gsd-plan-review-convergence

Iteratively review and refine AI-generated plans using a convergence loop.

Updated May 3, 2026

Search Tags:#plan refinement #iterative review #ai plan convergence #ai review tools #cross-ai collaboration

Ready to run

npx skills add https://github.com/ThiagoVitale/endless-crystal --skill gsd-plan-review-convergence-thiagovitale

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gsd-plan-review-convergence
Source: https://github.com/ThiagoVitale/endless-crystal/tree/main/.codex/skills/gsd-plan-review-convergence
Command: npx skills add https://github.com/ThiagoVitale/endless-crystal --skill gsd-plan-review-convergence-thiagovitale

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the issue of AI-generated plans containing high-level concerns, by facilitating an iterative process of review and replanning until no significant issues remain.

Core Features & Use Cases

Iterative Plan Review: Facilitates the review of AI-generated plans and allows for feedback-driven replanning.
Cross-AI Convergence: Uses multiple AI tools and local model servers to review and refine plans.
Use Case: Ideal for scenarios where multiple AI systems are generating plans, and there is a need for a high degree of convergence and refinement.

Quick Start

Invoke the skill with $gsd-plan-review-convergence and provide any necessary arguments, such as flags for specific reviewers or maximum cycle limits.

Frequently Asked Questions about gsd-plan-review-convergence

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

FAQPage Schema

How do I refine AI-generated plans to resolve high-level concerns?▼

Refine AI-generated plans by applying an iterative review and replanning convergence loop that continues until no significant issues remain. This feedback-driven process systematically eliminates high-level concerns through multiple rounds of revision.

What is AI plan convergence and how does it work?▼

AI plan convergence is an iterative review process that refines AI-generated plans using a convergence loop. It leverages external AI CLI tools and local model servers to review plans and apply feedback-driven replanning until plan quality is assured.

Can I use local model servers and external AI CLI tools for cross-AI plan review?▼

Yes, cross-AI convergence utilizes multiple external AI CLI tools and local model servers to review and refine plans. This multi-tool approach ensures a high degree of convergence and refinement across different AI systems generating plans.

How do I start an iterative plan review cycle?▼

Start an iterative plan review cycle by invoking the skill with specific arguments, such as flags for designated reviewers or maximum cycle limits. This initiates the feedback-driven replanning loop to process and refine the AI-generated plan.

When should I use an iterative replanning loop for plan quality assurance?▼

Use an iterative replanning loop for plan quality assurance when multiple AI systems are generating plans and a high degree of convergence is required. It is ideal for scenarios needing multiple rounds of review and revision to resolve high-level concerns.