skills.rest
shalevamin
shalevaminCOMMUNITY
Explore all skills by this author →
GitHub

gemini

Runs one-shot prompts against the Gemini CLI for Q&A, summaries, and generation.

Updated Mar 7, 2026
Search Tags:#summarization#cli#llm#generation#gemini#q&a#prompt
One-click install
npx skills add https://github.com/shalevamin/Tau_agent --skill gemini-shalevamin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini
Source: https://github.com/shalevamin/Tau_agent/tree/main/tau-agent-main/skills/gemini
Command: npx skills add https://github.com/shalevamin/Tau_agent --skill gemini-shalevamin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It provides a quick way to query Google's Gemini models from the command line for one-shot questions, summaries, and text generation without building a custom API integration. ## Core Features & Use Cases - One-Shot Prompting: Pass a positional prompt to gemini to get an immediate answer without entering interactive mode. - Model and Output Control: Select a specific model with --model and request structured results with --output-format json. - Extension Management: List and manage Gemini CLI extensions via gemini --list-extensions and gemini extensions <command>. - Use Case: Ask the agent to summarize a long document or answer a technical question by running gemini "Summarize this text..." and capturing the response. ## Quick Start Ask the agent to run gemini with your question as a single quoted prompt, for example to answer a question or summarize provided text.

Frequently Asked Questions about gemini

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

FAQPage Schema
How do I use the Gemini CLI for one-shot prompts?▼

Run gemini followed by your prompt as a quoted positional argument, such as gemini "Answer this question...". This returns a single response without entering interactive mode.

How do I get JSON output from the Gemini CLI?▼

Use the --output-format json flag with your prompt, for example gemini --output-format json "Return JSON". The CLI then returns the response structured as JSON.

How do I choose a specific Gemini model in the CLI?▼

Pass the --model flag followed by the model name, such as gemini --model <name> "Prompt...". This overrides the default model for that invocation.

Why does the Gemini CLI ask for authentication?▼

The Gemini CLI requires login on first use. Run gemini once interactively and follow the login flow to complete authentication before using one-shot mode.

How do I manage Gemini CLI extensions?▼

List installed extensions with gemini --list-extensions and manage them using gemini extensions <command>. Extensions add extra capabilities to the CLI.

Related Skills

Explore More Software Engineering Skills→
trpc-grouptrpc-group
1.8k

gemini

Runs Gemini CLI in one-shot mode for Q&A, summaries, and text generation.

Official
Basic
SpillwaveSolutionsSpillwaveSolutions
4

gemini

Pipe input content to the Gemini CLI for headless AI tasks and file outputs.

Official
Intermediate
AradotsoAradotso
2

duel-agents-routing

Route prompts across OpenAI and Anthropic models to minimize cost.

Official
Advanced
ClyptAIClyptAI

gemini-interactions-api

Orchestrates Gemini models via Interactions API for chat and streaming workflows in Python and TypeScript.

Official
Intermediate