Skill UI

Coordinates a pre-task intelligence protocol that activates all relevant agents, synthesizes parallel analyses, estimates real execution time, maps probable risks, and produces a contingency-aware plan before executing the user’s request.

Evaluates incoming requests, decides if specialized skills are needed, orchestrates optimal combinations, and logs successful pairings in agent-memory while guarding against overusing complex tools on simple tasks.

Coordinate multiple AI agents concurrently via dmux’s tmux pane manager, running Claude Code, Codex, OpenCode and other tools in parallel tracks for research, implementation, testing, review, or multi-role coding tasks.

Detect malicious scheduled task creation and modification using Sysmon (Event IDs 1/11), Windows Security events (4698/4702), and correlation of suspicious parents, public paths, and encoded arguments for persistence and lateral movement analysis.

Provides an interactive menu to browse agent catalogs, pick up to five specialists or mixed-domain agents, and launch them in parallel with a unified task prompt so you can gather consolidated findings and recommendations.

Adds x402 payment execution stack to AI agents, giving per-task/session budgets, allowed recipients, rate controls, and non-custodial wallets via MCP tools so agents can autonomously pay for APIs, services, or other agents with no custodial risk.

This skill is designed for performing local, on-premise evaluations and benchmarking of models hosted on the Hugging Face Hub. It facilitates running specialized evaluation frameworks like `inspect-ai` and `lighteval` against local hardware. Users can select optimal inference backends, including `vllm` for high throughput, or fall back to Hugging Face Transformers or `accelerate`, ensuring comprehensive smoke testing and task selection for LLMs. It focuses purely on the local execution process, separate from remote jobs or publishing workflows.

Run Hugging Face models directly in JavaScript/TypeScript for text, vision, and speech tasks without backend servers, using Transformers.js in Node.js or modern browsers with WebGPU, quantization, and pipeline abstractions for efficient inference.

This skill automates the process of renting, configuring, and managing GPU instances on vast.ai for deep learning and AI tasks. It analyzes the task requirements (VRAM, GPU count, estimated time) from the experiment plan or user input, searches for the most cost-effective and reliable GPU offers, and manages the entire resource lifecycle, ensuring efficient and economic AI training.

A cross-protocol platform for discovering and searching 18,000+ MCP servers and AI agents across six or more registries. It allows users to find the necessary endpoint for specific tasks (like database access or file conversion) by searching across MCP, A2A, and agents.txt protocols simultaneously.

A robust, production-tested pattern for coordinating multiple specialized AI agents. The orchestrator decomposes complex tasks, routes them to the most suitable specialist, prevents redundant or conflicting work (anti-duplication), and enforces mandatory quality gates (e.g., running tests, checking file diffs) to verify results before marking a task as complete. It also includes heartbeat monitoring for task progress.

Discover, download, and manage reusable AI agent skills from the AionUI Skills registry, making it easy to augment autonomous assistants with community-built capabilities whenever a task benefits from specialized functionality.