gemini-cli

Runs Gemini CLI headlessly and returns structured summary, exitCode, and output tails.

1|Updated Jan 21, 2026
One-click install
npx skills add https://github.com/dustland/openviber --skill gemini-cli-dustland
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-cli
Source: https://github.com/dustland/openviber/tree/main/src/skills/gemini-cli
Command: npx skills add https://github.com/dustland/openviber --skill gemini-cli-dustland

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates coding and general task execution by running Google Gemini CLI in headless mode and returning chat-friendly outputs for seamless AI-assisted work.

Core Features & Use Cases

  • Headless execution of Gemini CLI for automated coding tasks and prompt-driven workflows.
  • Returns structured results including a summary, stdoutTail, and stderrTail to support follow-up actions.
  • Use Case: A developer asks the AI to review a repo, generate a patch, and test it using Gemini prompts with concise feedback.

Quick Start

Install Gemini CLI globally and run gemini in headless mode to perform tasks.

Frequently Asked Questions about gemini-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate coding tasks with the Gemini CLI in headless mode?

Automating coding tasks with the Gemini CLI in headless mode involves executing autonomous prompts programmatically. The system runs without a UI, returning structured outputs like a summary, exitCode, and stdoutTail for AI-assisted workflows.

What is headless execution for autonomous coding and how does it return results?

Headless execution for autonomous coding runs CLI prompts without an interactive interface. It returns concise, chat-friendly structured results, including a summary, exitCode, and stdoutTail/stderrTail, to support follow-up actions in AI-assisted workflows.

Can I configure wait times and model overrides when running Gemini CLI autonomously?

Yes, when running Gemini CLI autonomously, you can apply configurable wait times and model overrides. This allows you to tailor the execution environment and control how long the system waits for task completion.

What's the best way to integrate headless Gemini CLI outputs into AI-assisted development workflows?

The best way to integrate headless Gemini CLI outputs is by utilizing its structured format. The CLI returns a compact summary, exitCode, and stdoutTail/stderrTail, which can be directly parsed to drive follow-up actions in AI-assisted workflows.

Does this headless execution approach work for delegating general tasks and code reviews?

Yes, headless execution works for delegating general tasks and code reviews. You can prompt the Gemini CLI to review a repo, generate a patch, and test it, receiving concise feedback suitable for development automation.