diff --git a/README.md b/README.md
index 4c59055..87ef164 100644
--- a/README.md
+++ b/README.md
@@ -27,35 +27,45 @@ Inspired by [this reading workflow demo](https://www.bilibili.com/video/BV1FxoGB
## Quick Start
-### Install
+### Step 1: Install the Plugin
-**Manual** — Download `main.js`, `manifest.json`, and `styles.css` from the [latest release](https://github.com/fancive/obsidian-parallel-reader/releases), place them in `.obsidian/plugins/parallel-reader/`, and enable the plugin in Obsidian settings.
+1. Go to the [Releases page](https://github.com/fancive/obsidian-parallel-reader/releases) and download three files from the latest release: **main.js**, **manifest.json**, **styles.css**
+2. Open your vault folder, navigate to `.obsidian/plugins/` (create it if it doesn't exist), and create a new folder called `parallel-reader`
+3. Put the three downloaded files into that folder
+4. Open Obsidian → **Settings** → **Community plugins** → find **Parallel Reader** → toggle it **on**
-### Configure a Provider
+> **Tip**: Can't see the `.obsidian` folder? On macOS press `Cmd+Shift+.` in Finder; on Windows enable "Show hidden files" in File Explorer.
-Open plugin settings, pick a provider preset, enter your API key and model ID. Done.
+### Step 2: Set Up Your AI Provider
-| Provider | Format | Notes |
-|----------|--------|-------|
-| Anthropic | `anthropic-messages` | Default, recommended |
-| OpenAI | `openai-chat` | Chat Completions |
-| Google Gemini | `google-generative-ai` | generateContent |
-| OpenRouter / Groq / DeepSeek / Moonshot / ... | `openai-chat` | OpenAI-compatible |
-| Ollama / LM Studio | `openai-chat` | Local, no API key needed |
-| Custom endpoint | Any | Just fill in Base URL |
+1. In Obsidian, go to **Settings** → **Parallel Reader**
+2. Choose a **Provider preset** (e.g. Anthropic, OpenAI, DeepSeek, etc.)
+3. Paste your **API Key**
+4. (Optional) Change the **Model** if you prefer a different one
+5. Click **Test** to verify the connection
-Model IDs support `provider/model` notation (e.g. `anthropic/claude-sonnet-4-6`) — the matching prefix is stripped automatically.
+That's it! Open any note and run the command **"Parallel Reader: Generate"** from the command palette (`Cmd/Ctrl+P`).
-### CLI Backends (Optional)
+
+Supported providers
-Switch backend to **Claude Code CLI** or **Codex CLI** to use your local CLI installation.
+| Provider | Notes |
+|----------|-------|
+| **Anthropic** | Default, recommended |
+| **OpenAI** | GPT models |
+| **Google Gemini** | Gemini models |
+| **OpenRouter / Groq / DeepSeek / Moonshot / ...** | OpenAI-compatible |
+| **Ollama / LM Studio** | Local models, no API key needed |
+| **Custom endpoint** | Any OpenAI or Anthropic compatible API |
-Since Obsidian's GUI doesn't inherit your shell `PATH`, enter the absolute CLI path in settings:
+
-```bash
-which claude # Claude Code
-which codex # Codex
-```
+
+CLI backends (advanced)
+
+If you have **Claude Code** or **Codex** installed locally, you can use them as backends instead of API keys. Switch the backend in settings and enter the CLI path. The plugin auto-detects common install locations, but Obsidian's GUI may not find it — in that case, paste the full path (run `which claude` or `which codex` in your terminal to find it).
+
+
## Usage
diff --git a/README.zh-CN.md b/README.zh-CN.md
index a61a1b2..465a28f 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -27,35 +27,45 @@ Obsidian 对照阅读插件 — 左边原文、右边 AI 摘要卡片，滚动
## 快速开始
-### 安装
+### 第一步：安装插件
-**手动安装** — 从 [最新 Release](https://github.com/fancive/obsidian-parallel-reader/releases) 下载 `main.js`、`manifest.json`、`styles.css`，放入 `.obsidian/plugins/parallel-reader/`，然后在 Obsidian 设置中启用。
+1. 打开 [Release 页面](https://github.com/fancive/obsidian-parallel-reader/releases)，下载最新版的三个文件：**main.js**、**manifest.json**、**styles.css**
+2. 打开你的 Vault 文件夹，进入 `.obsidian/plugins/`（没有就新建），再创建一个叫 `parallel-reader` 的文件夹
+3. 把下载的三个文件放进去
+4. 打开 Obsidian → **设置** → **第三方插件** → 找到 **Parallel Reader** → 打开开关
-### 配置 Provider
+> **找不到 `.obsidian` 文件夹？** macOS 在 Finder 里按 `Cmd+Shift+.` 显示隐藏文件；Windows 在文件资源管理器里勾选「显示隐藏的项目」。
-打开插件设置，选择 Provider preset，填入 API Key 和模型 ID 即可。
+### 第二步：配置 AI 服务
-| Provider | 格式 | 说明 |
-|----------|------|------|
-| Anthropic | `anthropic-messages` | 默认，推荐 |
-| OpenAI | `openai-chat` | Chat Completions |
-| Google Gemini | `google-generative-ai` | generateContent |
-| OpenRouter / Groq / DeepSeek / Moonshot 等 | `openai-chat` | OpenAI 兼容格式 |
-| Ollama / LM Studio | `openai-chat` | 本地模型，无需 API Key |
-| 自定义端点 | 任意 | 填写 Base URL 即可 |
+1. 在 Obsidian 中打开 **设置** → **Parallel Reader**
+2. 选择一个 **Provider**（比如 Anthropic、OpenAI、DeepSeek 等）
+3. 粘贴你的 **API Key**
+4. （可选）修改 **模型**
+5. 点击 **Test** 验证连接
-Model ID 支持 `provider/model` 写法（如 `anthropic/claude-sonnet-4-6`），匹配当前 preset 时自动剥离前缀。
+搞定！打开任意笔记，按 `Cmd/Ctrl+P` 调出命令面板，运行 **「Parallel Reader: 为当前笔记生成对照笔记」** 即可。
-### CLI 模式（可选）
+
+支持的 Provider 一览
-切换后端为 **Claude Code CLI** 或 **Codex CLI**，通过本地 CLI 调用 LLM。
+| Provider | 说明 |
+|----------|------|
+| **Anthropic** | 默认推荐 |
+| **OpenAI** | GPT 系列 |
+| **Google Gemini** | Gemini 系列 |
+| **OpenRouter / Groq / DeepSeek / Moonshot 等** | OpenAI 兼容格式 |
+| **Ollama / LM Studio** | 本地模型，无需 API Key |
+| **自定义端点** | 任何 OpenAI 或 Anthropic 兼容的 API |
-Obsidian GUI 不继承 shell `PATH`，需要在设置中填写绝对路径：
+
-```bash
-which claude # Claude Code
-which codex # Codex
-```
+
+CLI 模式（进阶）
+
+如果你本地装了 **Claude Code** 或 **Codex**，可以在设置里切换后端直接使用。插件会自动探测常见安装位置，如果找不到，在终端运行 `which claude` 或 `which codex` 获取完整路径，粘贴到设置里即可。
+
+
## 使用