ccg

Route user requests through Codex and Gemini prompts and synthesize outputs.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/ClementATH/oh-my-claudecode --skill ccg-clementath
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ccg
Source: https://github.com/ClementATH/oh-my-claudecode/tree/main/skills/ccg
Command: npx skills add https://github.com/ClementATH/oh-my-claudecode --skill ccg-clementath

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Claude orchestrates multi-model prompts by routing user requests through Codex and Gemini and synthesizes the outputs into a single coherent answer.

Core Features & Use Cases

  • Orchestrates Codex and Gemini prompts in parallel to surface diverse perspectives.
  • Synthesizes outputs into a single, actionable recommendation.
  • Supports fallback behavior when one provider is unavailable, with clear reconciliation.

Quick Start

Submit a task description as /oh-my-claudecode:ccg <task description> to run Codex and Gemini prompts and synthesize the final answer.

Frequently Asked Questions about ccg

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

FAQPage Schema
How do I orchestrate multi-model prompts to synthesize outputs from Codex and Gemini?

Multi-model orchestration routes a user request through Claude's Codex and Gemini prompts in parallel, then synthesizes the differing outputs into one coherent answer. This surfaces diverse perspectives for complex tasks like architecture reviews.

What is the best way to get cross-model validation for code and design critique?

Cross-model validation coordinates parallel prompts across Codex and Gemini to review code or design, then synthesizes the results into a single actionable recommendation while reconciling any differing perspectives.

How do I run a task through Codex and Gemini prompts using this orchestration environment?

To run coordinated prompts, submit your task description using the command syntax /oh-my-claudecode:ccg followed by your task description, which triggers the parallel prompt execution and final answer synthesis.

Does multi-model synthesis still work if one provider is unavailable?

Yes, multi-model synthesis supports fallback behavior when one provider is unavailable. It continues processing with the available model and provides clear reconciliation of the synthesized outputs.

Do I need a dedicated environment to orchestrate Codex and Gemini prompts?

Yes, orchestrating Codex and Gemini prompts requires a dedicated orchestration environment and access to both Codex and Gemini prompts to properly execute parallel routing and synthesize the final outputs.

When should I use multi-model orchestration instead of a single AI model?

Use multi-model orchestration for complex tasks like architecture reviews, code critique, and cross-model validation where you need diverse perspectives. It coordinates parallel prompts and reconciles differing results into one coherent answer.