vc-marbles

Orchestrates adaptive denoising loops to converge AI-generated code into a coherent product.

1|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/VetCoders/vibecrafted --skill vc-marbles
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vc-marbles
Source: https://github.com/VetCoders/vibecrafted/tree/main/skills/vc-marbles
Command: npx skills add https://github.com/VetCoders/vibecrafted --skill vc-marbles

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Iterative convergence of AI-generated code by running adaptive denoising loops that transform chaotic outputs into a coherent product, stopping only when entropy reaches zero.

Core Features & Use Cases

  • Iterative denoising loops: measure residual entropy, target gaps, implement fixes, and re-denoise to converge to a complete solution with bounded iteration scopes.
  • Convergence governance: supports supervisor/watchdog mode and specialized agent-based execution patterns (vc-delegate and vc-agents) with structured loop reports and convergence metrics.
  • Robust state and safety: frontmatter-driven iteration limits, optional completion promises, and per-session state tracking to ensure repeatable progress across runs.

Use cases include iterative refactoring, incremental feature implementation, and systematic bug fixes in AI-assisted software projects.

Quick Start

Start a Marbles loop in your codebase and let it iteratively refine the output until convergence is achieved.

Frequently Asked Questions about vc-marbles

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

FAQPage Schema
How do I iteratively refine AI-generated code to reduce errors?

To iteratively refine AI-generated code, adaptive denoising loops measure residual entropy, target gaps, implement fixes, and re-denoise until convergence is achieved with bounded iteration scopes.

What is code convergence through adaptive denoising loops?

Code convergence through adaptive denoising loops orchestrates incremental transformations of chaotic AI outputs into a coherent product, stopping only when entropy reaches zero and a complete solution is formed.

How do I track iteration progress for incremental refactoring across sessions?

Track iteration progress for incremental refactoring using frontmatter-driven iteration limits and per-session state tracking, ensuring repeatable progress and structured loop reporting across runs.

Can I use a supervisor mode for systematic bug fixes in AI-assisted projects?

Yes, you can use supervisor or watchdog mode for systematic bug fixes, supporting specialized agent-based execution patterns with structured loop reports and convergence metrics.

What's the best way to manage bounded iteration scopes during feature implementation?

The best way to manage bounded iteration scopes during feature implementation is utilizing frontmatter-driven state to enforce iteration limits and optional completion promises for controlled convergence.

Why does my AI code generation loop fail to converge?

AI code generation loops fail to converge when residual entropy remains high, requiring adaptive denoising to target gaps, implement fixes, and re-denoise until reaching a coherent product state.