Skill

ml-ai-assistant

Building ML & AI Systems - model training, inference optimization, MLOps pipelines, experiment tracking, prompt engineering, embeddings, vector stores, LLM application development, RAG systems, knowledge graph integration (Graphiti), meta-prompting frameworks, LLM judge evaluation, and AWS AI services (SageMaker, Bedrock). Use when performing any machine learning, deep learning, or AI engineering task.

npx claudepluginhub diegouis/provectus-marketplace --plugin proagent-ml-ai

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Comprehensive ML and AI skill covering model training, evaluation, deployment, monitoring, LLM application development, RAG systems, and knowledge graph integration.

Supporting Assets

references/deployment-patterns.mdreferences/evaluation-tracking.mdreferences/llm-patterns.mdreferences/pipeline-workflows.mdreferences/training-patterns.md

SKILL.md

Similar Skills

ml-plan

155

Generates validated, runnable implementation plans for ML pipelines, architecture designs, and multi-step projects grounded in official framework documentation.

superml

cortex

Dispatches to ML/AI sub-skills for LLM integrations, prompt engineering with evals, model pipelines, performance evaluations, RAG, and system inventory. Use for AI engineering tasks.

11 tools

tonone

ai-ml

36.5k

Orchestrates AI/ML workflows for LLM app development, RAG implementation, agent architecture, ML pipelines, and AI features. Use for production AI systems including design, integration, and observability.

antigravity-awesome-skills

Stats

Parent Repo Stars2

Parent Repo Forks1

Last CommitMar 12, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Building ML & AI Systems

Comprehensive ML and AI skill covering model training, evaluation, deployment, monitoring, LLM application development, RAG systems, and knowledge graph integration.

When to Use This Skill

Training and evaluating machine learning models (classification, regression, ranking)
Engineering features and tuning hyperparameters
Tracking experiments with MLflow or Weights & Biases
Deploying models via REST APIs, SageMaker, or Bedrock
Building LLM-powered applications with RAG and prompt engineering
Creating embeddings and managing vector stores
Monitoring model performance and detecting data drift
Building knowledge graphs with Graphiti
Evaluating AI outputs using LLM judge patterns
Designing ML pipeline validation workflows

When Invoked Without Clear Intent

MANDATORY: You MUST call the AskUserQuestion tool — do NOT render these options as text:

AskUserQuestion( header: "ML/AI", question: "What ML/AI topic do you need help with?", options: [ { label: "Model Training", description: "Scikit-learn, TensorFlow, XGBoost, feature engineering" }, { label: "Evaluation & Tracking", description: "Metrics, MLflow, W&B, experiment tracking" }, { label: "Model Deployment", description: "FastAPI serving, SageMaker, batch prediction, drift monitoring" }, { label: "LLM & RAG", description: "RAG systems, prompt engineering, embeddings, vector stores, LLM judge" } ] )

If the user selects "Other", offer: ML Pipeline Validation (project structure, validation gates).

Reference Routing

CONTEXT GUARD: Load reference files only when the user's request matches a specific topic below. Do NOT load all references upfront.

User Intent	Reference File
Model training, data splitting, scikit-learn, TensorFlow, XGBoost, feature engineering	`references/training-patterns.md`
Model evaluation, metrics, classification report, MLflow, W&B, experiment tracking	`references/evaluation-tracking.md`
Model deployment, FastAPI serving, SageMaker, batch prediction, data drift monitoring	`references/deployment-patterns.md`
RAG systems, prompt engineering, embeddings, vector stores, Graphiti, LLM judge, Bedrock, LangSmith	`references/llm-patterns.md`
ML pipeline validation, project structure, common pitfalls, validation gates	`references/pipeline-workflows.md`

Visual Diagramming with Excalidraw

Use the Excalidraw MCP server to generate ML pipeline diagrams, RAG topology maps, experiment DAGs, and model deployment architecture visualizations. Describe what you need in natural language.