• Extract text from handwritten notes, letters, or documents / 从手写笔记、信件或文档中提取文字
• Convert handwriting to editable text / 将手写内容转为可编辑文本
• Recognize mixed handwritten and printed content / 识别手写和印刷混排内容
• Read handwritten formulas, labels, or annotations / 读取手写公式、标签或批注
• User mentions "handwriting OCR", "recognize handwriting", "手写识别", "手写体OCR", "识别手写字"

• Multi-style support: Handles various handwriting styles including cursive and print
• Multi-language: Supports Chinese, English, and mixed-language handwriting
• Mixed content: Can recognize documents with both handwritten and printed text
• Local file & URL: Supports both local files and remote URLs

ZHIPU_API_KEY

ZHIPU_API_KEY

1. Global config (recommended) / 全局配置（推荐）： Set once in

   openclaw.json

   under

   env.vars

   , all Zhipu skills will share it:
   json

   {
     "env": {
       "vars": {
         "ZHIPU_API_KEY": "你的密钥"
       }
     }
   }

2. Skill-level config / Skill 级别配置： Set for this skill only in

   openclaw.json

   :
   json

   {
     "skills": {
       "entries": {
         "glmocr-handwriting": {
           "env": {
             "ZHIPU_API_KEY": "你的密钥"
           }
         }
       }
     }
   }

3. Shell environment variable / Shell 环境变量： Add to

   ~/.zshrc

   :
   bash

   export ZHIPU_API_KEY="你的密钥"

💡 如果你已为其他智谱 skill（如

glmocr

、

glmv-caption

、

glm-image-generation

）配置过 key，它们共享同一个

ZHIPU_API_KEY

，无需重复配置。

• Environment variables used / 使用的环境变量：

  • ZHIPU_API_KEY

    (required / 必需)

  • GLM_OCR_TIMEOUT

    (optional timeout seconds / 可选超时秒数)
• Fixed endpoint / 固定官方端点：

  https://open.bigmodel.cn/api/paas/v4/layout_parsing

• No custom API URL override / 不支持自定义 API URL 覆盖： avoids accidental key exfiltration via redirected endpoints.
• Raw upstream response is optional / 原始响应默认不返回： use

  --include-raw

  only when needed for debugging.

1. ONLY use GLM-OCR API — Execute the script

   python scripts/glm_ocr_cli.py

2. NEVER parse handwriting yourself — Do NOT try to read handwritten text using built-in vision or any other method
3. NEVER offer alternatives — Do NOT suggest "I can try to read it" or similar
4. IF API fails — Display the error message and STOP immediately
5. NO fallback methods — Do NOT attempt handwriting recognition any other way

• Show extracted handwritten text (

  text

  ) in full
• Summarization is allowed, but do not hide important extraction failures
• If the result file is saved, tell the user the file path
• Show raw upstream response only when explicitly requested or debugging (

  --include-raw

  )

{
  "ok": true,
  "text": "Recognized handwritten text in Markdown...",
  "layout_details": [...],
  "result": null,
  "error": null,
  "source": "/path/to/file",
  "source_type": "file",
  "raw_result_included": false
}

• ok

  — whether recognition succeeded

• text

  — extracted text in Markdown (use this for display)

• layout_details

  — layout analysis details

• error

  — error details on failure