# Gemini

> Delegate tasks or get a second opinion from Gemini CLI. Infers mode (delegation vs validation) from prompt context. Detects available models at runtime via the CLI. Use when cross-validating code, plans, or architecture with Gemini CLI, or offloading work to it. Do not use when already running inside Gemini CLI or for tasks that do not benefit from cross-model input.

- Skill: `darshitpp/gemini` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add darshitpp/gemini`
- Raw SKILL.md: https://api.skillmd.com/api/skills/darshitpp/gemini/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: darshitpp (https://skillmd.com/u/darshitpp)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/darshitpp/gemini

---


# Cross-Agent Task Runner — Gemini CLI

## Procedures

**Step 1: Self-Call Detection**

1. Check for `GEMINI_CLI` environment variable.
2. If detected, stop and inform the user:
   "Cannot invoke Gemini from within Gemini. Use a different target CLI."

**Step 2: Execute Shared Procedure**

1. Read `references/shared-procedure.md` for the core workflow
   (mode inference, context gathering, prompt construction, result presentation).
2. Read `references/cli-gemini.md` for Gemini-specific flags, model selection
   heuristics, and version compatibility matrix.
3. Follow the shared procedure using the Gemini-specific details.