antigravity-image-gen
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
Why use this skill?
Generate professional-grade images directly in OpenClaw using the Google Antigravity API. Fast, native, and secure image generation for all your AI agent workflows.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/knightluozichu/antigravity-image-gen-1-0-0What This Skill Does
The antigravity-image-gen skill enables direct, high-quality image generation within your OpenClaw environment by interfacing directly with Google's Antigravity API (Gemini 3 Pro Image). Unlike traditional methods that rely on sluggish browser automation or third-party web scrapers, this skill communicates directly with the daily-cloudcode-pa.sandbox endpoint. By utilizing native OAuth credentials, the skill ensures a seamless, performant, and secure workflow for generating high-fidelity visual assets, illustrations, and conceptual imagery directly from your terminal or script workflows.
Installation
To integrate this skill into your environment, use the OpenClaw command-line interface. Ensure your system has Node.js installed, as the execution scripts rely on a Node runtime environment. Run the following command:
clawhub install openclaw/skills/skills/knightluozichu/antigravity-image-gen-1-0-0
Before running the skill, verify that your OAuth profile is correctly configured in ~/.clawdbot/agents/main/agent/auth-profiles.json. You must authenticate via the google-antigravity provider to authorize API requests.
Use Cases
This skill is ideal for developers, designers, and AI enthusiasts who need automated visual content generation without the overhead of browser-based tools. Use it to:
- Rapidly generate prototypes for web or app design.
- Create consistent assets for internal reports and documentation.
- Build automated content pipelines where specific images are required as part of a larger technical workflow.
- Integrate high-quality AI art into custom agent behavior without manually navigating external image generation websites.
Example Prompts
- "Generate a 16:9 widescreen image of a minimalist workspace with a neon-lit desk, save it to ~/designs/workspace.png."
- "Create an image of an ancient library with floating books, use a 4:3 aspect ratio and name the file fantasy_library.png."
- "Show me a futuristic city on Mars in a 9:16 vertical format for a mobile background."
Tips & Limitations
To maximize effectiveness, always define an aspect ratio that fits your use case. If you encounter a 429 status code, you have exceeded your project's API quota; please throttle your requests. If the image returns blank or incomplete, review the prompt for potential safety filters triggered by the Gemini 3 Pro model. Always ensure the file path is writeable by the agent process to avoid file-write errors.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-knightluozichu-antigravity-image-gen-1-0-0": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, external-api
Related Skills
agent-orchestrator
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
canvas-os
Canvas as an app platform. Build, store, and run rich visual apps on the OpenClaw Canvas.