decision-council

Spawns three adversarial subagents to analyze a decision and synthesize their findings for blind spots.

Updated May 16, 2026
One-click install
npx skills add https://github.com/aryaxt/aryaxt-skills --skill decision-council-aryaxt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: decision-council
Source: https://github.com/aryaxt/aryaxt-skills/tree/main/skills/decision-council
Command: npx skills add https://github.com/aryaxt/aryaxt-skills --skill decision-council-aryaxt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill assists in making non-trivial design or scope decisions by providing structured feedback from three adversarial subagents, reducing bias and promoting a comprehensive evaluation.

Core Features & Use Cases

  • Adversarial Subagents: Spawns three subagents with differing value functions to challenge assumptions.
  • Synthesis Pass: A final agent synthesizes the opinions of the first three, identifying blind spots.
  • Guardrails: Enforces rules to ensure the process is unbiased and effective.
  • Use Case: When faced with a decision like whether to include a feature in a PR, this Skill can provide a structured recommendation after considering various perspectives.

Quick Start

Invoke the decision-council skill with your decision question and relevant context.

Frequently Asked Questions about decision-council

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

FAQPage Schema
How do I reduce bias in complex design decisions?

Reduce bias in complex design decisions by using a structured process that spawns three adversarial subagents with differing value functions to challenge assumptions, followed by a synthesis pass to identify blind spots.

What is the best way to get structured feedback on scope decisions?

Get structured feedback on scope decisions by invoking an adversarial subagent process that provides three independent perspectives and a final synthesis pass to evaluate whether a feature should be included.

Can I use adversarial subagents for deciding whether to include a feature in a pull request?

Yes, you can use adversarial subagents for deciding whether to include a feature in a pull request by providing your decision question and relevant context to generate a structured recommendation.

How does the synthesis pass work in structured decision-making?

The synthesis pass works by having a final agent review the opinions of three adversarial subagents to identify blind spots and produce a comprehensive evaluation of a non-trivial design or scope decision.

When should I not use an adversarial subagent approach for decision-making?

You should not use an adversarial subagent approach for trivial decisions, as it requires careful framing and clear context to be effective for complex design or scope decisions where multiple perspectives are needed.