skills.rest
I-Onlabs
I-OnlabsCOMMUNITY
Explore all skills by this author →
GitHub

dwa-council

Orchestrate Debate-Weighted Aggregation for multi-agent decisions with weighted voting and audit trails.

3|1|Updated Dec 21, 2025
Search Tags:#architecture#audit#multi-agent#voting#decision-making#risk#deliberation
One-click install
npx skills add https://github.com/I-Onlabs/claude-code-skills --skill dwa-council
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dwa-council
Source: https://github.com/I-Onlabs/claude-code-skills/tree/main/dwa-council
Command: npx skills add https://github.com/I-Onlabs/claude-code-skills --skill dwa-council

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates Debate-Weighted Aggregation to resolve high-stakes, multi-agent decisions across architecture, security, and risk domains, reducing bias and accelerating consensus.

Core Features & Use Cases

  • Trigger-driven convening for eight decision contexts (architectural decisions, security risks, agent disagreements, quality gate failures, ethical flags, low confidence, external commitments, novel queries)
  • DWA voting formula that combines vote, confidence, and expertise weights to produce a transparent score
  • Structured workflow: trigger detection, agent selection, proposal generation, optional debate rounds, escalation, and auditable finalization
  • Escalation path to external models or human experts when needed, with complete audit trails

Quick Start

Convoke a council session automatically whenever triggers are detected to produce a decision.

Frequently Asked Questions about dwa-council

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

FAQPage Schema
How does multi-agent voting work for architectural decisions?▼

Multi-agent voting for architectural decisions uses a weighted formula combining agent votes, confidence, and expertise weights to produce a transparent score, optionally structured by debate rounds to reduce bias and accelerate consensus.

How do I orchestrate deliberation for multi-agent security risks?▼

Orchestrate deliberation for security risks by automatically convening a council session when triggers are detected, selecting agents, generating proposals, conducting weighted voting, and maintaining an auditable decision trail with optional escalation.

When should I use debate-weighted aggregation for risk-related decisions?▼

Use debate-weighted aggregation for high-stakes risk decisions when multiple informed proposals require deliberation, bias reduction is critical, or agent disagreements, quality gate failures, and ethical flags necessitate structured consensus.

Can multi-agent decision-making escalate to human experts?▼

Yes, multi-agent decision-making includes an escalation path to external models or human experts when agents cannot reach consensus or confidence thresholds are unmet, ensuring all escalations are recorded in the audit trail.

What triggers a council session for automated decision-making?▼

Council sessions trigger automatically across eight contexts including architectural decisions, security risks, agent disagreements, quality gate failures, ethical flags, low confidence, external commitments, and novel queries.

Related Skills

Explore More Software Engineering Skills→
markus41markus41
18

council-review

Orchestrate multi-agent council reviews with configurable roles, weighted voting, and consensus detection.

Community
Advanced
GanyuanRanGanyuanRan
968

first-principles-review

Identify irreducible outcomes and non-negotiable constraints for high-risk decisions.

Community
Advanced
rysweetrysweet
1

consensus-voting

Execute weighted multi-agent voting with configurable consensus thresholds.

Community
Advanced
marcusgollmarcusgoll
91

multi-agent-voting

Execute multi-agent voting with MAKER-style error correction for critical decisions.

Community
Advanced