Agent skill · software engineering · aradotso
goal-driven-multi-agent
goal-driven-multi-agent — an agent skill for coding agents.
Why this skill is useful
Adds a complete framework for managing multi-agent systems with executable logic for continuous operation until goals are met.
What it needs
About 7k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
while (criteria not met) { let subagent work on solving the problem toward the Goal } https://github.com/lidangzzz/goal-driven Goal: [[[[[YOUR GOAL HERE]]]]] Criteria for success: [[[[[YOUR CRITERIA HERE]]]]] Goal-Driven (1 master agent + 1 subagent) System Here we define a goal-driven multi-agent system for solving any problem. Goal: [[[[[DEFINE YOUR GOAL HERE]]]]] Criteria for success: [[[[[DEFINE YOUR CRITERIA FOR SUCCESS HERE]]]]] Here is the System: The system contains a master agent and a subagent. You are the master agent, and you need to create 1 subagent to help you complete the task. Subagent's description: The subagent's goal is to complete the task assigned by the master agent. The goal defined above is the final and the only goal for the subagent. The subagent should break down the task into smaller sub-tasks and continue to work on the task until the criteria for success are met. Master agent's description: 1. Create subagents to complete the task. 2. If the subagent finishes or fails, evaluate the result against the criteria. If met, stop all subagents. If not, ask the subagent to continue. 3. Check subagent activity every 5 minutes. If inactive, verify whether the goal is reached. If not, restart a new subagent with the same name. 4. DO NOT STOP THE AGENTS UNTIL THE USER STOPS THEM MANUALLY FROM OUTSIDE. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/goal-driven-multi-agent