gemini-cli

Automate headless Gemini CLI tasks and return structured JSON results.

1|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/nq-rdl/agent-extensions --skill gemini-cli-nq-rdl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-cli
Source: https://github.com/nq-rdl/agent-extensions/tree/main/skills/gemini-cli
Command: npx skills add https://github.com/nq-rdl/agent-extensions --skill gemini-cli-nq-rdl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates orchestration of headless Gemini CLI tasks to run in the background, reducing manual command overhead and enabling scalable automation.

Core Features & Use Cases

  • Spawn Gemini CLI as a subprocess in headless mode to execute prompts and receive structured JSON results.
  • Support ACP (persistent sessions) and parallel task execution for multi-turn and batch workloads.
  • Use workspace injection and model/flag controls (--model, --output-format, --resume, --sandbox) to tailor behavior across projects.

Quick Start

Summarize the content of a given document using Gemini in headless mode and return the result as JSON.

Frequently Asked Questions about gemini-cli

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

FAQPage Schema
How do I automate Gemini CLI tasks in the background and get JSON output?

To automate Gemini CLI tasks in the background and get JSON output, you can spawn the Gemini CLI as a headless subprocess. This allows you to execute prompts and receive structured JSON results without manual command overhead.

Can I run parallel batch workloads using headless Gemini CLI?

Yes, you can run parallel batch workloads using headless Gemini CLI. The skill supports parallel task execution and ACP mode for persistent sessions, enabling scalable multi-turn automation.

How do I customize Gemini CLI automation with different models and output formats?

You can customize Gemini CLI automation by injecting workspace context and applying specific flags. Use --model to select the AI model, --output-format to structure results, and --sandbox to control execution environments.

Do I need a specific environment to use headless Gemini CLI for automation?

Yes, you need an existing Gemini CLI environment to use headless automation. The skill operates within this environment, exposing prompts and controls through standard flags and workspace injection for system context.