Skill UI

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.

Interprets Culture Index survey and profile data to explain behavioral traits, team gas/brake/glue dynamics, burnout risk, hiring profiles, coaching cues, interview trait prediction, and conflict mediation, accepting extracted JSON or verified PDF input.

This skill provides comprehensive principles for developing multiplayer games, covering essential topics from networking architecture (Dedicated, P2P, Host-based) to advanced synchronization techniques. It details how to handle latency via prediction, interpolation, and lag compensation, optimize bandwidth using delta compression, and implement robust security measures like server authority and anti-cheat systems. Ideal for developers building real-time online experiences.

Prediction Monitor Assistant automates machine learning deployment monitoring tasks, offering step-by-step guidance, best-practice patterns, production-ready code and configuration generation, and validation to keep serving and inference workflows reliable.

Automate Replicate AI workflows via the Composio MCP integration to inspect model schemas, run predictions (sync or async), upload input files, list versions, and manage prediction history and related assets.

DeepChem is a Python library for molecular machine learning, providing featurizers, dataset loaders, splitters, and models spanning traditional ML to GNNs for property prediction, drug discovery, and materials design.

Cloud-native Rowan orchestrates medicinal chemistry and molecular modeling pipelines via a Python API, offering pKa prediction, docking, descriptors, dynamics, and AI-driven structure workflows for scalable batch screening without local HPC.

Guides using SHAP to explain ML predictions, compute feature importance, generate diagnostic plots, debug models, analyze bias, and compare models across tree, deep, linear, or black-box architectures.

This skill provides zero-shot time series forecasting using Google's TimesFM foundation model. It forecasts any univariate time series (like sales, sensor data, or weather) without requiring custom model training. The model delivers point forecasts along with calibrated prediction intervals (quantiles), offering a robust and probabilistic view of future trends. It is ideal for rapid, reliable forecasting across diverse time-based datasets.

TorchDrug is a PyTorch-native toolbox for building graph neural networks tailored to molecules, proteins, and biomedical knowledge graphs, covering property prediction, generation, retrosynthesis, and knowledge graph reasoning with curated datasets and models.

Query InterPro for protein family, domain, and GO annotations via a REST API with Python helpers, enabling function prediction, domain architecture mapping, and evolutionary classification insights for proteomic workflows.

A specialized module containing Yann LeCun's comprehensive arguments on the limitations of Large Language Models (LLMs). It critically examines the concept of 'emergent reasoning,' contrasts LLMs' statistical prediction with genuine world models, and addresses deep technical rivalries (e.g., LeCun vs. Hinton). Ideal for advanced discussions on AI causality, common sense, and AGI feasibility.