An advanced automation skill that interacts with the Gemini web interface to perform high-level reasoning and AI image generation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install gemini-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Gemini Web Ops?
Gemini Web Ops is a specialized capability built for Openclaw Skills that enables AI agents to interact directly with the Google Gemini web interface. It bypasses standard API constraints by using a dedicated browser profile to access the most powerful models, including Gemini 3.1 Pro. This skill is designed to handle both complex text-based inquiries and creative image generation tasks, providing a bridge between natural language requests and the Gemini web ecosystem.
Gemini Web Ops Use Cases
- Requesting complex reasoning and long-form answers from the highest-tier Gemini models.
- Generating creative AI images and posters using the native Gemini image generation engine.
- Automating web-based AI workflows where API access might be restricted or insufficient.
- Executing multi-modal tasks that require switching between text analysis and visual output.
How Gemini Web Ops Works
- The skill identifies the user's intent through specific keywords like ask Gemini or generate image within the Openclaw Skills environment.
- It initializes the OpenClaw internal browser using the designated openclaw profile to maintain session state.
- The agent navigates to the Gemini portal and validates the authentication status.
- It automatically selects the most powerful available model, prioritizing Gemini 3.1 Pro.
- Depending on the task, it either captures the text output or activates the image generation toggle to produce and download visual assets.
Gemini Web Ops Setup
To use this skill, ensure you have an active Google account and have logged into the Gemini web portal at least once using the OpenClaw browser profile. This ensures session persistence for Openclaw Skills.
# Ensure your environment is ready for OpenClaw browser automation
# Verify that the following script exists:
# scripts/gemini_ui_shortcuts.js
Gemini Web Ops Data Schema & Taxonomy
| Component | Description |
|---|---|
| Browser Profile | Utilizes the openclaw profile for persistent login and cookies. |
| Input Triggers | Keywords like nanobanana, image generation, and ask Gemini. |
| Model Selection | Defaults to the strongest available model (Gemini 3.1 Pro). |
| Image Retrieval | Downloads original files via the UI button or context-menu save. |
Gemini Web Ops Advanced Features
- Intelligent task routing that differentiates between text-based Q&A and image generation flows.
- Low-token optimization strategy utilizing custom UI shortcuts to reduce processing overhead.
- Robust failure recovery including page refreshing, model downgrading, and timeout handling.
- Multi-image support capable of sequential retrieval and delivery of all generated visuals.
SKILL.md
Loading
Related Openclaw Skills
Lecture Notes Master
A powerful AI skill that converts various media into deep, multi-layered Obsidian vaults using recursive atomic decomposition.
Skill Inventory Manager
An automated utility to scan, index, and manage your library of installed Openclaw Skills for AI agents.
x-mirror
A comprehensive CLI tool to manage and switch download mirrors for various system and language package managers.
Business Opportunity Insight
An AI-driven analytical engine that evaluates market trends and technical data to uncover high-value entrepreneurial opportunities.
Firecrawl CLI
A comprehensive web scraping and automation toolkit that enables AI agents to crawl websites, map URLs, and execute browser actions via a cloud-based sandbox.
Commodities Quote
A high-precision financial skill for retrieving real-time commodity prices and technical market indicators via Octagon MCP.
Featured*
