gemini-guide

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Gemini Guide

Gemini 指南

Look up Gemini API documentation and SDK patterns when building with Google Gemini. This skill brings Gemini docs TO Claude — it does not call Gemini.

Skill	Direction	Tool
gemini-guide (this)	Gemini docs -> Claude	Local docs, WebFetch
gemini-peer-review	Code -> Gemini	gemini-coach CLI

在使用Google Gemini进行开发时，查阅Gemini API文档和SDK模式。该技能将Gemini文档集成到Claude中——它不会调用Gemini。

技能	方向	工具
gemini-guide（本技能）	Gemini 文档 -> Claude	本地文档、WebFetch
gemini-peer-review	代码 -> Gemini	gemini-coach CLI

Documentation Sources

文档来源

Check in this priority order:

Priority	Source	Best For
1	Local cached docs ( `~/Documents/google-gemini-context/` )	Most topics — 24 JS, 24 Python, 7 common topics
2	GitHub codegen_instructions	Always-current SDK patterns — fetch `https://raw.githubusercontent.com/googleapis/js-genai/refs/heads/main/codegen_instructions.md`
3	Google AI docs via WebFetch	When local docs don't cover it — `https://ai.google.dev/gemini-api/docs/{topic}`

按以下优先级顺序查阅：

优先级	来源	适用场景
1	本地缓存文档（ `~/Documents/google-gemini-context/` ）	大多数主题——包含24个JavaScript主题、24个Python主题、7个通用主题
2	GitHub codegen_instructions	实时更新的SDK模式——获取 `https://raw.githubusercontent.com/googleapis/js-genai/refs/heads/main/codegen_instructions.md`
3	通过WebFetch获取Google AI文档	本地文档未覆盖的内容—— `https://ai.google.dev/gemini-api/docs/{topic}`

Lookup Workflow

查阅流程

When the user asks about a Gemini topic:

Check corrections first: Read references/deprecated-patterns.md — know what NOT to suggest before writing any code
Map the query to a topic: Read references/topic-index.md to find the right local doc file

Read the local doc: The file path will be

~/Documents/google-gemini-context/{path from topic index}

If local doc seems stale: Fetch the GitHub codegen_instructions.md for latest SDK patterns
Synthesise: Combine the documentation into a clear answer with working code examples. Always use the CORRECT patterns from step 1.

当用户询问Gemini相关主题时：

先检查修正内容：阅读references/deprecated-patterns.md——在编写任何代码前，先了解哪些内容是不应该推荐的
将查询映射到对应主题：阅读references/topic-index.md以找到正确的本地文档文件

读取本地文档：文件路径为

~/Documents/google-gemini-context/{主题索引中的路径}

若本地文档过时：获取GitHub上的codegen_instructions.md以获取最新的SDK模式
整合内容：将文档内容整合成清晰的答案，并附上可运行的代码示例。务必遵循步骤1中的正确模式。

Quick Corrections

快速修正

These are the most common mistakes. Apply these even without reading the full references:

Claude Might Suggest	Correct
`@google/generative-ai`	`@google/genai`
`google-generativeai` (Python)	`google-genai`
`GoogleGenerativeAI`	`GoogleGenAI`
`genAI.getGenerativeModel()`	`ai.models.generateContent()`
`model.startChat()` / `chat.sendMessage()`	`ai.chats.create()` / `chat.send()`
`generationConfig`	`config`
`stream=True` (method param)	`config={"stream": True}`
`gemini-pro`	`gemini-2.5-flash`
`gemini-pro-vision`	`gemini-2.5-flash` (unified multimodal)
4 safety categories	5 categories (include `HARM_CATEGORY_CIVIC_INTEGRITY` )
`HARM_CATEGORY_DANGEROUS_CONTENT`	`HARM_CATEGORY_DANGEROUS` (no `_CONTENT` )
`X-Goog-Api-Key` (capitalised)	`x-goog-api-key` (lowercase)
Daily rate limits	No daily limits — only per-minute (RPM, TPM)

以下是最常见的错误。即使未阅读完整参考内容，也应遵循这些修正规则：

Claude可能建议的写法	正确写法
`@google/generative-ai`	`@google/genai`
`google-generativeai` （Python）	`google-genai`
`GoogleGenerativeAI`	`GoogleGenAI`
`genAI.getGenerativeModel()`	`ai.models.generateContent()`
`model.startChat()` / `chat.sendMessage()`	`ai.chats.create()` / `chat.send()`
`generationConfig`	`config`
`stream=True` （方法参数）	`config={"stream": True}`
`gemini-pro`	`gemini-2.5-flash`
`gemini-pro-vision`	`gemini-2.5-flash` （统一多模态模型）
4个安全类别	5个类别（包含 `HARM_CATEGORY_CIVIC_INTEGRITY` ）
`HARM_CATEGORY_DANGEROUS_CONTENT`	`HARM_CATEGORY_DANGEROUS` （无 `_CONTENT` 后缀）
`X-Goog-Api-Key` （大写）	`x-goog-api-key` （小写）
每日调用限制	无每日限制——仅存在每分钟调用限制（RPM，TPM）

