Index of every page on this site: llms.txt
All skills
langchain-ai avatar

/cudf-analytics

@3748a9e
by LangChainlangchain-ai/deepagents31k stars
4,447
Run it yourself

Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical summaries, anomaly detection, or large-scale data profiling.

Use this Skill: https://skilld.dev/gh/langchain-ai/deepagents/cudf-analytics

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈58 tokens for metadata: the name and description. ≈824 when used: this file.

Description uses 2.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈231 characters, or 2.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

cuDF Analytics Skill

GPU-accelerated data analysis using NVIDIA RAPIDS cuDF. cuDF provides a pandas-like API that runs on NVIDIA GPUs, enabling massive speedups on large datasets.

When to Use This Skill

Use this skill when:

  • Analyzing CSV files, datasets, or tabular data
  • Computing statistical summaries (mean, median, std, quartiles)
  • Performing groupby aggregations
  • Detecting anomalies or outliers in data
  • Profiling datasets with millions of rows
  • Computing correlation matrices

Initialization (REQUIRED)

Always start every script with this boilerplate. It tests actual GPU operations, not just import.

import pandas as pd

try:
    import cudf
    # Smoke-test: verify GPU compute AND host transfer both work
    _test = cudf.Series([1, 2, 3])
    assert _test.sum() == 6
    assert _test.to_pandas().tolist() == [1, 2, 3]
    GPU = True
except Exception as e:
    print(f"[GPU] cudf unavailable, falling back to pandas: {e}")
    GPU = False

def read_csv(path):
    return cudf.read_csv(path) if GPU else pd.read_csv(path)

def to_pd(df):
    """Convert cuDF DataFrame/Series to pandas. Use this instead of .to_pandas() directly."""
    if not GPU:
        return df
    try:
        return df.to_pandas()
    except Exception as e:
        print(f"[GPU] .to_pandas() failed, using Arrow fallback: {e}")
        return df.to_arrow().to_pandas()

Quick Reference

cuDF mirrors the pandas API. Common operations:

Read Data

df = read_csv("data.csv")

Statistical Summary

# Use to_pd() when you need pandas output
summary = to_pd(df[["value", "score"]].describe())

# Scalar values work directly with float()
mean_val = float(df["value"].mean())
q1 = float(df["value"].quantile(0.25))

# Correlation
corr = float(df["value"].corr(df["score"]))

Groupby Aggregation

result = df.groupby("category").agg({
    "revenue": ["sum", "mean", "count"],
    "quantity": ["sum", "mean"],
})
result_pd = to_pd(result)

Anomaly Detection (IQR Method)

col = "value"
Q1 = float(df[col].quantile(0.25))
Q3 = float(df[col].quantile(0.75))
IQR = Q3 - Q1
lower = Q1 - 1.5 * IQR
upper = Q3 + 1.5 * IQR
outliers = to_pd(df[(df[col] < lower) | (df[col] > upper)])

Anomaly Detection (Z-Score Method)

mean = float(df[col].mean())
std = float(df[col].std())
df["z_score"] = (df[col] - mean) / std
anomalies = to_pd(df[df["z_score"].abs() > 3])

Filtering and Selection

# Filter rows
filtered = df[df["status"] == "active"]

# Select columns
subset = df[["name", "revenue", "date"]]

# Sort
sorted_df = df.sort_values("revenue", ascending=False)

# Convert to pandas for final output / iteration
result_pd = to_pd(sorted_df)

Data Type Requirements

cuDF requires explicit type specification for optimal performance:

  • Use float32 or float64 for numeric data
  • Use int32 or int64 for integer data
  • String columns use cuDF's string dtype automatically

Output Guidelines

When reporting analysis results:

  • Include dataset dimensions (rows x columns)
  • Show key statistics in formatted tables
  • Highlight notable patterns, trends, or anomalies
  • Provide both summary statistics and specific examples
  • Note any data quality issues (missing values, outliers)

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts7mo5 checks · Risk SAFE
  • Gen Agent Trust Hub8mo

    This skill enables GPU-accelerated data analysis and is generally safe for its intended use case. It includes a standard security consideration regarding the processing of external data files, which is typical for tools of this nature. Please see the detailed analysis for context.

  • Socket8mo

    No alerts

  • Snyk8mo

    Risk: LOW · No issues

  • Runlayer8mo

    1 file scanned · No issues

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 3748a9e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 hours ago.

Activeupdated 8 months ago

README badge

README badge for langchain-ai/deepagents/cudf-analytics