Browse skills

OCR Super Surya extracts text from images and PDFs quickly & accurately, boosting data processing efficiency for various tasks.

Leverages PyTorch for deep learning model development and experimentation, accelerating AI research and custom solution creation.

Generates detailed, photorealistic images from text prompts using advanced diffusion techniques.

Zai TTS converts text into natural-sounding speech, offering a quick and easy way to add voiceovers or audio content to your projects.

Reduces LLM file sizes & speeds up inference by quantizing GGuf models – making them more efficient to run and deploy.

Optimizes attention flash mechanisms for models like GPT to reduce memory usage and accelerate inference speed, boosting efficiency.

This skill efficiently trains sparse autoencoders for dimensionality reduction and feature learning by optimizing for sparsity, saving time & resources.

Grpo RL Training facilitates rapid reinforcement learning model development by automating and optimizing agent training processes for improved performance.

Nnsight Remote Interpretability analyzes model behavior in real-time across deployed environments, revealing insights for debugging and trust.

Llava allows you to generate detailed images from natural language prompts, offering a powerful way to visualize your ideas and concepts.

Llamaguard analyzes user prompts to refine and improve AI responses, ensuring more accurate and helpful outputs for complex queries.

Cocoindex enables semantic search across your documents by indexing content for faster, more relevant retrieval – boosting productivity and knowledge discovery.

GPTQ enables faster, smaller language model inference by quantizing weights – crucial for deploying large models on limited hardware.

Sentencepiece efficiently tokenizes text into subword units, improving NLP model performance and handling rare words effectively.

Awq Quantization optimizes model size & speed by intelligently reducing numerical precision, boosting performance for deployment.

This skill implements the RWKV language model architecture, offering a unique recurrent approach for efficient and potentially high-quality text generation.

Simpo Training simulates realistic customer interactions for agent practice, boosting confidence and improving real-world performance.

Hqq Quantization optimizes model size & speed by reducing numerical precision, making AI faster and more efficient for deployment.

Stores and retrieves vector embeddings in a Qdrant database, enabling semantic search and similarity analysis.

Agentica Claude Proxy allows you to seamlessly integrate Claude's powerful language model into your existing agents for enhanced reasoning and creative capabilities.

Wiring allows you to create complex circuits and logic gates within your game, enabling intricate interactions and gameplay mechanics.

Seamlessly transfers OpenAI applications and data between environments using a standardized model context protocol.

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 min