Use Case
Image Gen is a powerful AI agent skill that extends your assistant with new capabilities. Nano-banana image generation and editing skill. Supports text-based pictures and picture-based pictures, uses AI to generate/edit images based on text descriptions or reference pictures, automatically compresses large images, saves them to the workspace/img directory, and displays them directly on Feishu. Trigger scenario: User requests to generate pictures, draw pictures, AI drawing, create images, modify pictures, generate pictures based on pictures, and generate pictures from pictures. This guide walks you through installing Image Gen, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Image Gen: npx clawhub@latest --dir ~/.claude/skills install image-gen-skill
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to design & creative to trigger Image Gen
Review the output and refine your prompt for better results
Combine Image Gen with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Image Gen
Help me get started with Image Gen
What can Image Gen do for my design & creative workflow?
Show me an example of using Image Gen
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install image-gen-skillOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install image-gen-skillβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/image-gen-skill/π‘Extract and place the folder at the path above, then restart your agent.