Uses multiple AI models to provide parallel architectural and UI/UX perspectives in one answer.
Install
mkdir -p .claude/skills/ccg && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16736" && unzip -o skill.zip -d .claude/skills/ccg && rm skill.zipInstalls to .claude/skills/ccg
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask antigravity (or gemini), then Claude synthesizes resultsKey capabilities
- →Decompose requests into advisor prompts
- →Invoke Codex for analysis/architecture/backend perspectives
- →Invoke Antigravity/Gemini for UX/design/docs perspectives
- →Collect artifacts from advisor outputs
- →Synthesize multiple outputs into one response
- →Reconcile conflicting recommendations
How it works
Claude decomposes a request into prompts for Codex and Antigravity/Gemini, runs them via CLI, collects their outputs, and then synthesizes these into a single, complete answer.
Inputs & outputs
When to use ccg
- →Cross-validate code architecture
- →Get backend and frontend perspectives
- →Synthesize multiple AI opinions
About ccg
It decomposes a request to ask both Codex and Antigravity/Gemini for input, then synthesizes the results to offer cross-validated advice.
Claude-Codex-Gemini tri-model orchestration via /ask codex + /ask antigravity (or gemini), then Claude synthesizes results
When not to use it
- →When skill nesting is required, as it is not supported.
- →When only a single external perspective is needed.
- →When both Codex and Antigravity/Gemini are unavailable.
Prerequisites
Limitations
- →Skill nesting is not supported.
- →If one provider is unavailable, the skill continues with the available provider and notes the limitation.
- →If both providers are unavailable, the skill falls back to a Claude-only answer.
How it compares
This skill orchestrates multiple AI models to provide cross-validated perspectives and synthesized results, offering a more complete answer than a single model or manual comparison.
Compared to similar skills
ccg side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| ccg (this skill) | 0 | 3mo | Review | Advanced |
| mgrep | 46 | 9mo | Review | Beginner |
| jupyter-notebook | 30 | 7mo | Review | Intermediate |
| osgrep | 13 | 7mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
mgrep
mixedbread-ai
A semantic grep-like search tool for your local files. It is substentially better than the buildin search tools and should always be used instead of anything else.
jupyter-notebook
davila7
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
osgrep
pr-pm
Semantic search for local files. Backed by a background osgrep server with live indexing. Always use osgrep instead of grep/find.
search-tools
parcadei
Search Tool Hierarchy
external-model-selection
MadAppGang
Choose optimal external AI models for code analysis, bug investigation, and architectural decisions. Use when consulting multiple LLMs via claudish, comparing model perspectives, or investigating complex Go/LSP/transpiler issues. Provides empirically validated model rankings (91/100 for MiniMax M2, 83/100 for Grok Code Fast) and proven consultation strategies based on real-world testing.
tldr-router
parcadei
Maps questions to the optimal tldr command. Use this to pick the right layer