Skill UI

An advanced AI-driven framework for holistic performance engineering of multi-agent systems. It provides coordinated profiling, workload distribution, and cost-aware orchestration across various domains (database, application, frontend). Use this tool to identify bottlenecks, improve throughput, enhance reliability, and manage resource constraints in complex agent workflows.

This comprehensive skill implements advanced event-driven patterns for LangChain applications. It provides custom callback handlers to observe every stage of chain execution (e.g., tool start/end, LLM token generation). Furthermore, it supports real-time data transmission via Server-Sent Events (SSE) and WebSockets, and integrates webhooks for centralized event logging and comprehensive tracing.

ZAI CLI provides comprehensive access to Z.AI's advanced capabilities, including image/video analysis, real-time web search, web page extraction, and GitHub code exploration. It is designed for users needing multi-modal content analysis, error diagnosis, and complex data processing through a unified command-line interface. Ideal for developers and analysts requiring robust, API-driven AI functionality.

Hypogenic automates LLM-driven hypothesis generation and testing over tabular datasets, blending literature insights with empirical analysis to accelerate discovery in domains like deception detection or AI content evaluation.

This skill utilizes AI/LLM reasoning capabilities combined with industry-standard OSINT tools (Sherlock, theHarvester, SpiderFoot). It correlates fragmented data—including usernames, emails, domain records, and breach data—from multiple sources into unified, confidence-scored intelligence profiles. It is ideal for deep target profiling, identity resolution, and mapping complex threat landscapes.

This skill provides a comprehensive framework for optimizing, improving, and debugging Large Language Model (LLM) prompts. It leverages production trace data, system evaluations, and human annotations to extract prompts from spans. Users can run a data-driven optimization loop, ensuring the AI responses meet desired quality standards. Ideal for prompt tuning, system prompt refinement, and improving overall AI output quality.

This guide teaches developers how to implement robust, event-driven architecture patterns with the Anthropic Claude API. It covers two key methods: Server-Sent Events (SSE) for real-time streaming responses, and the Message Batches API for high-volume, asynchronous bulk processing. Use this when building real-time chat features or processing large datasets offline.

A universal infrastructure for automatically evolving and optimizing AI agents across any domain. Using LLM-driven mutation and iterative solve-observe-evolve cycles, it enhances critical components like prompts, skills, and memory by benchmarking performance against measurable datasets, enabling the creation of self-improving AI systems.

This comprehensive skill manages the entire computer vision pipeline, from custom dataset annotation to model deployment. Users can fine-tune YOLO models on proprietary COCO-formatted datasets using an agent-driven workflow. Key features include hardware-aware training (supporting CUDA, MPS, ROCm), automatic export to optimized formats (TensorRT, CoreML, OpenVINO, ONNX), and seamless, one-click deployment as an active detection skill.

A comprehensive framework for producing high-authority, multi-layered AI industry content. This skill teaches how to structure content across three pillars: real-time quick news reports (Speed), data-driven deep dives (Depth), and annual trend reports/panorama maps (Authority). Ideal for content creators, journalists, and industry analysts needing to establish thought leadership in the rapidly evolving AI sector.

This AI-driven system integrates multi-dimensional health data including lifestyle, medical history, and mental health to identify anomalies and predict risks. It provides personalized health recommendations based on evidence-based guidelines and generates comprehensive interactive reports. Supports intelligent Q&A for health metrics and trends, ensuring data privacy with local processing. Ideal for users seeking data-driven health insights without replacing professional medical advice.