Skills
.Work. You
Rest

multi-round-deliberation

Official

Coordinate multi-agent discussions to convergence.

Education & Research#multi-agent#iteration#convergence#deliberation#review-workflow
AuthorEvoClaw
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Real deliberations often end with superficial feedback and unresolved issues. This protocol ensures iterative refinement until all concerns are resolved or converged. It is a reusable framework used by results-integration (Phase 5) and paper-writing (Phase 6) to guarantee discussions actually resolve issues rather than merely noting them.

Core Features & Use Cases

  • Shared Value Framework injected into prompts to align agent objectives.
  • Iterative rounds with Assess → Check Convergence → Modify → Re-assess.
  • Convergence criteria: all agents PASS or max rounds reached; supports phase-specific rules.
  • Integration with Phase 5 (story design) and Phase 6 (writing) to guarantee quality.
  • Automatic re-assessment of the full artifact after modifications to prevent regression.

Quick Start

Initiate a round-based deliberation with three agents evaluating the current artifact and iterate until all issues are resolved or convergence is reached.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: multi-round-deliberation
Download link: https://github.com/EvoClaw/amplify/archive/main.zip#multi-round-deliberation

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.