Correct Initialisation (JS)

正确初始化方式（JS）

javascript

import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});  // auto-reads GEMINI_API_KEY env var
const response = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: "Your prompt"
});

javascript

import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});  // 自动读取GEMINI_API_KEY环境变量
const response = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: "Your prompt"
});

Correct Initialisation (Python)

正确初始化方式（Python）

python

from google import genai
client = genai.Client()  # auto-reads GEMINI_API_KEY env var
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Your prompt"
)

python

from google import genai
client = genai.Client()  # 自动读取GEMINI_API_KEY环境变量
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Your prompt"
)

Local Docs Structure

本地文档结构

All at

~/Documents/google-gemini-context/

Directory	Contents
`javascript/`	24 topic files — quickstart, function-calling, streaming, structured-output, etc.
`python/`	24 topic files — same topics as JavaScript
`common/`	7 cross-language files — safety, pricing, rate-limits, errors, auth, regions, openai-compat
`rest-api/`	REST endpoint docs
`MODELS.md`	Current model IDs, capabilities, token limits, rate limits
`CLAUDE.md`	Full correction reference (source for deprecated-patterns.md)
`googlegenai-gemini-api.md`	Comprehensive SDK guide (608 lines, JS + Python)
`INDEX.md`	Keyword index mapping topics to files

所有文档均位于

~/Documents/google-gemini-context/

：

目录	内容
`javascript/`	24个主题文件——快速入门、函数调用、流式传输、结构化输出等
`python/`	24个主题文件——与JavaScript主题一致
`common/`	7个跨语言文件——安全、定价、调用限制、错误处理、认证、区域、OpenAI兼容
`rest-api/`	REST端点文档
`MODELS.md`	当前模型ID、功能、令牌限制、调用限制
`CLAUDE.md`	完整修正参考（deprecated-patterns.md的数据源）
`googlegenai-gemini-api.md`	全面的SDK指南（608行，包含JS和Python）
`INDEX.md`	关键词索引，将主题映射到对应文件

Current Models

当前可用模型

Model	ID	Best For
Gemini 2.5 Pro	`gemini-2.5-pro`	Complex reasoning, advanced coding
Gemini 2.5 Flash	`gemini-2.5-flash`	Most tasks (recommended default)
Gemini 2.5 Flash-Lite	`gemini-2.5-flash-lite-preview-06-17`	Budget, low latency
Gemini 2.0 Flash	`gemini-2.0-flash`	Fast inference
Text Embedding	`text-embedding-004`	Semantic search, RAG (768 dims)

For full model details including token limits and rate limits, read

~/Documents/google-gemini-context/MODELS.md

模型	ID	适用场景
Gemini 2.5 Pro	`gemini-2.5-pro`	复杂推理、高级编码
Gemini 2.5 Flash	`gemini-2.5-flash`	大多数任务（推荐默认使用）
Gemini 2.5 Flash-Lite	`gemini-2.5-flash-lite-preview-06-17`	低成本、低延迟
Gemini 2.0 Flash	`gemini-2.0-flash`	快速推理
Text Embedding	`text-embedding-004`	语义搜索、RAG（768维度）

如需了解完整的模型详情，包括令牌限制和调用限制，请阅读

~/Documents/google-gemini-context/MODELS.md

。

Maintenance

维护说明

The local docs at

~/Documents/google-gemini-context/

were curated in January 2025. When information seems wrong or outdated:

Check the GitHub codegen_instructions.md (always current)

Verify model IDs against

https://ai.google.dev/gemini-api/docs/models

Flag stale docs to the user

本地文档

~/Documents/google-gemini-context/

整理于2025年1月。当信息看起来错误或过时：

检查GitHub上的codegen_instructions.md（始终为最新内容）

对照

https://ai.google.dev/gemini-api/docs/models

验证模型ID

向用户标记过时文档

Reference Files

参考文件

When	Read
Mapping a query to a documentation file	references/topic-index.md
Checking for deprecated patterns before writing code	references/deprecated-patterns.md

场景	查阅文件
将查询映射到对应文档文件	references/topic-index.md
在编写代码前检查已弃用模式	references/deprecated-patterns.md