Gemini CLI

← Back to skills

Use Gemini in headless one-shot mode. Positional text starts interactive mode; use `-p/--prompt`.

Category: AI & Intelligent Agents
Repo: openclaw-openclaw
Path: skills/gemini/SKILL.md
Updated: 7/20/2026, 6:24:29 AM
Open on GitHubHow to Install

AI Summary

Use Gemini in headless one-shot mode. Positional text starts interactive mode; use `-p/--prompt`. It is useful for LLM applications, agent orchestration, RAG pipelines, AI evaluation, and multi-agent workflows. Source: openclaw-openclaw (skills/gemini/SKILL.md).

Gemini CLI

Use Gemini in headless one-shot mode. Positional text starts interactive mode; use -p/--prompt.

Quick start

  • gemini -p "Answer this question..."
  • gemini -m <model> -p "Prompt..."
  • gemini -p "Return JSON" --output-format json
  • stdin appends to -p: cat notes.md | gemini -p "Summarize"

Extensions

  • List: gemini --list-extensions
  • Manage: gemini extensions <command>
  • Skills: gemini skills <command>
  • Hooks: gemini hooks <command>
  • MCP: gemini mcp <command>

Notes

  • If auth is required, run gemini once interactively and follow the login flow.
  • Avoid --yolo for safety.

Related skills