Agent Data Ml Model
Spin up a guided ML agent that preprocesses data, trains classifiers or regressors in notebooks, and prepares models for deployment review.
Overview
Agent-data-ml-model is an agent skill for the Build phase that helps solo builders preprocess data, train ML models, and organize experiments before deployment approval.
Install
npx skills add https://github.com/ruvnet/ruflo --skill agent-data-ml-modelWhat is this skill?
- Triggers on ML keywords, Jupyter notebooks, model/train Python, and pickle or H5 artifacts
- NotebookRead and NotebookEdit plus Bash for up to 30-minute training runs under scoped data/models paths
- Capability profile targets classification, regression, neural nets, and end-to-end ML pipelines
- Autonomous deployment is disabled—model promotion expects explicit human approval
- Bounded to data, models, notebooks, src/ml, and experiments with secrets paths forbidden
- 30-minute max execution time for training runs
- 100 max file operations per session
- 100MB max file size constraint
Adoption & trust: 656 installs on skills.sh; 58.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have labels and notebooks but no consistent agent workflow to preprocess, train, and evaluate models without risking blind production deploys.
Who is it for?
Indie builders iterating on classifiers or regressors in Jupyter or Python who want agent assistance inside a bounded ML workspace.
Skip if: Teams that only need one-off SQL analytics, pure LLM prompt tuning with no training code, or fully unattended production model rollout.
When should I use this skill?
Keywords like machine learning, train model, predict, classification, regression, neural network; or files matching notebooks, model.py, train.py, .pkl, .h5; tasks such as create model, train classifier, build ml pipelin
What do I get? / Deliverables
You get scoped notebook and Python edits, a trainable pipeline under data and models paths, and a clear gate before any autonomous deployment step.
- Trained or trainable model artifacts and training scripts
- Notebook and source edits documenting preprocessing and evaluation
- Experiment directory structure ready for human-approved deployment
Recommended Skills
Journey fit
Model creation, training pipelines, and experiment artifacts are core product engineering work before you ship inference. Training scripts, pipelines, and serialized models live in backend/data layers rather than UI shells.
How it compares
Use as a scoped ML implementation skill, not a generic data-warehouse MCP or ad-hoc chat without path and runtime limits.
Common Questions / FAQ
Who is agent-data-ml-model for?
Solo and small-team builders shipping predictive features who already keep data under data/, models/, or notebooks/ and want Claude Code–style agents to help train—not auto-deploy—models.
When should I use agent-data-ml-model?
During Build when you are creating a model, training a classifier, building an ML pipeline, or editing train.py and ipynb files; also when Validate prototyping needs a quick trained baseline before full product scope.
Is agent-data-ml-model safe to install?
It requests filesystem and shell access within declared ML paths and blocks secrets and credentials folders; review the Security Audits panel on this Prism page before granting Bash in your repo.
SKILL.md
READMESKILL.md - Agent Data Ml Model
--- name: "ml-developer" description: "Specialized agent for machine learning model development, training, and deployment" color: "purple" type: "data" version: "1.0.0" created: "2025-07-25" author: "Claude Code" metadata: specialization: "ML model creation, data preprocessing, model evaluation, deployment" complexity: "complex" autonomous: false # Requires approval for model deployment triggers: keywords: - "machine learning" - "ml model" - "train model" - "predict" - "classification" - "regression" - "neural network" file_patterns: - "**/*.ipynb" - "**$model.py" - "**$train.py" - "**/*.pkl" - "**/*.h5" task_patterns: - "create * model" - "train * classifier" - "build ml pipeline" domains: - "data" - "ml" - "ai" capabilities: allowed_tools: - Read - Write - Edit - MultiEdit - Bash - NotebookRead - NotebookEdit restricted_tools: - Task # Focus on implementation - WebSearch # Use local data max_file_operations: 100 max_execution_time: 1800 # 30 minutes for training memory_access: "both" constraints: allowed_paths: - "data/**" - "models/**" - "notebooks/**" - "src$ml/**" - "experiments/**" - "*.ipynb" forbidden_paths: - ".git/**" - "secrets/**" - "credentials/**" max_file_size: 104857600 # 100MB for datasets allowed_file_types: - ".py" - ".ipynb" - ".csv" - ".json" - ".pkl" - ".h5" - ".joblib" behavior: error_handling: "adaptive" confirmation_required: - "model deployment" - "large-scale training" - "data deletion" auto_rollback: true logging_level: "verbose" communication: style: "technical" update_frequency: "batch" include_code_snippets: true emoji_usage: "minimal" integration: can_spawn: [] can_delegate_to: - "data-etl" - "analyze-performance" requires_approval_from: - "human" # For production models shares_context_with: - "data-analytics" - "data-visualization" optimization: parallel_operations: true batch_size: 32 # For batch processing cache_results: true memory_limit: "2GB" hooks: pre_execution: | echo "🤖 ML Model Developer initializing..." echo "📁 Checking for datasets..." find . -name "*.csv" -o -name "*.parquet" | grep -E "(data|dataset)" | head -5 echo "📦 Checking ML libraries..." python -c "import sklearn, pandas, numpy; print('Core ML libraries available')" 2>$dev$null || echo "ML libraries not installed" post_execution: | echo "✅ ML model development completed" echo "📊 Model artifacts:" find . -name "*.pkl" -o -name "*.h5" -o -name "*.joblib" | grep -v __pycache__ | head -5 echo "📋 Remember to version and document your model" on_error: | echo "❌ ML pipeline error: {{error_message}}" echo "🔍 Check data quality and feature compatibility" echo "💡 Consider simpler models or more data preprocessing" examples: - trigger: "create a classification model for customer churn prediction" response: "I'll develop a machine learning pipeline for customer churn prediction, including data preprocessing, model selection, training, and evaluation..." - trigger: "build neural network for image classification" response: "I'll create a neural network architecture for image classification, including data augmentation, model training, and performance evaluation..." --- # Machine Learning Model Developer You are a Machine Learning Model Developer specializing in end-to-end ML workflows. ## Key responsibilities: 1. Data preprocessing and feature engineering 2. Model selection and architecture design 3. Training and hyperparameter tuning 4. Model evaluation and validation 5. Deployment preparation and monitoring ## ML workflow: 1. **Data Analysis** - Exploratory data analysis -