Data analysis, machine learning, LLM apps, and prompt design (9.1K skills)
Automate AI ML API tasks through Rube MCP, a connection for accessing external tools. The skill guides tool discovery, connection checks, and execution using current input requirements, with guidance for bulk operations and paginated results.
Automate Alpha Vantage operations through Rube MCP and Composio. Discover tools for a specific task, inspect their required inputs, verify an active connection, and execute the workflow using the current tool definitions.
Run Apify Actors, programs that collect web data, through the Composio integration. Retrieve structured results, create reusable tasks with preset inputs, and inspect execution logs for both quick collection jobs and longer runs.
Build text, image, and audio features in JavaScript using machine learning models that run in browsers or server runtimes. Covers model selection, execution settings, caching, and memory cleanup without requiring a Python server.
Add support for a new language model in MNN, from downloading and analyzing it to mapping model fields, comparing intermediate results, and exporting files. Follow staged tests, with additional paths for image, audio, and unusual architectures.
Turn documentation, GitHub repositories, PDFs, videos, and local code into AI skills with Skill Seekers. It identifies source types, guides collection and packaging, and supports updates and export to databases for similarity search.
Turn a rough idea or an existing prompt into a ready-to-paste instruction for a specific AI tool. The skill clarifies the task, output format, constraints, and success criteria for writing, image generation, or coding agents.
Read and display CARLA object bounding boxes, then project them onto a camera image as 2D rectangles. Export an annotated PNG and box coordinates in JSON for object detection annotation work.
Read existing CARLA sensors to view live camera or lidar output, save recordings, or inspect a single reading. Display multiple sensors together and check ROS 2 topic names, delivery settings, and whether publishing is enabled.
Use LangSmith to record LLM application inputs, outputs, and timing, investigate failures, evaluate answers against test datasets, and monitor production usage. It also guides automated quality checks and analysis of token usage and costs.
Guides adapting OpenPI robot models to custom datasets and serving them to produce actions from observations. Covers JAX and PyTorch training, checkpoint conversion, and troubleshooting for normalization statistics and GPU memory.
Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.
Reduce LLM generation delays with speculative decoding, which proposes tokens ahead of verification. This skill compares small draft models, Medusa, and Lookahead Decoding, with implementation examples, tuning guidance, and deployment using vLLM.
Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.
Guides building chatbots and tool-using agents with LangChain. Covers conversation history, model provider integration, and RAG, which retrieves relevant documents to inform answers, plus tracing to inspect application behavior.
Create masks that identify object regions in images using points, boxes, or existing masks. The skill guides automatic mask generation, transparent-background extraction, annotation workflows, and deployment, without requiring training for each specific task.
Train Mixture of Experts models, which activate selected specialist networks for each input. The skill guides architecture, input routing, workload balancing, and GPU distribution using DeepSpeed or HuggingFace, with examples for training configuration and inference optimization.
Track machine learning experiments with SwanLab by recording training settings, metrics, and media such as images and audio. Learn to compare runs, inspect training charts, and connect existing training code to local, cloud, or self-hosted dashboards.
Build AI workflows with DSPy by defining inputs and outputs and combining reusable components. Create question answering systems that use retrieved documents, tool-using agents, and automatically optimized prompts, then compare results with evaluation data.
Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Guides logging for PyTorch and TensorFlow, including weight distributions and performance profiling to investigate training problems and processing bottlenecks.
Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.
Guides image classification and search with OpenAI's CLIP by comparing images with text descriptions, without additional training. Includes batch processing, image-text matching, and category-based checks for potentially inappropriate images.
Guides building AI applications that search documents before answering questions, an approach called RAG. Covers importing files and web data, creating searchable indexes, adding conversational interfaces, and evaluating whether answers match the retrieved material.