docs(skills): complete readme setup steps

Author: Aidenwu0209

skills/README.ch.md

@@ -25,7 +25,15 @@
 
 ## 快速开始
 
+下面的示例覆盖两个 skill；只需执行你实际使用的那个 skill 对应命令。
+
 1. 安装对应 skill 的依赖。
+   ```bash
+   python -m pip install -r paddleocr-text-recognition/scripts/requirements.txt
+   python -m pip install -r paddleocr-doc-parsing/scripts/requirements.txt
+   # 第三行可选，仅在使用文档文件优化时需要
+   python -m pip install -r paddleocr-doc-parsing/scripts/requirements-optimize.txt
+   ```
 2. 使用以下任一方式配置 API 凭证。
 
    方式 A：运行要测试的 skill 对应的辅助脚本。
@@ -65,22 +73,22 @@ URL 示例：
 
 ### paddleocr-doc-parsing
 
-URL 示例：
+解析 URL 示例：
 ```text
 解析这个 PDF，并返回主体内容和全部表格（结构化输出）：https://example.com/report.pdf
 ```
 
-本地文件示例：
+解析本地文件示例：
 ```text
 解析本地文件 C:\docs\report.pdf，并返回完整结构化结果。
 ```
 
 ## 验证与排错
 
-- 缺依赖报错：重新执行对应的 `python -m pip install -r ...` 命令。
+- 缺依赖报错：重新执行对应 requirements 文件的安装命令，例如 `paddleocr-text-recognition/scripts/requirements.txt`、`paddleocr-doc-parsing/scripts/requirements.txt`，以及文档文件优化需要时的 `paddleocr-doc-parsing/scripts/requirements-optimize.txt`。
 - 配置问题：优先检查宿主应用或当前运行环境中是否已正确设置所需环境变量。
 - 对于仓库内的冒烟测试，可以重跑对应的 `configure.py`，或更新本地 `.env` 文件。
-- API 地址与 token 获取入口：<https://www.paddleocr.com>
+- 如果使用 PaddleOCR 官方 API，可参考：<https://www.paddleocr.com>
 
 ## 文档入口
 
@@ -89,7 +97,7 @@ URL 示例：
 
 ## API 获取
 
-请在 PaddleOCR 官网获取 API 信息：<https://www.paddleocr.com>
+如果使用 PaddleOCR 官方 API，可参考：<https://www.paddleocr.com>
 
 ## 许可证
 

skills/README.md

@@ -25,7 +25,15 @@ This directory contains AI agent skills for PaddleOCR official APIs.
 
 ## Quick Start
 
+The examples below cover both skills. Run only the commands for the skill you need.
+
 1. Install dependencies for the skill you use.
+   ```bash
+   python -m pip install -r paddleocr-text-recognition/scripts/requirements.txt
+   python -m pip install -r paddleocr-doc-parsing/scripts/requirements.txt
+   # Optional: required only when using document file optimization
+   python -m pip install -r paddleocr-doc-parsing/scripts/requirements-optimize.txt
+   ```
 2. Configure API credentials using one of the following options.
 
    Option A: run the helper script for the skill you want to test.
@@ -77,10 +85,10 @@ Parse local file C:\docs\report.pdf and return complete structured output.
 
 ## Verification & Troubleshooting
 
-- Missing dependencies: rerun the corresponding `python -m pip install -r ...` command.
+- Missing dependencies: rerun the dependency installation command for the relevant file, such as `paddleocr-text-recognition/scripts/requirements.txt`, `paddleocr-doc-parsing/scripts/requirements.txt`, or `paddleocr-doc-parsing/scripts/requirements-optimize.txt`.
 - Configuration issues: first check whether the required environment variables are available in the host application or runtime environment.
 - For repository-local smoke tests, you can rerun the corresponding `configure.py` script or update the local `.env` file.
-- API URL and access token source: <https://www.paddleocr.com>
+- For direct PaddleOCR API access, see: <https://www.paddleocr.com>
 
 ## Documentation
 
@@ -89,7 +97,7 @@ Parse local file C:\docs\report.pdf and return complete structured output.
 
 ## API Access
 
-Get API credentials from the PaddleOCR official website: <https://www.paddleocr.com>
+For direct PaddleOCR API access, see: <https://www.paddleocr.com>
 
 ## License