cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
- Installs
- 247
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/langchain-ai/deepagents --skill cuml-machine-learning- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads cuml-machine-learning automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
cuML Machine Learning Skill
GPU-accelerated machine learning using NVIDIA RAPIDS cuML. cuML provides a scikit-learn-compatible API that runs on NVIDIA GPUs, enabling massive speedups on large datasets.
When to Use This Skill
Use this skill when:
- Training classification models (predict categories, detect fraud, classify text)
- Training regression models (forecast values, predict prices, estimate quantities)
- Clustering data (segment customers, group documents, find patterns)
- Dimensionality reduction (visualize high-dimensional data, compress features)
- Preprocessing and feature engineering on large datasets
- Any ML task on datasets with 10K+ rows where GPU acceleration helps
Initialization (REQUIRED)
Always start every script with this boilerplate. It tests actual GPU ML operations.
import pandas as pd
import numpy as np
try:
import cudf
import cuml
# Smoke-test: verify GPU ML works end-to-end
_test_data = cudf.DataFrame({'a': [1.0, 2.0, 3.0, 4.0], 'b': [5.0, 6.0, 7.0, 8.0]})
_km = cuml.cluster.KMeans(n_clusters=2, n_init=1, random_state=42)
_km.fit(_test_data)
assert len(_km.labels_) == 4
GPU = True
except Exception as e:
print(f"[GPU] cuml unavailable, falling back to scikit-learn: {e}")
GPU = False
def read_csv(path):
return cudf.read_csv(path) if GPU else pd.read_csv(path)
def to_pd(df):
"""Convert cuML/cuDF output 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()
Import Patterns
# GPU mode
if GPU:
from cuml.cluster import KMeans, DBSCAN, HDBSCAN
from cuml.ensemble import RandomForestClassifier, RandomForestRegressor
from cuml.linear_model import LinearRegression, Ridge, Lasso, LogisticRegression
from cuml.neighbors import KNeighborsClassifier, KNeighborsRegressor
from cuml.svm import SVC, SVR
from cuml.decomposition import PCA, TruncatedSVD
from cuml.manifold import UMAP, TSNE
from cuml.preprocessing import StandardScaler, MinMaxScaler, LabelEncoder
from cuml.model_selection import train_test_split
from cuml.metrics import accuracy_score, r2_score, mean_squared_error
# CPU fallback
else:
from sklearn.cluster import KMeans, DBSCAN, HDBSCAN
from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
from sklearn.linear_model import LinearRegression, Ridge, Lasso, LogisticRegression
from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor
from sklearn.svm import SVC, SVR
from sklearn.decomposition import PCA, TruncatedSVD
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler, MinMaxScaler, LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, r2_score, mean_squared_error
# UMAP not in sklearn — skip or pip install umap-learn
Quick Reference
Train/Test Split (Start Here)
X = df[["feature1", "feature2", "feature3"]].astype("float32")
y = df["target"]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
Classification
model = RandomForestClassifier(n_estimators=100, max_depth=10, random_state=42)
model.fit(X_train, y_train)
predictions = model.predict(X_test)
accuracy = float(accuracy_score(to_pd(y_test), to_pd(predictions)))
print(f"Accuracy: {accuracy:.4f}")
# Feature importances (tree models only)
importances = to_pd(model.feature_importances_)
for name, imp in zip(feature_names, importances):
print(f" {name}: {imp:.4f}")
Regression
model = Ridge(alpha=1.0)
model.fit(X_train, y_train)
predictions = model.predict(X_test)
r2 = float(r2_score(to_pd(y_test), to_pd(predictions)))
mse = float(mean_squared_error(to_pd(y_test), to_pd(predictions)))
print(f"R² Score: {r2:.4f}")
print(f"MSE: {mse:.4f}")
# Coefficients
coeffs = to_pd(model.coef_)
print(f"Intercept: {float(model.intercept_):.4f}")
Clustering (KMeans)
X = df[["feature1", "feature2"]].astype("float32")
model = KMeans(n_clusters=4, n_init=10, random_state=42)
model.fit(X)
labels = to_pd(model.labels_)
centroids = to_pd(model.cluster_centers_)
inertia = float(model.inertia_)
print(f"Inertia: {inertia:.2f}")
print(f"Cluster sizes: {labels.value_counts().sort_index().to_dict()}")
print(f"Centroids:\n{centroids}")
Dimensionality Reduction (PCA)
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X.astype("float32"))
pca = PCA(n_components=3)
X_reduced = pca.fit_transform(X_scaled)
variance_ratio = to_pd(pca.explained_variance_ratio_)
print(f"Explained variance: {[f'{v:.4f}' for v in variance_ratio]}")
print(f"Total explained: {float(sum(variance_ratio)):.4f}")
Dimensionality Reduction (UMAP — GPU only)
if GPU:
reducer = UMAP(n_components=2, n_neighbors=15, min_dist=0.1, random_state=42)
embedding = to_pd(reducer.fit_transform(X_scaled))
print(f"UMAP embedding shape: {embedding.shape}")
Preprocessing
# Scale numeric features
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X.astype("float32"))
# Encode categorical columns
le = LabelEncoder()
df["category_encoded"] = le.fit_transform(df["category"])
Data Type Requirements
- cuML requires float32 or float64 for features. Always cast:
X.astype("float32") - Integer targets (classification labels) work directly
- Categorical columns must be encoded first (LabelEncoder or OneHotEncoder)
- cuML does NOT support sparse matrices — always use dense data
Gotchas
| Issue | Fix |
|---|---|
TypeError: sparse input | Convert to dense: X.toarray() or don't use sparse |
PCA solver='randomized' fails | Use solver='full' or omit (cuML auto-selects) |
| UMAP not available on CPU | Skip UMAP in CPU mode or pip install umap-learn |
| Float64 slower than float32 | Cast to float32: X.astype("float32") |
| Large dataset OOM | Reduce features or sample data before fitting |
Output Guidelines
When reporting ML results:
- Include dataset shape (rows × features) and target distribution
- Show train/test split sizes
- Report key metrics in a formatted table (accuracy, R², MSE, etc.)
- For classification: show per-class metrics if multi-class
- For clustering: show cluster sizes and centroid summaries
- For dimensionality reduction: show explained variance ratios
- List feature importances ranked by magnitude
- Note any data quality issues (class imbalance, missing values, outliers)
FAQ
What does the cuml-machine-learning skill do?
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
How do I install cuml-machine-learning?
Run npx skills add https://github.com/langchain-ai/deepagents --skill cuml-machine-learning in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/cuml-machine-learning/ (personal) or .claude/skills/cuml-machine-learning/ (project).
Which AI agents can use cuml-machine-learning?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is cuml-machine-learning safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains cuml-machine-learning?
It is published by langchain-ai in langchain-ai/deepagents, and it is an official skill from the maker of the technology it covers. It has 247 recorded installs.
More from langchain-ai/deepagents
langgraph-docs
langchain-ai/deepagents
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use when the user asks about LangGraph, graph agents, state machines, agent orchestration, LangGraph API, or needs LangGraph implementation guidance.
web-research
langchain-ai/deepagents
Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic online, search the web, look something up, find current information, compare options, or produce a research report.
social-media
langchain-ai/deepagents
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
arxiv-search
langchain-ai/deepagents
Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look up preprints, find academic articles in physics, math, CS, biology, statistics, or related fields.
blog-post
langchain-ai/deepagents
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
skill-creator
langchain-ai/deepagents
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like "create a skill", "new skill", "make a skill", "skill for X", "how do I create a skill", or "help me build a skill".
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available