Enhance skills (#17801)

* Upgrade skills readme

* Enhance skill

* Update description

Author: Bobholamovic

skills/README.md

@@ -88,25 +88,23 @@ Below are configuration methods for some AI apps:
       "entries": {
         "paddleocr-text-recognition": {
           "enabled": true,
-          "apiKey": "<ACCESS_TOKEN>",
           "env": {
-            "PADDLEOCR_OCR_API_URL": "<OCR_API_URL>"
+            "PADDLEOCR_OCR_API_URL": "<OCR_API_URL>",
+            "PADDLEOCR_ACCESS_TOKEN": "<ACCESS_TOKEN>"
           }
         },
         "paddleocr-doc-parsing": {
           "enabled": true,
-          "apiKey": "<ACCESS_TOKEN>",
           "env": {
-            "PADDLEOCR_DOC_PARSING_API_URL": "<DOC_PARSING_API_URL>"
+            "PADDLEOCR_DOC_PARSING_API_URL": "<DOC_PARSING_API_URL>",
+            "PADDLEOCR_ACCESS_TOKEN": "<ACCESS_TOKEN>"
           }
         }
       }
     }
   }
   ```
 
-  Please note that this approach may store the access token in plain text in the configuration file. A more secure way is to configure it through the OpenClaw onboarding wizard or the dashboard.
-
 ### Usage Examples
 
 After configuration, describe the OCR or document parsing task in natural language and provide a file URL or local path so the AI app can invoke the corresponding skill.
@@ -158,7 +156,7 @@ Make sure your working directory is the directory containing this file.
 
 2. Configure environment variables (see [Configure Environment Variables](#configure-environment-variables) for the list of variables). Choose one of the following methods:
 
-   **Option A**: run the interactive configuration script.
+   **Option A**: run the configuration script.
 
    ```shell
    python paddleocr-text-recognition/scripts/configure.py

skills/README_cn.md

@@ -72,10 +72,10 @@ git clone https://github.com/PaddlePaddle/PaddleOCR.git
 
   ```json
   {
-    “env”: {
-      “PADDLEOCR_ACCESS_TOKEN”: “<ACCESS_TOKEN>”,
-      “PADDLEOCR_OCR_API_URL”: “<OCR_API_URL>”,
-      “PADDLEOCR_DOC_PARSING_API_URL”: “<DOC_PARSING_API_URL>”
+    "env": {
+      "PADDLEOCR_ACCESS_TOKEN": "<ACCESS_TOKEN>",
+      "PADDLEOCR_OCR_API_URL": "<OCR_API_URL>",
+      "PADDLEOCR_DOC_PARSING_API_URL": "<DOC_PARSING_API_URL>"
     }
   }
   ```
@@ -84,29 +84,27 @@ git clone https://github.com/PaddlePaddle/PaddleOCR.git
 
   ```json
   {
-    “skills”: {
-      “entries”: {
-        “paddleocr-text-recognition”: {
-          “enabled”: true,
-          “apiKey”: “<ACCESS_TOKEN>”,
-          “env”: {
-            “PADDLEOCR_OCR_API_URL”: “<OCR_API_URL>”
+    "skills": {
+      "entries": {
+        "paddleocr-text-recognition": {
+          "enabled": true,
+          "env": {
+            "PADDLEOCR_OCR_API_URL": "<OCR_API_URL>",
+            "PADDLEOCR_ACCESS_TOKEN": "<ACCESS_TOKEN>"
           }
         },
-        “paddleocr-doc-parsing”: {
-          “enabled”: true,
-          “apiKey”: “<ACCESS_TOKEN>”,
-          “env”: {
-            “PADDLEOCR_DOC_PARSING_API_URL”: “<DOC_PARSING_API_URL>”
+        "paddleocr-doc-parsing": {
+          "enabled": true,
+          "env": {
+            "PADDLEOCR_DOC_PARSING_API_URL": "<DOC_PARSING_API_URL>",
+            "PADDLEOCR_ACCESS_TOKEN": "<ACCESS_TOKEN>"
           }
         }
       }
     }
   }
   ```
 
-  请注意这种方式可能在配置文件中明文存储 access token。更安全的方式是通过 OpenClaw onboarding wizard 或者 dashboard 配置。
-
 ### 使用示例
 
 配置完成后，可以直接用自然语言描述 OCR 或文档解析需求，并附上文件 URL 或本地路径，让 AI 应用调用对应 skill。以下是部分提示词示例：
@@ -158,7 +156,7 @@ git clone https://github.com/PaddlePaddle/PaddleOCR.git
 
 2. 配置环境变量（需要配置的变量参见[配置环境变量](#配置环境变量)一节），可选择以下任一方式：
 
-   **方式 A**：运行交互式配置脚本。
+   **方式 A**：运行配置脚本。
 
    ```shell
    python paddleocr-text-recognition/scripts/configure.py

skills/paddleocr-doc-parsing/SKILL.md

@@ -1,9 +1,6 @@
 ---
 name: paddleocr-doc-parsing
-description: >
-  Advanced document parsing with PaddleOCR. Returns complete document
-  structure including text, tables, formulas, charts, and layout information. The AI agent extracts
-  relevant content based on user needs.
+description: Complex document parsing with PaddleOCR. Intelligently converts complex PDFs and document images into Markdown and JSON files that preserve the original structure.
 metadata:
   openclaw:
     requires:
@@ -198,11 +195,13 @@ Then return:
 
 ### First-Time Configuration
 
+You can generally assume that the required environment variables have already been configured. Only when a parsing task fails should you analyze the error message to determine whether it is caused by a configuration issue. If it is indeed a configuration problem, you should notify the user to fix it.
+
 **When API is not configured**:
 
 The error will show:
 ```
-PADDLEOCR_DOC_PARSING_API_URL not configured. Get your API at: https://paddleocr.com
+CONFIG_ERROR: PADDLEOCR_DOC_PARSING_API_URL not configured. Get your API at: https://paddleocr.com
 ```
 
 **Configuration workflow**:
@@ -217,29 +216,25 @@ PADDLEOCR_DOC_PARSING_API_URL not configured. Get your API at: https://paddleocr
      - PADDLEOCR_ACCESS_TOKEN
      - Optional: PADDLEOCR_DOC_PARSING_TIMEOUT
      ```
