菜单
General-purpose AI assistant using Gemini API with voice and text support. Use when you need a smart AI assistant that can answer questions, have conversations, or help with general tasks using Google's Gemini models with audio/text capabilities.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/dvcrn/openclaw-skills-marketplace --skill gemini-assistant命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | gemini-assistant |
| description | General-purpose AI assistant using Gemini API with voice and text support. Use when you need a smart AI assistant that can answer questions, have conversations, or help with general tasks using Google's Gemini models with audio/text capabilities. |
A general-purpose AI assistant powered by Google's Gemini API. Supports both text and voice interactions.
cd ~/.openclaw/agents/kashif/skills/gemini-assistant && python3 handler.py "Your question or message"
cd ~/.openclaw/agents/kashif/skills/gemini-assistant && python3 handler.py --audio /path/to/audio.ogg "optional context"
The handler returns a JSON response:
{
"message": "[[audio_as_voice]]\nMEDIA:/tmp/gemini_voice_xxx.ogg",
"text": "Text response from Gemini"
}
Set your Gemini API key:
export GEMINI_API_KEY="your-api-key-here"
Or create a .env file in the skill directory:
GEMINI_API_KEY=your-api-key-here
The default model is gemini-2.5-flash-native-audio-preview-12-2025 for audio support.
To use a different model, edit handler.py:
MODEL = "gemini-2.0-flash-exp" # For text-only
google-genai>=1.0.0numpy>=1.24.0soundfile>=0.12.0librosa>=0.10.0 (for audio input)