# Gemini

> Use the Gemini CLI for one-shot Q&A, summarization, and generation tasks. Trigger when Gemini-specific CLI usage, model selection, or JSON-formatted output is needed.

- Skill: `michaelschecht/gemini-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add michaelschecht/gemini-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/michaelschecht/gemini-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: michaelschecht (https://skillmd.com/u/michaelschecht)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/michaelschecht/gemini-2

---


# Gemini

Use this skill when the task specifically benefits from the `gemini` CLI rather than a generic model prompt.

## Prerequisites

- `gemini` CLI installed and available on `PATH`
- Authenticated locally by running `gemini` once interactively if needed

## When To Use

- Run one-shot prompts against Gemini models
- Request structured JSON output from the CLI
- Switch models explicitly for a prompt
- Summarize or generate text through Gemini without entering interactive mode

## Common Patterns

- Basic prompt: `gemini "Answer this question..."`
- Model selection: `gemini --model <name> "Prompt..."`
- Structured output: `gemini --output-format json "Return JSON"`
- Extension discovery: `gemini --list-extensions`

## Working Notes

- Prefer positional prompts for deterministic one-shot execution
- Avoid interactive sessions unless setup or login is required
- Avoid unsafe flags like `--yolo`
- If a task depends on Gemini extensions, list them first before assuming availability