Skill UI

Automatically evaluates Claude Code sessions at the Stop hook, identifies reusable patterns, and stores them as learned skills for future reuse, helping you capture troubleshooting steps, debugging techniques, and project conventions without manual effort.

This advanced system transforms session interactions into reusable, atomic knowledge units called "Instincts." By hooking into tool usage and session activity, it observes patterns (like preferred coding styles, error fixes, or repeated workflows). These instincts are then clustered and "evolved" into structured Skills, Commands, or specialized Agents, capturing deep contextual knowledge with weighted confidence scoring to enhance development productivity.

This skill models the expertise of a senior data scientist, covering the entire data science lifecycle. It provides advanced capabilities in statistical modeling, machine learning (deep learning, XGBoost), predictive analytics, and business intelligence. From raw data exploration (EDA) to deploying production-ready models and creating actionable dashboards, it covers technical depth across Python, R, SQL, and cloud platforms, while applying domain knowledge in finance, marketing, and operations.

Deploying Machine Learning Models automates serving trained models to production by analyzing requirements, generating API and infrastructure code, and orchestrating deployment workflows with validation, error handling, and monitoring baked in.

Personalized reports that analyze recent Claude Code chats to surface recurring challenges, highlight learning gaps, curate HackerNews resources, and deliver actionable development insights directly to your Slack DMs for targeted growth.

Feature Engineering Toolkit automates creating, selecting, and transforming dataset features to improve machine learning models; use it whenever you need new interactions, automatic selection, scaling, or encoding to boost accuracy and interpretability.

Provides detailed evaluation of machine learning models using plugin metrics to assess accuracy, precision, recall, F1, and other key indicators, helping users compare models and validate performance before deployment.

A comprehensive guide containing minimal working examples for all core Exa search operations. It demonstrates basic metadata search, deep content extraction (text, highlights, summary), finding semantically similar pages, and retrieving content for specified URLs. Ideal for developers starting a new Exa integration or learning advanced RAG patterns.

Provides interpretable explanations for ML predictions using SHAP, LIME, and other techniques, helping debug model behavior, highlight feature importance, and communicate fairness insights to stakeholders.

Automates guidance on assessing feature importance for machine learning training, covering data prep, model training, tuning, and experiment tracking while generating production-ready code, configurations, and validation instructions for best-practice compliance.

Provides minimal working examples and comprehensive instructions for querying the Fireflies.ai GraphQL API. Users can learn how to list workspace users, fetch recent meeting transcripts, and retrieve detailed summaries, including action items and keywords, using code examples in TypeScript, Python, and Bash. Ideal for initial API setup, integration testing, or learning GraphQL patterns for meeting data.

Automates Flask-based machine learning API deployment by guiding you through best practices, generating production code/configurations, and validating outputs for serving, monitoring, and MLOps pipelines.