Skill UI

A comprehensive tool and API wrapper for accessing, parsing, and analyzing research papers published on Hugging Face and arXiv. Users can input various URLs or IDs (e.g., arXiv ID) to retrieve structured metadata, full markdown content, and automatically link associated resources such as models, datasets, and application spaces. Ideal for researchers and developers needing structured access to cutting-edge AI knowledge.

Executes training, fine-tuning, inference, and batch jobs on Modal’s zero-config GPU cloud so you just write Python, run `modal run`, and let Modal auto scale, manage secrets, and halt billing when finishes.

This skill allows agents to persistently add external knowledge and conversational context to the OpenViking context database. It supports ingesting various resources (local files, URLs, repositories, directories) using 'add-resource', and storing rich, multi-turn conversation history as long-term memory using 'add-memory'. Use this when building a knowledge base, documenting projects, or ensuring conversation insights persist across sessions.

Generates concise TLDR-format summaries for GitHub Copilot customization files, MCP server docs, or related URLs, ensuring actionable examples and context-aware verbosity for inline or chat view sessions.

Modal delivers cloud-native serverless Python with on-demand GPUs, persistent storage, and web endpoints to deploy ML workloads, batch jobs, and APIs without writing Dockerfiles.

PufferLib is a high-performance library designed for advanced reinforcement learning simulations and training. It excels in parallel environment simulation, offering optimized vectorization and native support for multi-agent systems. Utilizing algorithms like PuffeRL (optimized PPO+LSTM), it achieves millions of steps per second, significantly accelerating research and deployment across single-agent and multi-agent environments.

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.

A comprehensive guide providing minimal, working examples for integrating with the Anthropic Claude Messages API. Covers core functionalities including basic text completion, advanced vision capabilities for image analysis, and real-time streaming responses. Ideal for developers starting a new Claude integration or testing core API patterns.

A comprehensive guide providing minimal working examples for core Cohere API v2 endpoints, including Chat completion, text embedding, and search reranking. This resource details basic setup, usage patterns, and includes runnable code examples in both TypeScript and Python, making it perfect for new AI integrations or learning advanced LLM functionality.

A robust utility for managing API calls to ElevenLabs, handling complex rate limiting, concurrency queuing, and quota monitoring. It implements plan-aware concurrency controls (managing 'too_many_concurrent_requests') and exponential backoff strategies for system overloads ('system_busy'). This is essential for building reliable, high-throughput Text-to-Speech applications.

Implement robust handling for AssemblyAI's asynchronous transcription completion events via webhooks. This guides users on how to set up secure endpoints that receive POST requests upon job completion or failure. It covers submitting transcripts with webhook URLs, verifying authentication headers, and processing the final transcript data, including running subsequent analyses like summarization.

This minimal working example demonstrates Abridge's ambient AI clinical documentation capabilities. It simulates a complete patient encounter session, allowing users to submit transcripts and receive a highly structured clinical note. Ideal for testing EHR connectivity, verifying AI workflow, or learning how structured medical data (SOAP notes, ICD/CPT codes) is automatically generated from free-text conversation.