agent-platform-tuning

Fine-tune open and Gemini models using Agent Platform infrastructure.

Updated Jul 4, 2026
One-click install
npx skills add https://github.com/ssmleo/govfolio --skill agent-platform-tuning-ssmleo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-platform-tuning
Source: https://github.com/ssmleo/govfolio/tree/main/.agents/skills/agent-platform-tuning
Command: npx skills add https://github.com/ssmleo/govfolio --skill agent-platform-tuning-ssmleo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-cloud-aiplatform, numpy, pandas, datasets, smart_open[gcs], pyarrow, google-genai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of fine-tuning open and Gemini models within the Agent Platform infrastructure, enabling users to optimize model performance for specific tasks.

Core Features & Use Cases

  • Model Category Identification: Determines whether the user wants to tune an Open Model or a Gemini Model.
  • Environment Check: Ensures the foundational environment is ready before proceeding.
  • Dataset Preparation & Upload: Converts and validates datasets, ensuring they are in the correct format and ready for tuning.
  • Model Configuration & Recommendation: Helps the user choose the best model and parameters based on the dataset and task.
  • Tuning Job Execution: Submits the tuning job to the Agent Platform and monitors its progress.
  • Model Deployment: Deploys the tuned model once the job is complete.
  • Use Case: For a user looking to improve the performance of a language model for a specific task, this Skill guides them through the entire process, from setting up the environment to deploying the final model.

Quick Start

Run the agent-platform-tuning skill to start the process of fine-tuning your model.

Frequently Asked Questions about agent-platform-tuning

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

FAQPage Schema
How do I fine-tune Gemini models using Agent Platform infrastructure?

Fine-tuning Gemini models on the Agent Platform involves environment setup, dataset preparation, job execution, and deployment. This Skill guides you through the process using Python and Google Cloud Platform services.

Can I tune open models with Google Cloud AI Platform?

Yes, you can tune open models using Google Cloud AI Platform. The Skill identifies whether you are tuning an Open or Gemini model and configures the environment accordingly for the Agent Platform infrastructure.

What is the process for preparing datasets for model tuning?

Dataset preparation for model tuning requires converting and validating your data into the correct format. The Skill ensures your datasets are properly formatted and uploaded to Google Cloud Storage before executing the tuning job.

Do I need Python and Google Cloud Platform to deploy a tuned model?

Yes, Python and Google Cloud Platform are required dependencies to deploy a tuned model. The Skill uses packages like google-cloud-aiplatform and datasets to handle the environment setup and deployment process.

How does the Agent Platform handle model configuration and recommendations?

The Agent Platform handles model configuration by recommending the best model and parameters based on your specific dataset and task. It automates the model selection process before submitting the tuning job.

Why validate datasets before submitting a model tuning job?

Validating datasets before submitting a model tuning job ensures they are in the correct format required by the Agent Platform. This prevents errors during job execution and guarantees the data is ready for tuning.