What is accelerated-computing-cudf?

Implementation guidance for NVIDIA cuDF, a GPU-based library for working with table-like data in Python, plus its pandas and multi-GPU options.

Use it to speed up data loading, cleaning, joins, grouping, and CSV or Parquet processing on supported NVIDIA GPUs.

It helps you choose between familiar pandas-compatible code and explicit GPU code while preserving data types, missing values, ordering, and expected results.

accelerated-computing-cudf — Skill for Codex by PracticalSwan

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add PracticalSwan/agent-skills --skill accelerated-computing-cudf

Clone the repo

git clone --depth 1 https://github.com/PracticalSwan/agent-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/practicalswan/agent-skills/accelerated-computing-cudf/github.svg)](https://agentmods.dev/skills/practicalswan/agent-skills/accelerated-computing-cudf)

Your own site

<a href="https://agentmods.dev/skills/practicalswan/agent-skills/accelerated-computing-cudf"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/accelerated-computing-cudf/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/practicalswan/agent-skills/accelerated-computing-cudf"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/accelerated-computing-cudf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,010 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 88% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.03010
Opus 5.5	$0.00022	$0.01204
Sonnet 5.5	$0.00011	$0.00602
Haiku 4.5	$0.00006	$0.00301

Measured 2d ago against content hash f60a67d4ffe3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

accelerated-computing-cudf scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 23 executable files (evals/files/cudf-apply-udf/code/generate_data.py, evals/files/cudf-apply-udf/code/udf_pipeline.py, evals/files/cudf-csv-etl/code/etl_pipeline.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

88% identical to accelerated-computing-cudf — 64 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

accelerated-computing-cudf/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cuDF & dask-cuDF Implementer's Guide

Compatibility

Development release tracked by this skill: 26.12 (VERSION: 26.12.00). Use the selected installed release for deployment requirements.
Read dependencies.yaml for the support matrix (py_version group for Python versions, cuda_version for CUDA versions). Match cuDF, pylibcudf, libcudf, and RMM release versions, and match pip wheel suffixes (-cu12 / -cu13) to the CUDA major version.
Requires a supported NVIDIA GPU and compatible driver. Check the installation requirements for the selected release and CUDA version.
For another checkout or installed release, check VERSION, dependencies.yaml, python/cudf/pyproject.toml, and cudf.__version__ before choosing versions or relying on an API.

Naming

Use NVIDIA library-first wording in user-facing answers. Keep literal RAPIDS/rapidsai URLs, package names, and release metadata when citing sources.

Role

You are a cuDF expert helping an implementer work with GPU DataFrames. The user understands pandas and their data — your job is to get them to correct, fast GPU code with minimal friction. Choose the path from the user's intent: cudf.pandas for broad compatibility or minimal-change acceleration, explicit cuDF for named DataFrame migrations, hot ETL paths, and parity-sensitive work. Treat source schema, row counts, null placement, ordering, and numeric tolerances as user-visible behavior.

Critical Rules

Choose the right cuDF path. Use cudf.pandas for broad compatibility or minimal-change acceleration. Use explicit cuDF when the user asks to migrate DataFrame code, inspect parity, optimize a visible ETL hot path, or control unsupported operations.
Benchmark the working set. GPU transfer and launch overhead can dominate small workloads; 100K rows is a starting heuristic, not a minimum. Use small data for correctness and representative data for performance.
Keep conversions at boundaries. Use .to_pandas() or .to_numpy() for CPU-only libraries, display, or final output boundaries. .values and .to_cupy() return GPU arrays, not NumPy arrays. Keep intermediate ETL data on GPU.
Choose precision deliberately. Float32 reduces memory use and may improve throughput, but preserve float64 when accuracy requires it and benchmark the target hardware.
Validate semantics on representative slices. For null handling, joins, time series, reshape, or grouped logic, keep a small pandas reference path and compare shape, labels, null counts, ordering, and representative values before claiming parity.
For data > GPU memory, move to dask-cuDF with enable_cudf_spill=True. See references/dask-cudf-patterns.md.

Read the full file on GitHub · 251 lines

Files

What ships with it

34 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago Changed · +5 lines f60a67d4ffe3
1mo ago Changed · -1 lines 91bfaf9fcaa7
1mo ago Changed cb91787a5852
1mo ago Changed 3741f743669b
1mo ago First seen · 247 lines · 56 tokens per session scan A 63325e06664f

Subscribe to this mod's changes

accelerated-computing-cudf is a skill published in the GitHub repository PracticalSwan/agent-skills (21 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 3,010 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to accelerated-computing-cudf, differing in 64 lines, and is treated as a copy.

Data and AI ETL GPU Languages NVIDIA Python RAPIDS cudf pandas

neo4j-knowledge-graph

Use when designing, importing, querying, or modernizing Neo4j knowledge graphs from CSV, Excel, pandas, Cypher, py2neo, the official neo4j Python driver, vector indexes, or GraphRAG workflows.

MazzaWill/neo4j-python-pandas-py2neo-v3 · 55 tokens

geopandas

Use when doing vector spatial analysis in Python — gpd.readfile/tofile via pyogrio (GPKG, Shapefile, GeoParquet), sjoin/sjoinnearest, overlay, clip, dissolve, tocrs vs setcrs, gdf.plot choropleth; also for CRSError from a missing PROJ data dir, area/distance computed in degrees, or GeoDataFrame geometry-column…

znlgis/opengis-skills · 108 tokens

python-panel-data

Panel data analysis with Python using linearmodels and pandas.

brycewang-stanford/Auto-Empirical-Research-Skills · 17 tokens

rapids-first

Use only when the user explicitly mentions "rapids-first" or "RAPIDS first", to prefer the RAPIDS GPU stack (cudf, cuml, cupy, cupyx) and its zero-code accelerators over pandas, scikit-learn, numpy and scipy when writing Python data-science, ML, ETL or numerical code.

TioSisai/rapids-first · 76 tokens

python-panel-data

Panel data analysis with Python using linearmodels and pandas.

meleantonio/awesome-econ-ai-stuff · 17 tokens

data-analysis

Structured data analysis workflow from raw data to shareable insights.

furkangonel/cowrangler · 15 tokens

accelerated-computing-cudf

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

cuDF & dask-cuDF Implementer's Guide

Compatibility

Naming

Role

Critical Rules

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

neo4j-knowledge-graph

geopandas

python-panel-data

rapids-first

python-panel-data

data-analysis