gemini-cli-agent

Dispatch Gemini CLI sub-agents for persona-based analysis on large contexts.

5|3|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/richfrem/agent-plugins-skills --skill gemini-cli-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-cli-agent
Source: https://github.com/richfrem/agent-plugins-skills/tree/main/plugins/gemini-cli/skills/gemini-cli-agent
Command: npx skills add https://github.com/richfrem/agent-plugins-skills --skill gemini-cli-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Coordinates Gemini CLI sub-agents to perform specialized analyses on large contexts, reducing manual orchestration and enabling targeted, model-guided reviews.

Core Features & Use Cases

  • Orchestrates persona-based Gemini CLI sub-agents with consistent prompts and model guidance.
  • Enables isolated analysis for security audits, architecture reviews, QA analyses, and code refactor tasks.
  • Provides a deterministic runner and validation protocol to ensure safe piping and model selection.

Quick Start

Run the provided runner to dispatch a persona-based analysis against your target file using the Gemini CLI sub-agent.

Frequently Asked Questions about gemini-cli-agent

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

FAQPage Schema
How do I automate security audits and architecture reviews on large codebases?

Dispatch persona-based Gemini CLI sub-agents to perform focused analysis tasks on large contexts using consistent frontmatter-driven prompts and a deterministic orchestrator that pipes input and outputs to a file.

Do I need a locally installed Gemini CLI to run sub-agent analysis tasks?

Yes, a locally installed Gemini CLI is required to dispatch sub-agents for analysis, serving as the execution engine for persona-based prompts and deterministic piping.

What is the best way to orchestrate persona-based prompts for code refactoring?

Use a deterministic orchestrator to dispatch isolated Gemini CLI sub-agents with consistent persona prompts, ensuring structured evaluations for code refactoring without memory leakage.

How does deterministic orchestration prevent memory leakage during sub-agent analysis?

Deterministic orchestration prevents memory leakage by piping inputs and outputs directly to a file, ensuring isolated sub-agents maintain no state between analysis tasks.

Can I use frontmatter-driven persona prompts for QA analyses on large contexts?

Yes, you can use frontmatter-driven persona prompts to execute QA analyses on large contexts, as the Skill provides consistent model guidance and isolated sub-agents for structured evaluations.

When should I use isolated sub-agents instead of a single model for code analysis?

Use isolated sub-agents instead of a single model when performing security audits or code refactoring on large contexts, where focused persona-based prompts prevent memory leakage and provide structured evaluations.