A powerful command-line interface for Google Gemini models, designed for codebase analysis, AI-driven code generation, and automated developer workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-cli
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-cli 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 CLI?
The Gemini CLI skill is a comprehensive developer tool that brings the power of Google's Gemini models directly into your terminal. This official tool allows developers to interact with large codebases, perform AI-powered debugging, and even generate full React components or API specs from visual assets like screenshots and PDF documents. By integrating this into Openclaw Skills, developers can bridge the gap between their local development environment and advanced generative AI.
Built on Node.js, the CLI provides a seamless bridge for automated scripting and interactive AI sessions. It is specifically designed to handle complex context-heavy tasks like reviewing pull request patches or explaining architecture patterns within a local directory. Using Openclaw Skills ensures you have the technical documentation and setup steps needed to leverage this tool safely and efficiently without leaving your terminal workflow.
Gemini CLI Use Cases
- Analyzing large or unfamiliar codebases to understand complex logic and architecture
- Generating functional code and applications directly from design screenshots or PDF specifications
- Automating repetitive developer workflows like documentation generation and code reviews
- Troubleshooting and debugging code via an interactive AI shell within the terminal environment
- Creating batch processing scripts to analyze or transform multiple files simultaneously using AI models
How Gemini CLI Works
- The user installs the official gemini-cli package via npm and configures the environment with a valid Google API key.
- The skill initializes a secure connection to Google's Gemini API endpoints using the provided environment variables.
- Developers invoke specific commands like code or chat to send prompts and local file context to the model.
- The CLI processes various inputs—including text, images, or PDFs—and streams AI-generated responses back to the terminal or redirects them to output files.
- Advanced users can chain these commands into shell scripts to perform complex batch operations across an entire project directory.
Gemini CLI Setup
To get started with this skill from Openclaw Skills, ensure you have Node.js 20 or higher installed on your system. Install the CLI globally using npm:
npm install -g @google/gemini-cli
Next, obtain your API key from Google AI Studio and set it as an environment variable in your shell session:
export GEMINI_API_KEY="your_api_key_here"
Verify that the tool is correctly installed and authenticated by checking the version:
gemini --version
Gemini CLI Data Schema & Taxonomy
The Gemini CLI manages data primarily through standard input/output streams and local environment variables. It follows a stateless security model for credentials within the Openclaw Skills ecosystem:
| Component | Handling Method | Persistence |
|---|---|---|
| API Credentials | Environment Variable (GEMINI_API_KEY) | Volatile / Session-based |
| Code Context | Local file system paths passed as arguments | Read-only during execution |
| Temporary Assets | System temp directory | Auto-cleaned by OS |
| AI Outputs | Standard output (stdout) or specified JSON files | User-defined storage |
This architecture ensures that no persistent configuration files or sensitive authentication data are stored in hidden local directories.
Gemini CLI Advanced Features
- Context-aware codebase querying using the context flag for deep directory analysis and understanding
- Multimodal generation support for creating apps from images and automated document parsing from PDF files
- Automated workflow engine for chaining multi-step AI tasks via a single command interface
- Batch processing mode for executing AI tasks on large lists of files using structured JSON input and output
- Model selection flexibility allowing users to switch between different versions of Gemini using the model flag
SKILL.md
Loading
Related Openclaw Skills
AI Data Visualization Tool
An intelligent automation skill that transforms complex datasets into high-impact visual reports and actionable insights using advanced AI processing.
AI Content Rewriting Tool
A high-performance AI agent skill designed to automate content rewriting and multi-language transformation for professional teams.
nano-pdf
A command-line interface for applying precise PDF edits through natural language instructions.
AI Code Assistant
A high-performance automation skill designed to streamline coding workflows and boost development efficiency through AI-driven batch operations.
Cloak
Cloak enables secure, one-time secret sharing between humans and AI agents via encrypted, self-destructing links.
Repo Surveyor
A specialized skill for manual repository orientation and task context generation when automated mapping tools are unavailable.
Featured*
