How do I install the Ccg skill?

Run npx skillmds add zereight/ccg in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ccg?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

zereight (@zereight) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ccg by zereight — Agent Skill

Name: Ccg
Rating: 4.2 (5 reviews)
Author: zereight

File contents

CCG - Claude-Codex-Gemini Tri-Model Orchestration

Route a task through three AI models in parallel, then synthesize their outputs into one unified answer.

When to Use

Backend/analysis + frontend/UI work in one request
Code review from multiple perspectives
Cross-validation where models may disagree
Fast parallel input without full team orchestration

When NOT to Use

Simple, straightforward tasks → execute directly
Already clear on approach → use /omg-autopilot
Need coordinated multi-agent work → use /team

Requirements

Codex CLI: npm install -g @openai/codex
Gemini CLI: npm install -g @google/gemini-cli
If either CLI is unavailable, continue with whichever provider works

Execution Protocol

1. Decompose Request

Split the user request into:

Codex prompt: architecture, correctness, backend, risks, test strategy
Gemini prompt: UX/content clarity, alternatives, edge-case usability, docs polish
Synthesis plan: how to reconcile conflicts

2. Invoke Advisors

Run both advisors via CLI in parallel:

# Run in terminal
codex "<codex prompt>"
gemini "<gemini prompt>"

Or via VS Code's selectChatModels() API if available:

Promise.all([
  model_openai.sendRequest(codex_prompt),
  model_google.sendRequest(gemini_prompt)
])

3. Collect Results

Gather outputs from both advisors.

4. Synthesize

Return one unified answer with:

Agreed recommendations
Conflicting recommendations (explicitly called out)
Chosen final direction + rationale
Action checklist

Fallbacks

Scenario	Action
One provider unavailable	Continue with available + Claude synthesis
Both unavailable	Fall back to Claude-only answer

Example

/ccg Review this PR - architecture/security via Codex and UX/readability via Gemini

Output:

=== CCG Synthesis ===

## Agreed
- Authentication middleware needs rate limiting
- Error messages should be more user-friendly

## Conflicting
- Codex: Use middleware pattern for validation
- Gemini: Use inline validation for simplicity
→ Chosen: Middleware pattern (consistency with existing codebase)

## Action Checklist
- [ ] Add rate limiting middleware
- [ ] Improve error messages in auth flow
- [ ] Extract validation to middleware layer

---name: ccgdescription: Claude-Codex-Gemini tri-model orchestration for multi-perspective analysis. Activate when user says: ccg, tri-model, three models, multi-model, cross-validate, get multiple opinions, compare models.--- # CCG - Claude-Codex-Gemini Tri-Model Orchestration Route a task through three AI models in parallel, then synthesize their outputs into one unified answer. ## When to Use - Backend/analysis + frontend/UI work in one request - Code review from multiple perspectives - Cross-validation where models may disagree - Fast parallel input without full team orchestration ## When NOT to Use - Simple, straightforward tasks → execute directly - Already clear on approach → use `/omg-autopilot` - Need coordinated multi-agent work → use `/team` ## Requirements - **Codex CLI**: `npm install -g @openai/codex` - **Gemini CLI**: `npm install -g @google/gemini-cli` - If either CLI is unavailable, continue with whichever provider works ## Execution Protocol ### 1. Decompose Request Split the user request into: - **Codex prompt**: architecture, correctness, backend, risks, test strategy - **Gemini prompt**: UX/content clarity, alternatives, edge-case usability, docs polish - **Synthesis plan**: how to reconcile conflicts ### 2. Invoke Advisors Run both advisors via CLI in parallel: ```bash # Run in terminal codex "<codex prompt>" gemini "<gemini prompt>" ``` Or via VS Code's `selectChatModels()` API if available: ``` Promise.all([ model_openai.sendRequest(codex_prompt), model_google.sendRequest(gemini_prompt) ]) ``` ### 3. Collect Results Gather outputs from both advisors. ### 4. Synthesize Return one unified answer with: - **Agreed** recommendations - **Conflicting** recommendations (explicitly called out) - **Chosen** final direction + rationale - **Action** checklist ## Fallbacks | Scenario | Action | |----------|--------| | One provider unavailable | Continue with available + Claude synthesis | | Both unavailable | Fall back to Claude-only answer | ## Example ``` /ccg Review this PR - architecture/security via Codex and UX/readability via Gemini ``` Output: ``` === CCG Synthesis === ## Agreed - Authentication middleware needs rate limiting - Error messages should be more user-friendly ## Conflicting - Codex: Use middleware pattern for validation - Gemini: Use inline validation for simplicity → Chosen: Middleware pattern (consistency with existing codebase) ## Action Checklist - [ ] Add rate limiting middleware - [ ] Improve error messages in auth flow - [ ] Extract validation to middleware layer ```

Frequently asked questions