gemini-flow

🥈Silver

Gemini-Flow automates AI development workflows. It enables operations teams to build and deploy AI agents. It connects to Google's Gemini CLI and supports multi-agent systems. It is ideal for devops and software engineering teams.

380690Updated Today

Intermediate30min to implementautomation

Saves ~240 min per use

Quick InstallView Source

git clone https://github.com/clduab11/gemini-flow.git

Works with:

Claude

Overview

About This Skill

https://github.com/clduab11/gemini-flow/wiki

How to Use

["1. Install the Gemini CLI and authenticate with your Google Cloud account.","2. Create a new directory for your workflow and initialize it with `gemini-flow init`.","3. Define your agents in the workflow YAML file, specifying their types and configurations.","4. Test your workflow locally using `gemini-flow test` to ensure all components work as expected.","5. Deploy your workflow with `gemini-flow deploy` and monitor its performance in the Gemini console."]

Use Cases

Automate the generation of corporate training videos using Google's Veo3 service.

Create high-resolution images for marketing campaigns with Imagen4 in batch processing.

Implement OAuth 2.0 authentication in applications using the autonomous coding capabilities of Jules Tools.

Spawn intelligent agent swarms to handle large-scale data processing tasks efficiently.

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/clduab11/gemini-flow

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Create a Gemini-Flow workflow to automate [SPECIFIC AI TASK] for our team. The workflow should integrate with [SPECIFIC TOOLS] and handle [SPECIFIC DATA INPUTS]. Include error handling for [COMMON ISSUES] and deploy it to our [DEPLOYMENT ENVIRONMENT].

Example Output

Here's a Gemini-Flow workflow for automating customer support ticket classification:

```yaml
name: support_ticket_classification
agents:
  - name: ticket_receiver
    type: api
    config:
      endpoint: "https://api.support.example.com/tickets"
      auth:
        type: bearer
        token: "${env.SUPPORT_API_TOKEN}"
  - name: ticket_classifier
    type: llm
    config:
      model: "gemini-pro"
      prompt:
        "Classify the following support ticket into one of these categories: [Billing, Technical, Account, General]. Provide only the category name as output."
  - name: ticket_router
    type: workflow
    config:
      routes:
        - category: Billing
          action: "create_jira_issue"
          params:
            project: "Billing"
            type: "Task"
        - category: Technical
          action: "create_jira_issue"
          params:
            project: "Engineering"
            type: "Bug"
        - category: Account
          action: "create_jira_issue"
          params:
            project: "Customer Success"
            type: "Task"
        - category: General
          action: "create_slack_message"
          params:
            channel: "#support-team"
            message: "New general support ticket received"

triggers:
  - type: cron
    schedule: "0 * * * *"
    agent: ticket_receiver

```

This workflow will run every hour, fetch new support tickets, classify them using Gemini Pro, and route them to the appropriate team or system.