Data & Analysis ✓ Google · Official google-cloudagent-platformmodel-tuninggemini-modelsopen-modelsjsonlcloud-storage

Agent Platform Model Tuning

A guided end-to-end workflow for fine-tuning open or Gemini models on Google Agent Platform.

FollowSkills review · FSRS-2.0
Not recommended
44/ 100 5-point scale 2.2 / 5
Trust15 / 25 · 3.0/5

The evidence shows confirmations for project and region, dataset columns, model, hyperparameters, job submission, and deployment, plus stop conditions for inaccessible data or GCS objects. However, least-privilege IAM roles, sensitive-data handling, data-flow disclosure, deployment rollback, and an integrated cancellation/recovery path are incomplete. Authentication, API enablement, dependency installation, uploads, and deployment create external effects, so points are deducted.

Reliability5 / 20 · 1.3/5

The skill provides a staged workflow, input checks, dataset validation, a fixed split seed, and some actionable error feedback. However, referenced requirements.txt, tune_open_model.py, and tune_gemini_model.py files are absent from the supplied material; messages_gemini is inconsistent with the validator's supported formats; and a gcloud configuration command appears nonstandard. Key paths cannot be reproduced from a static read, so the score remains below the static 10-point ceiling.

Adaptability8 / 15 · 2.7/5

The intended users, Agent Platform tuning scenarios, and exclusions for non-Agent-Platform training, deployment, and endpoint management are reasonably clear. Model-category and dataset-state decision points are also specified. Trigger precision, non-fit ranges, Chinese-language support, and mainland-China reachability are underdocumented, while core dependencies include Google Cloud, Hugging Face, and overseas documentation services, so points are deducted.

Convention8 / 15 · 2.7/5

The documentation uses an overview, decision tree, phased workflow, references, installation notes, commands, limitation warnings, Apache-2.0 licensing, and support/contribution paths. It lacks explicit versioning, a changelog, named maintenance responsibility, and a clear update path. Referenced dependencies and scripts are incomplete, and format terminology is inconsistent, so points are deducted.

Effectiveness5 / 15 · 1.7/5

The skill theoretically covers environment setup, dataset conversion and validation, upload, configuration, submission, monitoring, and deployment. However, key submission scripts and the requirements file are not supplied, the Gemini path may require manual work, the cost script only handles messages-shaped data, and result validation is limited. The static ceiling is therefore 7, with additional deductions for incomplete direct usability.

Verifiability3 / 10 · 1.5/5

The supplied Markdown, Python scripts, model table, and official documentation links provide limited auditability. There are no committed tests, CI coverage, third-party execution records, or corroborating evidence types, and several capability and currency claims cannot be independently confirmed from the supplied files. The score is therefore low.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 513a7a51e85f
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • Do not perform authentication, API enablement, uploads, or deployment before verifying least-privilege IAM, data sensitivity, and the target project.
  • Confirm that requirements.txt, tuning scripts, and Gemini data-format support actually exist, and resolve inconsistencies between the scripts and documentation.
  • Core operation depends on Google Cloud, Hugging Face, and external documentation services; mainland-China reachability and enterprise proxy requirements need separate verification.
  • Add explicit rollback, cancellation, and failure-recovery procedures before deployment.
See the full review method →

What does this skill do, and when should you use it?

This skill is for fine-tuning large language models with Google Agent Platform, covering both open models and Gemini models. It starts with authentication, API, IAM, and virtual-environment setup, then handles dataset preparation, JSONL validation, GCS upload, model and hyperparameter configuration, job submission, and monitoring. It also provides deployment guidance after tuning completes. It is not intended for training outside Agent Platform, endpoint deployment, or endpoint management.

Checks and configures the gcloud CLI, project, and region; guides API enablement; and verifies relevant service agents and user permissions. It uses Python scripts to prepare, convert, and validate JSONL data, asks whether to create an 80/20 validation split when appropriate, and uploads datasets to Google Cloud Storage. It recommends models and hyperparameters from the referenced catalog and tuning guide, calculates a rough Open Model cost estimate, and submits tuning jobs only after user confirmation. It also guides job monitoring and deployment of a successfully tuned model.

  1. A machine-learning engineer wants to fine-tune an open model on Google Cloud and needs dataset validation, cost estimation, and job-submission guidance.
  2. A team wants to tune a Gemini model with Agent Platform and needs help preparing the environment, data format, and submission path.
  3. A developer has training data that is not yet valid JSONL and needs its message roles and schema checked.
  4. A Google Cloud user needs to upload prepared training data to GCS and run a tuning job.
  5. A user has a completed tuning job and needs guidance deploying the resulting model on Agent Platform.

What are this skill's strengths and limitations?

Pros
  • Covers the tuning lifecycle from environment setup through data preparation, configuration, submission, monitoring, and deployment.
  • Supports both open models and Gemini models with separate data-format guidance.
  • Includes explicit checks for dataset validity, column mapping, GCS accessibility, and user approval.
  • Provides a rough cost-calculation workflow and model-recommendation process for open models.
Limitations
  • Requires gcloud, a Python virtual environment, Google Cloud APIs, IAM permissions, and GCS; it is not a standalone tuning workflow.
  • Model recommendations depend on referenced files such as references/models.md and references/tuning_guide.md, which were not included here, so their specific catalog contents cannot be verified.
  • The source provides no test suite, performance measurements, or evidence of execution on specific platforms.
  • The Gemini submission path requires a runtime check for the script; if it is absent, the user must submit through the console or SDK.
  • It does not cover training outside Agent Platform, endpoint deployment, or endpoint management.

