skills.rest
fkguo
fkguoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gemini-cli-runner

Execute the Gemini CLI with model selection and file-based prompts.

14|6|Updated Feb 24, 2026
Search Tags:#model selection#Gemini CLI#output handling#prompt input#cross-model work
One-click install
npx skills add https://github.com/fkguo/nullius --skill gemini-cli-runner
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-cli-runner
Source: https://github.com/fkguo/nullius/tree/main/skills/gemini-cli-runner
Command: npx skills add https://github.com/fkguo/nullius --skill gemini-cli-runner

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill allows users to run the local Gemini CLI with model selection, file-based prompt input, and output handling, enabling one-shot mode for arbitrary prompts.

Core Features & Use Cases

  • Model Selection: Run the Gemini CLI with a specified model, supporting different reasoning depths.
  • File-based Prompt Input: Input prompts from files, including system prompts and user prompts.
  • Output Handling: Write output to a target file with safe fallbacks if the model alias differs.
  • Use Case: For users who need to interact with the Gemini CLI from a different host or for cross-model work, this Skill provides a convenient way to invoke Gemini and manage the output.

Quick Start

Run the gemini-cli-runner skill with the desired model and prompt files, specifying the output file.

Frequently Asked Questions about gemini-cli-runner

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

FAQPage Schema
How do I run the Gemini CLI with a specific model for cross-model tasks?▼

To run the Gemini CLI with a specific model, provide the desired model name and prompt input to execute the command. Output is written to a target file with safe fallbacks applied if the model alias differs.

Can I use file-based prompt input to execute the Gemini CLI in one-shot mode?▼

Yes, you can use file-based prompt input to execute the Gemini CLI in one-shot mode. The skill processes system prompts and user prompts from files to handle arbitrary prompts efficiently.

What is the best way to handle Gemini CLI output writing when model aliases differ?▼

Handling Gemini CLI output involves writing the execution results to a target file. The skill automatically provides safe fallbacks during output writing to manage discrepancies when the model alias differs.

Do I need a local Gemini CLI installation to invoke it from a different host?▼

Yes, a valid local Gemini CLI installation and configuration are required to invoke it from a different host. The skill executes the local CLI environment to process cross-model work.

How do I execute arbitrary prompts with the Gemini CLI using system and user prompt files?▼

Executing arbitrary prompts with the Gemini CLI requires specifying system and user prompt files as input. The skill passes these file-based prompts to the CLI, enabling one-shot mode for your tasks.

Related Skills

Explore More Software Engineering Skills→
BumblebiberBumblebiber
23

hmem-setup

Install and configure the hmem MCP server across system-wide or project-local scopes.

Community
Advanced
zhcndoczhcndoc

gemini

Query the Gemini CLI in one-shot mode with a natural language prompt.

Official
Intermediate
akiyoshiakiyoshi

benchmark-models

Compare the same prompt across multiple AI models for latency, cost, and quality.

Community
Advanced
annquinannquin

gemini

Run one-shot Gemini AI prompts via a command-line interface.

Community
Basic