菜单
Generate or edit images with Google Gemini. Alternative to DALL-E for image generation. Requires GEMINI_API_KEY.
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。
基于 SOC 职业分类
Guide for creating, updating, and managing skills. Use when: you need to extend your capabilities with a new skill, or the user asks you to create one. Skills are persistent Markdown instruction modules auto-discovered at runtime.
Send and read WhatsApp messages via the wacli CLI. Search chats, view history, send text and files to contacts or groups.
Access 1Password secrets via the op CLI: read passwords, inject secrets into commands, manage vaults. Requires desktop app integration.
Manage Apple Reminders via remindctl CLI: list, add, edit, complete, delete. Supports lists, date filters, and JSON output. Syncs to iOS devices.
Create, search, and manage Bear notes via the grizzly CLI. Supports tags, x-callback-url, and JSON output.
Control Bluesound/NAD players: discovery, playback, volume, grouping, and TuneIn radio via blu CLI.
| name | gemini-image-gen |
| description | Generate or edit images with Google Gemini. Alternative to DALL-E for image generation. Requires GEMINI_API_KEY. |
| requires_env | ["GEMINI_API_KEY"] |
Generate images using Google's Gemini model.
curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-exp:generateContent?key=$GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"contents": [{"parts": [{"text": "Generate an image of: detailed description here"}]}],
"generationConfig": {"responseModalities": ["TEXT", "IMAGE"]}
}'
Response contains candidates[0].content.parts[]. Image data appears in parts with:
inlineData.mimeType (e.g., image/png)inlineData.data (base64-encoded)Save to file:
echo "BASE64_DATA" | base64 -d > image.png