How do you install this skill?

This skill is distributed as part of the google/skills collection. Run: npx skills add google/skills. Select Agent Platform Model Tuning during installation; the source does not document a standalone installation command for this skill.

How do you use this skill?

In an Agent Skills-compatible client, make the model category explicit, for example: “I want to fine-tune an Open Model for customer-support responses using Agent Platform.” You should have a Google Cloud project, region, dataset, and GCS access available. The workflow requests confirmation of the project and region, column mapping, model and hyperparameters, job-submission command, and deployment command at the relevant stages.

How does this skill compare with similar options?

Its scope is distinct from the collection’s Agent Platform Model Garden Deploy Skill and Agent Platform Endpoint Management Skill: this skill handles model tuning, while those skills address endpoint deployment and endpoint management.

FAQ

Does this require Google Cloud?
Yes. The workflow uses Agent Platform infrastructure and requires gcloud, Vertex AI and Cloud Storage APIs, IAM permissions, and GCS.
What data format is required?
The dataset must be valid tuning-ready JSONL. Open models use the messages format, while Gemini models use messages_gemini. A .jsonl extension alone is not sufficient.
Will it submit a tuning job automatically?
No. The workflow requires confirmation of the model, hyperparameters, accessible GCS dataset URI, and the proposed command before submission.
Can it provide the actual tuning cost?
It can calculate a rough estimate for open-model tuning, but the source states that the estimate may differ from actual billing. No fixed price is provided.

More skills from this repository

All from google/skills

Dev & Engineering ✓ Google · Official

Gemini API Enterprise Development Guide

Helps developers build enterprise Gemini applications on Agent Platform with Google's unified Gen AI SDK.

Data & Analysis ✓ Google · Official

Agent Platform Model Registry Manager

Manage Agent Platform models, versions, and metadata from the gcloud CLI.

Dev & Engineering ✓ Google · Official

Agent Platform Tuning Manager

Inspect, list, and safely cancel Agent Platform GenAI tuning jobs.

Automation & Ops ✓ Google · Official

Agent Platform Model Deployment Assistant

Deploy, verify, and clean up Model Garden models on Google Agent Platform.

Dev & Engineering ✓ Google · Official

Gemini Enterprise Skill Registry

Search, manage, monitor, and scaffold skills for the Gemini Enterprise Agent Platform.

Dev & Engineering ✓ Google · Official

Gemini Enterprise Managed Agents

Manage stateful Gemini Enterprise agents through the Managed Agents API.

Automation & Ops ✓ Google · Official

Agent Platform Endpoint Management

Manage Agent Platform serving endpoints and troubleshoot common endpoint failures.

Dev & Engineering ✓ Google · Official

Agent Platform Prompt Manager

Manage Agent Platform managed prompts with Python SDK guidance.

Data & Analysis ✓ Google · Official

Google Cloud Data Lineage Summary

Summarize BigQuery and GCS lineage to debug data quality and provenance.

Automation & Ops ✓ Google · Official

Gemini AI Studio to Agent Platform Migration

Guides Gemini API applications from Google AI Studio to Google Cloud Agent Platform.

Automation & Ops ✓ Google · Official

Google Cloud AI Agent Builder

Design, implement, deploy, and validate AI agents and multi-agent systems on Google Cloud.

Data & Analysis ✓ Google · Official

Google Cloud Agent Evaluation Flywheel

Improve model and agent quality through structured evaluation, failure analysis, and iteration.

Dev & Engineering ✓ Google · Official

Google Cloud Agent Platform Inference Assistant

Guides developers in connecting to Google Cloud Agent Platform and calling Gemini or OpenMaaS models.

Dev & Engineering ✓ Google · Official

Google Agents CLI Agent Development Guide

Guides agents from specification through development, deployment, and monitoring.

Automation & Ops ✓ Google · Official

Google Cloud Storage Basics

Manage GCS buckets and objects while configuring access, protection, lifecycle, cost, and performance.

Automation & Ops ✓ Google · Official

Google Cloud Live Multimodal Streaming Architect

Design and deploy Google Cloud solutions for live, bidirectional multimodal streams.

Dev & Engineering ✓ Google · Official

Gemini LiveAPI Client Service Skill

Generate a resumable, multimodal, bidirectional Gemini LiveAPI client over WebSockets.

Dev & Engineering ✓ Google · Official

Gemini Interactions API Guide

Build stateful, multi-turn Gemini interactions on Google Agent Platform.

Automation & Ops ✓ Google · Official

Google Cloud Authentication Guide

Choose secure Google Cloud authentication and authorization for local, production, and cross-cloud workloads.

Automation & Ops ✓ Google · Official

Google Cloud Solution Architect

Plan, validate, and package end-to-end architectures for complex multi-product Google Cloud workloads.

Related skills