skills.rest
wendeus0
wendeus0COMMUNITY
Explore all skills by this author →
GitHub

council

Orchestrate multi-agent debates to produce auditable verdicts for architectural decisions.

Updated Aug 23, 2026
Search Tags:#architecture#transcript#adr#decision#multi-agent#council#debate
One-click install
npx skills add https://github.com/wendeus0/AI-dotfiles --skill council-wendeus0
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: council
Source: https://github.com/wendeus0/AI-dotfiles/tree/main/core/skills/council
Command: npx skills add https://github.com/wendeus0/AI-dotfiles --skill council-wendeus0

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill orchestrates structured, auditable debates among multiple agents to arrive at robust architectural decisions, preserving a transcript of arguments and a clear verdict.

Core Features & Use Cases

  • Multi-agent cooperative/adversarial debate with defined roles (Protagonist, Antagonists, Chairman, Assistant-Chairman).
  • Transcript preservation and attachable evidence for each decision path.
  • Automated role resolution based on decision context and optional contextual roles.
  • Deterministic execution flow from context loading to final verdict, with documented changes and open issues.
  • ADR-oriented decision support and integration hooks for downstream tooling.

Quick Start

Start a council debate by providing a clear decision or question; the system will load context, assign roles, and generate a full transcript and verdict.

Frequently Asked Questions about council

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

FAQPage Schema
How do I facilitate a multi-agent debate to evaluate architectural trade-offs?▼

Multi-agent debate for architectural trade-offs is facilitated by assigning roles like Protagonist, Antagonist, and Chairman to analyze a decision text and generate an evidence-based verdict.

What is the best way to automate ADR generation with traceable decision transcripts?▼

Automating ADR generation with traceable transcripts involves running a deterministic execution flow that captures arguments, resolves roles, and outputs a final chairman verdict for reproducibility.

Can I use multi-agent debate for design decisions requiring evidence-based conclusions?▼

Yes, multi-agent debate supports design decisions requiring evidence-based conclusions by orchestrating adversarial arguments and attaching evidence to each decision path within the transcript.

Does the architectural decision debate workflow preserve transcripts for auditing?▼

The architectural decision debate workflow preserves full transcripts of arguments and documents open issues, ensuring the final verdict is auditable and traceable for downstream tooling.

How to assign roles automatically in a multi-agent architecture decision debate?▼

Roles are assigned automatically through role resolution based on the decision context provided, with optional contextual roles available to tailor the debate participants to the specific scenario.

When should I not use a multi-agent council debate for decision making?▼

A multi-agent council debate is not suited for simple, unilateral decisions lacking trade-offs, as it imposes a structured adversarial flow designed for complex architectural analysis and evidence evaluation.

Related Skills

Explore More Software Engineering Skills→
abdullah1854abdullah1854
1

pdf

Generate Markdown Architecture Decision Records from input fields.

Community
Advanced
easingthemeseasingthemes
6

dx-council

Route high-stakes questions through three advisors for peer-reviewed verdicts.

Community
Advanced
Mattyreed1Mattyreed1

judge

Score multi-agent debate transcripts on five criteria and output a winner.

Community
Advanced
sliorslior
3

role-agent

Execute one debate phase for a role-specific subagent in a multi-agent design debate.

Community
Basic