Skill UI

Designs and orchestrates role-based multi-agent workflows with CrewAI, defining agent personas, tasks, processes, and memory to run complex structured collaborations and planning pipelines.

CrewAI orchestrates autonomous multi-agent teams for role-based collaboration, sequential or hierarchical workflows, and production-grade orchestration with memory and tool integrations without LangChain.

This skill is designed to manage complex, multi-step tasks by coordinating the efforts of multiple specialized AI agents. It provides structured methods for listing available agents, initiating real-time conversations, submitting complex background tasks (such as data analysis or report generation), tracking task status, and maintaining conversational context using session IDs. It is essential when a core task requires diverse expert knowledge or sequential collaboration.

A robust protocol designed for multi-agent collaboration on long-running projects. It simulates a self-optimizing city where diverse AI agents (citizens) interact using decentralized markdown files (The Register, Contracts, Chronicle). This framework enables cross-vendor optimization, dynamic work routing, and constitutional evolution without requiring a centralized server or specific runtime environment.

This skill provides comprehensive guidance for authors targeting the AAAI Conference on Human Computation and Crowdsourcing (HCOMP). It helps authors strategically frame, position, and strengthen the evidence of manuscripts focused on crowdsourcing, human-AI collaboration, and collective intelligence, ensuring the work meets the specific academic bar of the venue.

Initialize an AgentHub collaboration session by defining task, agent count, and evaluation criteria. Supports interactive mode or command-line arguments for metrics like response time. Creates session directory structure and generates a unique session ID. Captures baseline measurements if evaluation commands are provided. Prepares the environment for spawning multiple AI agents to execute the defined task.

Build background agents in sandboxed environments for hosted coding agents and remote coding environments. This skill covers infrastructure design for quota-bounded concurrency, consistent execution, and multiplayer collaboration. It includes strategies like image registry patterns, snapshot restoration, predictive warm-up, and self-spawning agents to scale beyond local machine constraints.

A protocol enabling AI agents from different vendors to collaborate on long-running projects, route work to best-suited agents, and improve over time. Uses markdown files with no central server, featuring capability cards, contracts, chronicles, and self-amendment mechanisms for cross-vendor optimization and constitutional evolution.

Build and orchestrate teams of autonomous AI agents with role-based collaboration, shared memory, tools, and sequential or hierarchical workflows for production multi-agent systems.