skills.rest
xdkp
xdkpCOMMUNITY
Explore all skills by this author →
GitHub

ccg

Runs Codex and Gemini CLIs in parallel and synthesizes their outputs into one actionable answer with fallbacks.

Updated May 20, 2026
Search Tags:#code review#codex#synthesis#gemini#cli workflows#tri-model orchestration#cloude code
One-click install
npx skills add https://github.com/xdkp/oh-my-claudecode --skill ccg-xdkp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ccg
Source: https://github.com/xdkp/oh-my-claudecode/tree/main/skills/ccg
Command: npx skills add https://github.com/xdkp/oh-my-claudecode --skill ccg-xdkp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of getting a single, high-quality answer from multiple specialized AI perspectives (Codex for engineering rigor and Gemini for UX/design clarity) without manually coordinating separate runs.

Core Features & Use Cases

  • Parallel advisor execution: Runs Codex and Gemini via CLI in parallel to cover architecture/correctness and UX/content clarity.
  • Synthesis into one actionable answer: Reconciles agreements and conflicts into one final recommendation with a clear action checklist.
  • Graceful fallbacks: Continues with the available provider and transparently notes what perspective was missing.

Quick Start

Use the CCG skill to review a task by asking for architecture/security from Codex and UX/readability polish from Gemini, then returning one synthesized final answer.

Frequently Asked Questions about ccg

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

FAQPage Schema
How do I get a single code review from multiple AI perspectives?▼

Tri-model orchestration runs Codex and Gemini advisor prompts in parallel, synthesizing their outputs into one actionable answer with a clear checklist. This prevents manually coordinating separate runs for engineering correctness and UX refinement.

What is tri-model orchestration for CLI workflows?▼

Tri-model orchestration is a process that executes Codex and Gemini via CLI in parallel to cover architecture correctness and UX clarity. It then reconciles agreements and conflicts into one final recommendation for tasks like PR reviews.

Do I need the Codex CLI and Gemini CLI to run cross-validation tasks?▼

Yes, cross-validation tasks require the Codex CLI and Gemini CLI available via the omc ask codex and omc ask gemini commands. The tool reads artifacts from .omc/artifacts/ask for synthesis to function properly.

What happens if one AI provider is unavailable during parallel code review?▼

Graceful fallbacks continue the code review with the available provider and transparently notes what perspective was missing. It does not fail the entire task if either Codex or Gemini is unavailable during execution.

Can I use this for PR reviews that need both architecture and readability checks?▼

Yes, PR reviews are a core use case. You ask for architecture and security feedback from Codex and UX or readability polish from Gemini, returning one synthesized final answer that addresses both engineering and design dimensions.

Related Skills

Explore More Software Engineering Skills→
Leap0920Leap0920
1

ask

Route prompts to local Claude, Codex, or Gemini CLIs and persist outputs as OMC ask artifacts.

Community
Intermediate
Leap0920Leap0920
1

ccg

Combine Codex and Gemini outputs into one synthesized answer.

Community
Intermediate
ClementATHClementATH

ask

Route advisor prompts to Claude, Codex, or Gemini via the omc ask wrapper and save artifacts.

Community
Intermediate
HuuBarHuuBar

product-analysis

Coordinate parallel multi-model analyses into structured product evaluation reports.

Community
Advanced