Agent Skills
› the-open-agent/openagent
› gemini
gemini
GitHub提供 Gemini CLI 命令行工具的使用指南，支持单轮问答、摘要生成及 JSON 输出。涵盖快速启动、模型选择、扩展管理及认证流程，旨在通过非交互模式高效调用 AI 能力。
Trigger Scenarios
需要使用 Gemini CLI 进行文本生成或问答
需要获取 Gemini 支持的模型列表
需要将 AI 输出格式化为 JSON
Install
npx skills add the-open-agent/openagent --skill gemini -g -y
SKILL.md
Frontmatter
{
"name": "gemini",
"homepage": "https:\/\/ai.google.dev\/",
"metadata": {
"emoji": "✨",
"requires": {
"bins": [
"gemini"
]
}
},
"description": "Gemini CLI for one-shot Q&A, summaries, and generation."
}
Gemini CLI
Use Gemini in one-shot mode with a positional prompt (avoid interactive mode).
Quick start
gemini "Answer this question..."gemini --model <name> "Prompt..."gemini --output-format json "Return JSON"
Extensions
- List:
gemini --list-extensions - Manage:
gemini extensions <command>
Notes
- If auth is required, run
geminionce interactively and follow the login flow. - Avoid
--yolofor safety.
Version History
- 618631e Current 2026-08-20 18:16
