ccg

Coordinates Codex and Gemini prompts to synthesize a unified output with rationale.

16|3|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/sehoon787/my-claude --skill ccg-sehoon787
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ccg
Source: https://github.com/sehoon787/my-claude/tree/main/skills/omc/ccg
Command: npx skills add https://github.com/sehoon787/my-claude --skill ccg-sehoon787

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinate Codex and Gemini prompts to generate a unified, synthesized answer.

Core Features & Use Cases

  • Orchestrates Codex and Gemini prompts to aggregate parallel advisor outputs.
  • Synthesizes outputs into a single coherent result with rationale.
  • Use Case: Complex reviews requiring architecture and UX perspectives in one pass.

Quick Start

Provide a task description and let the skill route it through Codex and Gemini prompts, then synthesize a single, unified result.

Frequently Asked Questions about ccg

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

FAQPage Schema
How do I synthesize Codex and Gemini outputs into one unified answer?

To synthesize Codex and Gemini outputs, you provide a task description that the skill routes through parallel prompts to each model, resolving conflicts and generating a single coherent result.

What is multi-agent prompt orchestration for large language models?

Multi-agent prompt orchestration coordinates separate prompts to models like Codex and Gemini, aggregating their parallel advisor outputs into a synthesized result with rationale for complex reviews.

Do I need both Codex and Gemini toolchains available to use this orchestration skill?

Yes, you need the underlying toolchains for Codex and Gemini available, because the skill orchestrates a two-prompt workflow that requires both to generate and reconcile parallel outputs.

Can I reconcile architecture and UX perspectives in one pass using parallel LLM prompts?

Yes, you can reconcile architecture and UX perspectives by routing a task through Codex and Gemini prompts, allowing the skill to synthesize the parallel outputs into one unified result.

What is the best way to aggregate parallel advisor outputs for engineering reviews?

The best way to aggregate parallel advisor outputs is using a two-prompt orchestration workflow that generates responses from Codex and Gemini, then applies conflict resolution to synthesize a single answer.

What are the limitations of synthesizing multiple model outputs for product decisions?

A limitation is that synthesizing multiple model outputs depends entirely on the availability of both underlying toolchains, and the final result requires effective conflict resolution between differing parallel perspectives.