Dual-AI engineering loop orchestrating Claude Code (planning/implementation) and Gemini (validation/review). Use when (1) complex feature development requiring validation, (2) high-quality code with security/performance concerns, (3) large-scale refactoring, (4) user requests gemini-claude loop or dual-AI review. Do NOT use for simple one-off fixes or prototypes.
/plugin marketplace add creator-hian/claude-code-plugins/plugin install codex-plugin@creator-hian-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
VALIDATION.mdreferences/commands.mdPlan (Claude) → Validate (Gemini) → Implement (Claude) → Review (Gemini) → Fix → Re-validate → Done
| Role | Responsibility |
|---|---|
| Claude | Architecture, planning, code implementation (Edit/Write/Read) |
| Gemini | Validation, code review, quality assurance |
Non-TTY environment: See gemini-cli SKILL for CLI fundamentals. Key rule: Always use
gemini -p "prompt"(headless mode required)
mkdir -p .gemini-loopAskUserQuestion:
.gemini-loop/plan.mdAsk user for role mode, then execute with timeout: 600000:
gemini -m gemini-3-flash-preview -p "Review this plan: $(cat .gemini-loop/plan.md) ..."
Full prompts by role mode: See commands.md
Save result: > .gemini-loop/phase2_validation.md
If issues found:
AskUserQuestion: "Revise and re-validate, or proceed?".gemini-loop/implementation.mdExecute with timeout: 600000:
gemini -m gemini-3-flash-preview --include-directories ./src -p "Review: $(cat .gemini-loop/plan.md) $(cat .gemini-loop/implementation.md) ..."
Full prompts by role mode: See commands.md
Save result: > .gemini-loop/phase5_review.md
Claude response by severity:
.gemini-loop/phase5_review.md.gemini-loop/
├── plan.md # Implementation plan
├── phase2_validation.md # Plan validation result
├── implementation.md # Implementation summary
├── phase5_review.md # Code review result
└── iterations.md # Iteration history
Always use timeout: 600000 (10 min) for all Gemini commands.