skills/ccg/SKILL.md
Antigravity-Codex-Gemini tri-model orchestration via /ask codex + /ask gemini, then Antigravity synthesizes results
npx skillsauth add Rheinmir/skills-kit ccgInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
CCG routes through the canonical /ask skill (/ask codex + /ask gemini), then Antigravity synthesizes both outputs into one answer.
Use this when you want parallel external perspectives without launching tmux team workers.
npm install -g @openai/codex (or @openai/codex)npm install -g @google/gemini-cliomc ask command available1. Antigravity decomposes the request into two advisor prompts:
- Codex prompt (analysis/architecture/backend)
- Gemini prompt (UX/design/docs/alternatives)
2. Antigravity runs via CLI (skill nesting not supported):
- `omc ask codex "<codex prompt>"`
- `omc ask gemini "<gemini prompt>"`
3. Artifacts are written under `.omc/artifacts/ask/`
4. Antigravity synthesizes both outputs into one final response
When invoked, Antigravity MUST follow this workflow:
Split the user request into:
Note: Skill nesting (invoking a skill from within an active skill) is not supported in Antigravity. Always use the direct CLI path via Bash tool.
Run both advisors:
omc ask codex "<codex prompt>"
omc ask gemini "<gemini prompt>"
Read latest ask artifacts from:
.omc/artifacts/ask/codex-*.md
.omc/artifacts/ask/gemini-*.md
Return one unified answer with:
If one provider is unavailable:
If both unavailable:
/oh-my-claudecode:ccg <task description>
Example:
/oh-my-claudecode:ccg Review this PR - architecture/security via Codex and UX/readability via Gemini
development
Full autonomous execution from idea to working code
development
Full autonomous execution from idea to working code
documentation
Agentic memory system for writers - track characters, relationships, scenes, and themes
testing
Structured visual QA verdict for screenshot-to-reference comparisons