agent-platform-inference
覆盖一方与三方模型与 SDK 鉴权示例，便于快速集成推理能力。
需要凭证与网络访问权限，推理请求会产生成本并可能泄露输入数据。
连接并对接 Agent Platform 上的 Gemini 与第三方 OpenMaaS 模型，提供鉴权与调用示例进行推理。
帮你接入 Google Cloud Agent Platform 上的推理模型（比如 First‑Party 的 Gemini 或 Third‑Party 的 OpenMaaS：Llama、Qwen 等）并给出鉴权与调用示例。需要把模型当成服务调用、配置 base URL、区域端点或排查 429/400/404 之类错误时会用到。它侧重写调用和鉴权示例，不负责模型部署或评测。
▸ 展开 SKILL.md 英文原文
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 you need to 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.
帮我安装这个 skill：https://raw.githubusercontent.com/google/skills/main/skills/cloud/agent-platform-inference/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/google/skills/main/skills/cloud/agent-platform-inference/SKILL.md"# Agent Platform GenAI Inference Skill
This skill provides instructions for authenticating and connecting to Google
Cloud Agent Platform to use Generative AI models. It covers:
* **First-Party publisher models** (Gemini) — section 2.
* **Third-Party publisher models** (OpenMaaS: Llama, DeepSeek, Qwen, etc.)
— section 3.
* **Custom endpoints** (any model on a numeric `projects/.../endpoints/<id>`
resource — tuned Gemini models, OSS LLMs self-deployed from Model Garden
via the `agent-platform-deploy` skill, and legacy custom models) —
section 4.
## Safety & Confirmation Tiers (CRITICAL)
Before executing any commands or scripts on behalf of the user, you must adhere
to