ai-cli-gemini

Route Gemini CLI tasks through Analyze-Challenge-Gap workflows with soft triage.

Updated Apr 26, 2026
One-click install
npx skills add https://github.com/EndUser123/cc-marketplace --skill ai-cli-gemini
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-cli-gemini
Source: https://github.com/EndUser123/cc-marketplace/tree/main/plugins/cc-skills-ai-cli/skills/ai-cli-gemini
Command: npx skills add https://github.com/EndUser123/cc-marketplace --skill ai-cli-gemini

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Gemini-powered general-purpose task assistant that provides source-grounded, high-quality answers by applying an Analyze-Challenge-Gap workflow with soft orchestration, enabling safe, guided task resolution.

Core Features & Use Cases

  • Soft triage that classifies each invocation into RESEARCH, ENGINEERING, DESIGN, or RCA and routes to the appropriate workflow path
  • Route to appropriate workflow path based on triage classification, with user override support
  • Execute the selected path (ACG for RESEARCH, TDD cycle for ENGINEERING, Adversarial Review for DESIGN, or Hypothesis Ledger for RCA)
  • Verification pyramid for ENGINEERING path (Unit, Integration, E2E) to ensure robust outputs
  • Source-grounded outputs with material citations and provenance loaded into context

Quick Start

Describe your task and Gemini will triage it and route it to the appropriate workflow.

Frequently Asked Questions about ai-cli-gemini

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

FAQPage Schema
How do I get source-grounded answers for software engineering and RCA tasks?

To get source-grounded answers for software engineering and RCA tasks, use a Gemini-powered assistant that applies an Analyze-Challenge-Gap workflow. It triages invocations into RESEARCH, ENGINEERING, DESIGN, or RCA paths, loading material citations and provenance directly into context.

What is the Analyze-Challenge-Gap workflow for AI task triage?

The Analyze-Challenge-Gap workflow is a soft orchestration mechanism that classifies prompts into RESEARCH, ENGINEERING, DESIGN, or RCA categories. It routes each task to a specialized execution path like TDD cycles or Hypothesis Ledgers to ensure safe, guided resolution.

How does the Gemini CLI handle model availability and capacity errors?

The Gemini CLI handles capacity and availability errors by enforcing model-pinning strategies alongside a verification pyramid. This approach ensures robust outputs and manages error conditions effectively during task execution.

Can I override the automatic triage routing for RCA and engineering tasks?

Yes, you can override automatic triage routing for RCA and engineering tasks. The assistant supports optional user overrides, allowing you to manually choose the most appropriate workflow path instead of relying on soft routing classification.

What verification processes are used for engineering tasks in this workflow?

Engineering tasks use a verification pyramid encompassing Unit, Integration, and E2E testing levels. This ensures robust outputs by validating the software engineering components thoroughly during the TDD cycle execution.