and manages NVIDIA RAG Blueprint. Use it when RAG services run through Docker, Kubernetes, or library workflows. CX Codex +1 3,300installs cuopt-developer Guides AI coding assistants through modifying and building NVIDIA cuOpt internals, covering C++/CUDA and Python bindings. CX Codex +1 2,700installs cudaq-guide Walks you through CUDA-Q installation, simulation targets, QPU access and Python kernel authoring. Useful when you need to get moving with NVIDIA's quantum stack. CX Codex +1 2,500installs cuopt-install Installs NVIDIA cuOpt for Python, C, or as a REST server via pip, conda, or Docker, then verifies the setup. Helpful when configuring GPU-accelerated routing environments. CX Codex +1 2,500installs data-designer Creates synthetic datasets and Python data-generation pipelines with Data Designer. Use it when you need to describe a dataset and turn that description into a script. CX Codex +1 2,500installs deepstream-dev Teaches the agent to write NVIDIA DeepStream SDK code in Python: GStreamer pipelines, TensorRT inference, tracking and broker output. CX Codex +1 2,400installs nemo-retriever Indexes and queries document collections using the NeMo Retriever 26.8.1 CLI. Useful for local LanceDB storage and deployed Retriever services. CX Codex +1 2,400installs rag-eval Evaluates filesystem RAG datasets built around corpus/ and train.json. Use it to compare retrieval and generation settings with RAGAS quality scores. CX Codex +1 2,400installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor