multi-round-deliberation

Coordinate iterative multi-agent discussions to converge on a resolved artifact.

11|1|Updated Feb 22, 2026
One-click install
npx skills add https://github.com/EvoClaw/amplify --skill multi-round-deliberation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: multi-round-deliberation
Source: https://github.com/EvoClaw/amplify/tree/main/skills/multi-round-deliberation
Command: npx skills add https://github.com/EvoClaw/amplify --skill multi-round-deliberation

SYSTEM DOCUMENTATION & REQUIREMENTS

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.

Frequently Asked Questions about multi-round-deliberation

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

FAQPage Schema
How do I coordinate multi-agent discussions to reach consensus on a design review?

Multi-agent discussions reach consensus by applying an iterative Assess, Check Convergence, Modify, and Re-assess workflow. Agents critique and revise artifacts until all participants pass the convergence criteria or hit a maximum round cap.

What is the best way to prevent superficial feedback in iterative writing cycles?

Iterative writing cycles prevent superficial feedback by injecting a shared value framework into agent prompts and running full re-assessments after modifications. This ensures agents resolve issues rather than merely noting them before convergence checks.

How does multi-round deliberation handle complex decision-making workflows?

Complex decision-making workflows handle iterative refinement through round-based assessment and modification steps. Agents evaluate the artifact, apply changes, and re-assess the full output until consensus is achieved or the maximum round limit is reached.

Can I use iteration and convergence checks for automated story design and paper writing?

Iteration and convergence checks apply directly to story design and paper writing workflows. The protocol integrates with these phases to guarantee quality by enforcing round-based assessments and modifications until all agent concerns are fully resolved.

What happens if agents do not reach consensus during a review workflow?

If agents do not reach consensus during a review workflow, the iteration stops automatically when the maximum round cap is reached. This stop condition prevents infinite loops while ensuring multiple rounds of critique and modification are attempted.

Why does the full artifact need re-assessment after modifications in a multi-agent workflow?

Full artifact re-assessment after modifications prevents regression in multi-agent workflows. By re-evaluating the entire output rather than just the changed sections, the system ensures that new modifications do not introduce unresolved issues into the converged result.