skills.rest
sunmin-oss
sunmin-ossCOMMUNITY
Explore all skills by this author →
GitHub

agent-council

Orchestrate multi-agent workflows with diverse model families for collaborative brainstorming or adversarial stress-testing.

1|Updated Oct 12, 2025
Search Tags:#architecture#brainstorming#collaboration#multi-agent#debate#stress-test
One-click install
npx skills add https://github.com/sunmin-oss/sunmin-oss --skill agent-council-sunmin-oss
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-council
Source: https://github.com/sunmin-oss/sunmin-oss/tree/main/.copilot/skills/agent-council
Command: npx skills add https://github.com/sunmin-oss/sunmin-oss --skill agent-council-sunmin-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the problem of cognitive bias and limited perspective in complex decision-making by orchestrating multiple AI models to collaborate or debate.

Core Features & Use Cases

  • Collaborative Mode: Leverages three distinct model families to brainstorm, build, and synthesize novel solutions for complex architectural or creative tasks.
  • Adversarial Mode: Stress-tests ideas through a rigorous debate and red-teaming process to identify flaws, edge cases, and security vulnerabilities.
  • Use Case: Use this when you need to perform a high-stakes security review of a codebase or brainstorm a system architecture where missing a single edge case could be costly.

Quick Start

Invoke the agent-council skill to debate the security implications of the current system architecture.

Frequently Asked Questions about agent-council

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is multi-agent brainstorming and how does it improve architectural reviews?▼

Multi-agent brainstorming leverages diverse model families to collaborate or debate, mitigating cognitive bias in architectural reviews by synthesizing distinct cognitive perspectives into a validated output.

How do I stress-test system architecture for security vulnerabilities and edge cases?▼

Stress-test system architecture by invoking an adversarial multi-agent workflow that applies red-teaming and rigorous debate to identify security vulnerabilities, flaws, and edge cases.

Can I use multiple AI models to debate the security implications of a codebase?▼

Yes, you can debate the security implications of a codebase by running parallel subagents with distinct cognitive roles that execute an adversarial debate and stress-testing workflow.

When should I use collaborative vs adversarial mode for complex problem-solving?▼

Use collaborative mode to brainstorm and synthesize novel solutions for complex problem-solving, and use adversarial mode to stress-test ideas through rigorous debate to identify flaws.

What are the limitations of using multi-agent workflows for high-stakes decision-making?▼

Multi-agent workflows for high-stakes decision-making require parallel execution of subagents with distinct cognitive roles, meaning complex problem-solving scenarios demand significant orchestration overhead to synthesize a final validated output.

Related Skills

Explore More Software Engineering Skills→
NVIDIANVIDIA
2.8k

lp-milp-formulation

Translate natural-language problem statements into explicit LP/MILP formulations.

Official
Intermediate
dividedbydividedby
1

council

Orchestrate a multi-persona panel to synthesize adversarial second opinions on decisions.

Community
Advanced
diegosanchespereira1diegosanchespereira1

bmad-party-mode

Orchestrate multi-agent roundtable discussions across installed BMAD agents.

Community
Advanced
Imad-OuteImad-Oute
2

mh-mgi-adversarial-designer

Stress-test plans and system designs with three adversarial agents.

Community
Advanced