Multi-Agent on Vibe Coding

Google Antigravity

Mon, 01 Jan 0001 00:00:00 +0000

Antigravity reframes the IDE around managing agents rather than writing code directly: a standalone desktop app lets you run several Gemini-powered coding agents in parallel, schedule automated tasks, and give agents built-in browser automation to test and verify their own work.

Loki Mode

Mon, 01 Jan 0001 00:00:00 +0000

Loki Mode orchestrates dozens of coordinated AI agents to build, deploy, and operate a complete startup end-to-end, from a PRD through to a live, revenue-generating product.

Why a skill for this

Coordinating many agents toward one large goal needs explicit role division and hand-off structure, or the agents duplicate work or conflict. This skill packages that orchestration pattern rather than leaving it to be improvised per project.

Mercury MCP Cheatsheet

Mon, 01 Jan 0001 00:00:00 +0000

This reference skill covers the Mercury (Proton) MCP tools for messaging agent teammates, managing threads, and scheduling automations across a coordinated team of agents.

Why a skill for this

Multi-agent coordination tools tend to have enough surface area — threading, scheduling, teammate addressing — that a quick reference beats re-deriving the API each time. This skill keeps that reference on hand.

MetaGPT

Mon, 01 Jan 0001 00:00:00 +0000

MetaGPT assigns different LLM agents distinct roles — product manager, architect, project manager, engineer — and has them collaborate through standard software-team artifacts like PRDs and design docs on the way to generating a working codebase from a single requirement.