Interact with a web browser. Can start a browser, connect to it, evaluate JavaScript, make screenshots, read console logs and let the user select DOM elements. Use when interacting with unknown...
Process and analyze massive documents (PDF, Word, HTML, JSON, Markdown) that exceed context limits. Use when a document is too large to fit in context, when you need to search large files, find...
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or...
Conducts comprehensive frontend code reviews including React/Vue/Angular component analysis, TypeScript/JavaScript quality assessment, CSS/styling review, performance optimization, accessibility...
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search,...
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with...
Analyzes software bugs including root cause identification, severity assessment, impact analysis, reproduction steps validation, and fix recommendations. Performs bug triage, categorization,...
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform...
Best practices and workflows for the Spotify Web API. Use when building apps that interact with Spotify to: (1) Handle rate limits and 429 errors, (2) Implement efficient polling strategies, (3)...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities....
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than...
Guides infrastructure and platform migration including cloud-to-cloud migration (AWS to GCP, Azure to AWS), Kubernetes cluster migration, CI/CD platform changes, monitoring stack migration,...
Expert backend development guidance covering Node.js, Python, Java, Go, API design (REST/GraphQL/gRPC), database patterns, authentication, caching, message queues, microservices, and testing....
Analyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies...
Expert frontend development guidance covering React, Vue, Angular, TypeScript, state management, component architecture, performance optimization, accessibility, testing, and modern web APIs....
Guides systematic code refactoring to improve code quality, maintainability, and design. Identifies code smells, applies refactoring patterns, ensures test coverage, and follows safe refactoring...
Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes',...
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with...
SSH remote access patterns and utilities. Connect to servers, manage keys, tunnels, and transfers.
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring...