Overview
What It Does
Agent Platform Inference packages a focused communication workflow for an AI agent. Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to perform inference, ask a model a question, run a test prompt, execute chat completions, or generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent Platform SDK, configure base URLs and global/regional endpoints, or troubleshoot 429 Resource Exhausted (DSQ), 400 User Validation, or 404 Not Found errors. Don't use for deploying models to endpoints or for running model evaluations. It is best suited to users who can review the resulting actions and provide only the accounts, files, or command access needed for the task. It is not a substitute for human approval on destructive, financial, security-sensitive, or public-facing actions.
Task ideas
Popular Use Cases
- Draft and organize messages
- Work with communication channels and contacts
- Summarize conversations into next steps
- Automate routine coordination
Installation
Install this Agent Skill
Claude Code
npx skills add https://github.com/google/skills --skill agent-platform-inferenceDeepSeek Harness
npx -y @deepseek-ai/dsh plugin --profile web add github:google/skillsCommands derived from the public GitHub SKILL.md record. Checked 2026-09-02. Review the source before running them.
Before you start
Requirements
| DeepSeek Harness | Required / review |
| Claude Code | Required / review |
| Public SKILL.md source | Required / review |
| Review instructions and requested permissions before installation | Required / review |
| Paid service | Check source |
| Supported system | Check source |
Popularity context
Why It’s Popular
Agent Platform Inference is a verified Agent Skill from google with a public SKILL.md, compatible with DeepSeek Harness, Claude Code, Codex, Gemini CLI.
Alternatives
