Skill UI

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.

Combines ESM3 and ESM C protein language models to generate sequences, predict structures, condition functions, and extract embeddings via local or Forge API inference for protein design and engineering workflows.

PyHealth delivers a full-stack Python toolkit for building, evaluating, and deploying clinical machine learning models, covering EHR datasets, medical coding systems, physiological signals, and healthcare-tailored architectures such as RETAIN, SafeDrug, and Transformer-based pipelines.

Stable Baselines3 is a robust, PyTorch-based library providing production-ready implementations of core reinforcement learning algorithms (PPO, SAC, DQN, etc.). It facilitates the training of single-agent RL models, supports the creation of custom Gymnasium environments, and handles advanced parallel training via vectorized environments. It is ideal for rapid prototyping and rigorous RL experiments.

This comprehensive skill provides an end-to-end solution for video and audio content creation. Users can upload videos from various sources (YouTube, local files) and perform advanced operations such as real-time streaming, semantic search, and complex editing (trimming, overlays). Key features include AI-powered transcription, subtitle generation, and the ability to generate diverse media assets like images, music, sound effects, and voiceovers, making it ideal for content creators and media professionals.

Python toolkit that queries the arXiv Atom API to search papers by keywords, authors, categories, or IDs, filter results, download PDFs, and emit structured JSON for AI/ML literature reviews and monitoring.

AuraKit converts a single /aura command into a secure full-stack Claude pipeline with 34 modes, OWASP SEC-01~15 safeguards, runtime hooks, tiered models, token savings, and multilingual reviewers.

Run Hugging Face models directly in JavaScript/TypeScript for text, vision, and speech tasks without backend servers, using Transformers.js in Node.js or modern browsers with WebGPU, quantization, and pipeline abstractions for efficient inference.

Helps teams treat prompts like production code by providing registry, eval, and governance workflows for versioning, testing, and promoting prompts safely across environments.

Describes how to use the MemOS local memory toolkit to recall past conversations, search shared histories, and choose the right memory tool when automatic recall is insufficient.

Programmatic access to Google NotebookLM via CLI/SDK: create notebooks, add diverse sources, chat about content, generate artifacts, download outputs, and embed into automated workflows.

Automate Datadog monitoring tasks via Rube MCP’s Composio toolkit—query metrics, search logs, manage monitors/dashboards, and create events or downtimes while respecting live tool schemas.