Gemini CLI

---

name: gemini

description: Gemini CLI for one-shot Q&A, summaries, and generation.

homepage: https://ai.google.dev/

metadata: {"clawdbot":{"emoji":"♊️","requires":{"bins":["gemini"]},"install":[{"id":"brew","kind":"brew","formula":"gemini-cli","bins":["gemini"],"label":"Install Gemini CLI (brew)"}]}}

---

# Gemini CLI

Use Gemini in one-shot mode with a positional prompt (avoid interactive mode).

Quick start

File-output mode (for large token or explicit file return)

- Always saves Gemini output to a file under `outputs/` in this skill directory.

- Always returns `file_path` (absolute path) in JSON.

- Optionally returns `content` when `--include-content` is provided.

- `--model <model_name>`

- `--output-format text|json`

- `--output-file <filename>`

- `--output-dir <dir>`

- `--include-content`

Required response contract for this mode

Example

- `python3 /Users/shichen/skills/gemini/gemini_file_runner.py --prompt "写一篇约 1000 字中文小说，主题是..." --output-file novel-1000-words.txt`

- `{"ok":true,"file_path":"/Users/shichen/skills/gemini/outputs/novel-1000-words.txt"}`

Video parsing example (large content)

- `python3 /Users/shichen/skills/gemini/gemini_file_runner.py --model gemini-3-flash-preview --prompt "解析视频内容并输出结构化总结..." --output-file video-analysis.txt`

Extensions

Notes