meta-loop-methodology

Document a meta-loop methodology for AI-assisted software development workflows.

3|Updated Feb 5, 2026

Search Tags:#documentation #specification #ai-agent #wireframe #transferability #single-shot #meta-loop

Ready to run

npx skills add https://github.com/jpavley/meta-loop-ios --skill meta-loop-methodology

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: meta-loop-methodology
Source: https://github.com/jpavley/meta-loop-ios/tree/main/skills/meta-loop-methodology
Command: npx skills add https://github.com/jpavley/meta-loop-ios --skill meta-loop-methodology

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Meta-Loop methodology provides a repeatable, AI-assisted software development workflow that emphasizes external documentation as the durable artifact, enabling single-shot delivery and transferability across platforms.

Core Features & Use Cases

Three-loop model combining Wireframe → Spec → Implementation with Plan, Ask, and Agent modes to guide AI actions.
Delete and Regenerate discipline that discards faulty artifacts and rebuilds from clarified source docs.
Documentation-centric learning that persists across sessions and platforms, including wireframes, specs, and AGENTS.md.
Use cases include teams seeking reproducible AI-assisted development and cross-platform prototyping.

Quick Start

Draw a simple wireframe, verify understanding with /ml-wireframe, generate the spec with /ml-spec, implement with /ml-impl, and capture learnings with /ml-retain.

Frequently Asked Questions about meta-loop-methodology

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

FAQPage Schema

What is the meta-loop methodology for AI-assisted software development?▼

The meta-loop methodology is a repeatable AI-assisted workflow that uses external documentation artifacts like wireframes and specifications to achieve single-shot software delivery. It combines a Wireframe, Spec, and Implementation loop with Plan, Ask, and Agent modes to guide AI actions.

How do I use wireframes and specifications to generate code with an AI agent?▼

To generate code with an AI agent, you draw a wireframe, verify understanding, generate a specification, and then implement it. You capture learnings in documentation files to ensure the process is repeatable across sessions.

Can I use this AI-assisted development workflow across different platforms and projects?▼

Yes, this methodology is designed for cross-platform prototyping and transferability. It emphasizes external documentation as the durable artifact, ensuring persistent learning and reproducible development across different platforms and projects.

Why discard and regenerate faulty artifacts during AI-assisted development?▼

Discarding and regenerating faulty artifacts enforces a discipline that rebuilds code from clarified source documents. This approach prevents carrying over errors and maintains the integrity of the single-shot delivery workflow.

How does documentation-centric learning preserve context across AI sessions?▼

Documentation-centric learning preserves context by relying on external artifacts like wireframes, specs, and AGENTS.md files. These documents act as the durable memory for the AI, capturing learnings that persist across sessions and platforms.

What are the Plan, Ask, and Agent modes in AI-assisted software loops?▼

Plan, Ask, and Agent modes are operational states that guide AI actions within the development loop. They structure how the AI interacts with the Wireframe, Spec, and Implementation phases to ensure controlled and repeatable software generation.