Skill UI

This technique is designed to identify South Asian (Indian/Bollywood) films when the question provides insufficient information to name the movie directly. Instead, it requires chaining together the biographical details of the actor or director—such as birth year, debut era, family relations, or awards—to first uniquely identify the person, and then use that identity to locate the target film and verify all constraints.

Evolver is a comprehensive self-evolution engine designed for autonomous AI agents. It analyzes complex runtime history, identifies performance bottlenecks, and autonomously generates and applies improvements. Communication is architecturally confined to a local Proxy Mailbox, ensuring secure and reliable interaction with the EvoMap Hub for asset management and task acquisition. Ideal for developing highly adaptive, continuously improving intelligent systems.

A Python library for molecular machine learning, offering diverse featurizers, MoleculeNet benchmarks, graph neural networks, and pretrained models for property and ADMET prediction.

This skill extracts cognitive patterns and thinking fingerprints from any text using the Digital Human DNA (DHDNA) framework. It analyzes 12 cognitive dimensions like analytical depth, creativity, and emotional processing to create a unique cognitive profile. Use it to understand an author's reasoning style, compare thinking patterns, or gain deeper insight into decision-making processes behind written or spoken content.

Generate and edit images using OpenRouter's AI models like Gemini and Seedream. Supports photos, illustrations, logos, and concept art via command line. Requires API key for generation tasks.

Plans, audits, and safely runs ChicagoHAI HypoGeniC/HypoRefine workflows for LLM-assisted hypothesis generation from labeled text datasets, with pinned installs, config validation, dataset leakage checks, and bounded local review before any model call.

Unified Python library with 100+ molecular featurizers and pretrained embeddings. Converts SMILES or RDKit molecules into ML-ready numerical features for QSAR modeling, virtual screening, similarity search, and deep learning.

End-to-end analysis toolkit for Neuropixels extracellular recordings using SpikeInterface. Supports loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift correction, spike sorting with Kilosort4 and other algorithms, quality metrics computation, and AI-assisted unit curation for publication-ready neural data analysis.

Self-hosted open-source alternative to Google NotebookLM. Organize research sources, generate AI notes and summaries, create multi-speaker podcasts, chat with documents, and search materials via full-text or vector search with 16+ AI providers.

Hardware-agnostic quantum machine learning framework with automatic differentiation for training quantum circuits, building hybrid quantum-classical models, and deploying across IBM, Google, Rigetti, IonQ, and simulators.

Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Adapt Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or work with redesigned native 4.0 source line with Python 3.10+ and Torch 2.9+. Includes safe defaults for CPU-only, network-free tools with strict JSON output and dependency-free bundled CLIs.

Build clinical and healthcare deep learning pipelines with PyHealth: load EHR, signal, and imaging datasets, define prediction tasks, instantiate models, train, and evaluate using a modular five-stage workflow.