+   - For security reasons, do not run `configure.py` or create a local `.env` file by default if the skill is installed under a host application directory (for example, `~/.claude/skills`). You should also advise the user not to do this.
 
-3. **If the user provides credentials in chat anyway** (accept any reasonable format):
+3. **If the user provides credentials in chat anyway** (accept any reasonable format), for example:
    - `PADDLEOCR_DOC_PARSING_API_URL=https://xxx.paddleocr.com/layout-parsing, PADDLEOCR_ACCESS_TOKEN=abc123...`
    - `Here's my API: https://xxx and token: abc123`
    - Copy-pasted code format
    - Any other reasonable format
    - **Security note**: Warn the user that credentials shared in chat may be stored in conversation history. Recommend setting them through the host application's configuration instead when possible.
 
-4. **Parse and validate the values**:
+   Then parse and validate the values:
    - Extract `PADDLEOCR_DOC_PARSING_API_URL` (look for URLs with `paddleocr.com` or similar)
    - Confirm `PADDLEOCR_DOC_PARSING_API_URL` is a full endpoint ending with `/layout-parsing`
    - Extract `PADDLEOCR_ACCESS_TOKEN` (long alphanumeric string, usually 40+ chars)
-   - Tell the user exactly which environment variables to set
 
-5. **Ask the user to confirm the environment is configured**:
-   - Wait for the user to confirm these values have been set in their host application, runtime environment, or appropriate config file
-   - For security reasons, do not run `configure.py` or create a local `.env` file by default if the skill is installed under a host application directory (for example, `~/.claude/skills`)
+4. **Ask the user to confirm the environment is configured**.
 
-6. **Retry only after confirmation**:
+5. **Retry only after confirmation**:
    - Once the user confirms the environment variables are available, retry the original parsing task
 
-**IMPORTANT**: The error message format is STRICT and must be shown exactly as provided by the script. Do not modify or paraphrase it.
-
 ### Handling Large Files
 
 There is no file size limit for the API. For PDFs, the maximum is 100 pages per request.

skills/paddleocr-text-recognition/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: paddleocr-text-recognition
-description: >
-  Use this skill when users need to extract text from images, PDFs, or documents. Supports URLs and local files.
-  Returns structured JSON containing recognized text.
+description: Extracts text (with locations) from images and PDF documents using PaddleOCR.
 metadata:
   openclaw:
     requires:
@@ -156,6 +154,8 @@ The output JSON structure is as follows:
 
 ### First-Time Configuration
 
+You can generally assume that the required environment variables have already been configured. Only when an OCR task fails should you analyze the error message to determine whether it is caused by a configuration issue. If it is indeed a configuration problem, you should notify the user to fix it.
+
 **When API is not configured**:
 
 The error will show:
@@ -175,25 +175,23 @@ CONFIG_ERROR: PADDLEOCR_OCR_API_URL not configured. Get your API at: https://pad
      - PADDLEOCR_ACCESS_TOKEN
      - Optional: PADDLEOCR_OCR_TIMEOUT
      ```
+   - For security reasons, do not run `configure.py` or create a local `.env` file by default if the skill is installed under a host application directory (for example, `~/.claude/skills`). You should also advise the user not to do this.
 
-3. **If the user provides credentials in chat anyway** (accept any reasonable format):
+3. **If the user provides credentials in chat anyway** (accept any reasonable format), for example:
    - `PADDLEOCR_OCR_API_URL=https://xxx.paddleocr.com/ocr, PADDLEOCR_ACCESS_TOKEN=abc123...`
    - `Here's my API: https://xxx and token: abc123`
    - Copy-pasted code format
    - Any other reasonable format
    - **Security note**: Warn the user that credentials shared in chat may be stored in conversation history. Recommend setting them through the host application's configuration instead when possible.
 
-4. **Parse and validate the values**:
+   Then parse and validate the values:
    - Extract `PADDLEOCR_OCR_API_URL` (look for URLs with `paddleocr.com` or similar)
    - Confirm `PADDLEOCR_OCR_API_URL` is a full endpoint ending with `/ocr`
    - Extract `PADDLEOCR_ACCESS_TOKEN` (long alphanumeric string, usually 40+ chars)
-   - Tell the user exactly which environment variables to set
 
-5. **Ask the user to confirm the environment is configured**:
-   - Wait for the user to confirm these values have been set in their host application, runtime environment, or appropriate config file
-   - For security reasons, do not run `configure.py` or create a local `.env` file by default if the skill is installed under a host application directory (for example, `~/.claude/skills`)
+4. **Ask the user to confirm the environment is configured**.
 
-6. **Retry only after confirmation**:
+5. **Retry only after confirmation**:
    - Once the user confirms the environment variables are available, retry the original OCR task
 
 ### Error Handling