← Back to Skills Marketplace
zhangifonly

Gemini Guide

by zhangifonly · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
148
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install gemini-guide
Description
Google Gemini API 开发助手,精通 Gemini Pro/Flash、多模态、函数调用、上下文缓存
README (SKILL.md)

Gemini API - Google AI 模型接入指南

简介

Gemini 是 Google 的多模态大模型,通过 AI Studio 或 Vertex AI 提供 API。 核心优势:超长上下文(最高 200 万 token)和原生多模态(文本/图片/视频/音频)。

模型矩阵

模型 上下文窗口 特点 适用场景
gemini-2.5-pro 100 万 最强推理,思维链 复杂分析、代码生成
gemini-2.0-flash 100 万 速度快,性价比高 日常对话、批量处理
gemini-2.0-flash-lite 100 万 最快最便宜 简单任务、高并发
gemini-1.5-pro 200 万 超长上下文 长文档分析、代码库理解

SDK 安装与基础调用

pip install google-genai   # 官方 SDK
from google import genai
client = genai.Client(api_key="YOUR_API_KEY")
response = client.models.generate_content(
    model="gemini-2.0-flash",
    contents="用 Python 实现一个快速排序算法"
)
print(response.text)

多模态能力

from google.genai import types
import pathlib
# 图片理解
image = types.Part.from_bytes(data=pathlib.Path("photo.jpg").read_bytes(), mime_type="image/jpeg")
response = client.models.generate_content(model="gemini-2.0-flash", contents=["描述图片内容", image])
# 视频理解(直接上传文件)
video_file = client.files.upload(file="video.mp4")
response = client.models.generate_content(model="gemini-2.0-flash", contents=["总结视频内容", video_file])
# 音频理解
audio_file = client.files.upload(file="audio.mp3")
response = client.models.generate_content(model="gemini-2.0-flash", contents=["转录并翻译", audio_file])

函数调用与 JSON 模式

# 函数调用
get_weather = types.FunctionDeclaration(
    name="get_weather", description="获取城市天气",
    parameters=types.Schema(type="OBJECT",
        properties={"city": types.Schema(type="STRING", description="城市名")},
        required=["city"]))
tool = types.Tool(function_declarations=[get_weather])
response = client.models.generate_content(
    model="gemini-2.0-flash", contents="北京天气?",
    config=types.GenerateContentConfig(tools=[tool]))
# JSON 模式
response = client.models.generate_content(
    model="gemini-2.0-flash", contents="列出 3 种编程语言",
    config=types.GenerateContentConfig(response_mime_type="application/json"))

上下文缓存(Context Caching)

反复查询同一大文档时可大幅降低成本:

cache = client.caches.create(model="gemini-2.0-flash", contents=[large_document],
    config=types.CreateCachedContentConfig(display_name="my-cache", ttl="3600s"))
response = client.models.generate_content(model="gemini-2.0-flash", contents="第三章讲了什么?",
    config=types.GenerateContentConfig(cached_content=cache.name))

定价对比(每百万 token)

模型 输入价格 输出价格
Gemini 2.0 Flash $0.10 $0.40
Gemini 2.5 Pro $1.25 $10.00
Claude Sonnet 4 $3.00 $15.00
GPT-4o $2.50 $10.00

与 OpenAI/Claude API 的差异

特性 Gemini API OpenAI API Claude API
最大上下文 200 万 token 12.8 万 20 万
原生多模态 文本/图片/视频/音频 文本/图片/音频 文本/图片
免费额度 有(AI Studio)
上下文缓存 原生支持 Prompt Caching
SDK 风格 自有 + OpenAI 兼容 自有 自有

最佳实践

  • 默认用 gemini-2.0-flash,性价比最高
  • 长文档用上下文缓存,节省 75%+ 成本
  • 视频/音频理解是 Gemini 独特优势
  • API Key: https://aistudio.google.com/apikey
Usage Guidance
This skill is an example-driven guide for using Google Gemini via the google-genai Python SDK and appears coherent. Before using it: 1) Only supply your Google API key to trusted, official SDKs and endpoints; never paste keys into public chat. 2) Confirm the package 'google-genai' is the official release on PyPI and install it in an isolated environment. 3) Be mindful of costs when using high-context models or uploading large media; restrict API key permissions and set quotas in your Google account. 4) If you run the example code, ensure local files referenced (photo.jpg, video.mp4) are files you intend to upload. These checks will reduce accidental exposure or unintended charges.
Capability Analysis
Type: OpenClaw Skill Name: gemini-guide Version: 1.0.0 The skill bundle is a legitimate technical guide for using the Google Gemini API. It contains standard documentation, pricing comparisons, and code snippets for the official 'google-genai' SDK. There are no signs of malicious execution, data exfiltration, or prompt injection attacks in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
Name/description match the SKILL.md content: a developer guide for Google Gemini (models, SDK usage, multimodal examples, caching). Nothing requested (no env vars, no binaries) is disproportionate to that purpose.
Instruction Scope
Runtime instructions are example code snippets for the official google-genai SDK, covering model calls, multimodal uploads, function-calling, and caching. Examples reference local files (photo.jpg, video.mp4) and an API key placeholder — all expected for this type of guide. The instructions do not direct the agent to read unrelated system files, access unrelated secrets, or POST data to unexpected endpoints.
Install Mechanism
No install spec or code files are present; the SKILL.md only suggests installing the official 'google-genai' Python package via pip, which is appropriate and low-risk for a usage guide.
Credentials
The document mentions an API key in examples (api_key="YOUR_API_KEY") but the skill declares no required env vars or credentials. Requesting a Google AI API key is appropriate for the guide's purpose and there are no unrelated credential requests.
Persistence & Privilege
Skill is instruction-only, no install, does not request persistent presence or system-level changes. Platform flags (always: false, agent invocation allowed) are standard and consistent with a normal skill.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install gemini-guide
  3. After installation, invoke the skill by name or use /gemini-guide
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Gemini Guide 1.0.0 – 首发版 - 提供 Google Gemini API 接入与开发完整中文指南。 - 详细介绍 Gemini Pro/Flash、多模态、函数调用、上下文缓存等核心特性及用法。 - 涵盖主要模型对比、SDK 快速上手、多模态代码样例与价格对比。 - 总结与 OpenAI/Claude API 的差异与最佳实践建议。 - 适合 AI 应用开发者快速了解和上手 Gemini API。
Metadata
Slug gemini-guide
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Gemini Guide?

Google Gemini API 开发助手,精通 Gemini Pro/Flash、多模态、函数调用、上下文缓存. It is an AI Agent Skill for Claude Code / OpenClaw, with 148 downloads so far.

How do I install Gemini Guide?

Run "/install gemini-guide" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Gemini Guide free?

Yes, Gemini Guide is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Gemini Guide support?

Gemini Guide is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Gemini Guide?

It is built and maintained by zhangifonly (@zhangifonly); the current version is v1.0.0.

💬 Comments