skills.rest
DmitriyYukhanov
DmitriyYukhanovCOMMUNITY
Explore all skills by this author →
Website𝕏@dmitriy_focusGitHub

collaborative-loop

Orchestrate sequential drive-review cycles between Claude and Codex CLI for artifact development.

6|Updated Jan 27, 2026
Search Tags:#code review#collaboration#iterative development#codex cli#ai pair programming#sequential review
One-click install
npx skills add https://github.com/DmitriyYukhanov/claude-plugins --skill collaborative-loop
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: collaborative-loop
Source: https://github.com/DmitriyYukhanov/claude-plugins/tree/main/plugins/collaborative-loop/skills/collaborative-loop
Command: npx skills add https://github.com/DmitriyYukhanov/claude-plugins --skill collaborative-loop

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates complex, iterative AI-to-AI collaboration for code development, ensuring consistent quality and efficient progress through structured drive-review cycles.

Core Features & Use Cases

  • Sequential Drive-Review Cycles: Manages back-and-forth between a driver (Claude/Codex) and a reviewer (Claude/Codex) until consensus is reached.
  • Automated Stall Detection & Escalation: Identifies persistent issues and escalates to user for guidance.
  • Use Case: Use this skill when you need two AI models to work together to refine a piece of code, where one model writes and the other critiques, iterating until the code meets a high standard.

Quick Start

Initiate a collaborative loop for code development by running the collaborative-loop skill.

Frequently Asked Questions about collaborative-loop

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

FAQPage Schema
How do I automate AI pair programming for iterative code review?▼

Automate AI pair programming by orchestrating sequential drive-review cycles between Claude and Codex CLI, managing iterative feedback loops until code artifacts meet quality standards.

What is an AI-to-AI collaborative loop for code development?▼

An AI-to-AI collaborative loop is a structured process where a driver AI writes code and a reviewer AI critiques it, iterating sequentially until consensus is reached.

Do I need Codex CLI installed to run AI sequential code reviews?▼

Yes, you need Codex CLI installed and authenticated to perform Codex-driven operations, as the skill orchestrates sequential drive-review cycles between Claude and Codex CLI.

How does stall detection work during AI code generation cycles?▼

Stall detection identifies persistent issues during iterative development cycles and automatically escalates the problem to the user for guidance to resume progress.

Can I use this iterative development process for architecture and design artifacts?▼

Yes, the sequential drive-review cycles manage iterative feedback loops for code, plans, architecture, and design artifacts, ensuring consistent quality across various development outputs.

What are the limitations of using multiple AI models for code refinement?▼

A key limitation is the dependency on external tools; Codex-driven operations require proper CLI installation and authentication, and persistent stalls will halt automation for user-guided escalation.

Related Skills

Explore More Software Engineering Skills→
Quill-AgentQuill-Agent
3

codex

Automate coding tasks via OpenAI Codex CLI and git repositories.

Community
Advanced
phoenicisfphoenicisf

figma-implement-design

Translate Figma designs into production-ready UI code.

Community
Advanced
shogoggshogogg
4

coderabbit-review

Automate CodeRabbit code reviews for uncommitted and committed Git changes.

Community
Advanced
SivanwolSivanwol

laravel-iterating-on-code

Generate structured feedback to improve AI-generated PHP code.

Community
Advanced