← Back to Skills Marketplace
文档识别-表格识别（invoice-ocr-xy）翔云平台
by
liudengkui
· GitHub ↗
· v1.0.0
· MIT-0
74
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install doc-ocr-xy
Description
文档 OCR 识别技能。扫描文件夹中的文档（PDF/图片），调用翔云 OCR API 识别文档信息。**重要：首次使用必须先配置翔云凭证，主动向用户索要 netocr_key 和 netocr_secret，或引导用户运行 --config 命令自行配置。**
README (SKILL.md)
文档 OCR 识别技能
批量识别文档。
⚠️ 首次使用必须配置凭证
此技能需要翔云 OCR 服务，使用前必须先配置凭证！
方式一：向用户提供凭证（推荐）
主动询问用户：
"使用此技能需要翔云 netocr_key 和 netocr_secret，请提供这两个凭证。
获取方式：翔云个人中心"
然后运行：
python scripts/recognize_doc.py --config
方式二：引导用户自行配置
告诉用户：
"请先运行以下命令配置翔云凭证："
python ~/.openclaw/skills/invoice-ocr/scripts/recognize_doc.py --config
特点
| 支持语言 | 代码 |
|---|---|
| 简体中文（印刷） | 0 |
| 简体中文（印刷+手写） | 3 |
| 繁体中文（印刷） | 1 |
| 繁体中文（印刷+手写） | 4 |
| 英文 | 2 |
| 阿拉伯 | 5 |
| 乌尔都 | 6 |
| 格鲁吉亚 | 7 |
| 西里尔文 | 8 |
| 法文 | 9 |
| 西班牙文 | 10 |
| 日文 | 11 |
| 韩文 | 12 |
| 葡萄牙文 | 13 |
| 越南 | 14 |
| 孟加拉 | 15 |
支持的文件格式
| 格式 | 扩展名 |
|---|---|
| OFD | .ofd |
| 图片 | .jpg, .jpeg, .png, .bmp , .tif, .tiff, .webp |
使用方法
识别文档
# 识别文件夹中的所有文档
python scripts/recognize_doc.py /path/to/doc
# 识别单文档
python scripts/recognize_doc.py /path/to/doc/123.png
配置管理
# 设置翔云凭证
python scripts/recognize_doc.py --config
# 查看当前配置
python scripts/recognize_doc.py --list-config
获取 netocr_key 和 netocr_secret
- 登录翔云
- 在个人中心获得
详细 API 说明见 翔云 OCR API 参考
工作流程
文档文件 → OCR识别 → 返回结果（输出原文不必翻译）
↓ ↓
PDF/图片 md结构
注意事项
- 图片需清晰，建议长宽 > 500px
- 单个文件不超过 10MB
- 翔云 OCR 按次计费，注意费用控制
- 配置文件保存在技能目录下的 config.json
Usage Guidance
This skill appears to do what it says: send document data to the NetOCR API to perform OCR. Before installing/using it: (1) Do not paste your netocr_key/netocr_secret into chat — instead run the script locally with --config to store credentials in the skill directory. (2) Be aware config.json stores credentials in plaintext under the skill folder; treat that file as sensitive and restrict access. (3) Documents you process are uploaded to a third-party service (netocr.com) — ensure you're comfortable with that for any sensitive documents and check billing implications. (4) If you must provide credentials via conversation, understand that they may be retained in logs; prefer local configuration. If you want, I can point out the exact config path and show how to run the script locally to avoid sharing secrets in chat.
Capability Analysis
Type: OpenClaw Skill
Name: doc-ocr-xy
Version: 1.0.0
The skill is a legitimate tool for performing OCR on documents using the Xiangyun (netocr.com) API. The Python script `scripts/recognize_doc.py` correctly implements the API integration, handling file reading, base64 encoding, and multipart form-data submission to the official endpoint. While it requires and stores API credentials in `config.json`, this behavior is transparently documented in `SKILL.md` and is necessary for the tool's functionality. No evidence of data exfiltration to unauthorized domains, malicious execution, or prompt injection was found.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, and scripts/recognize_doc.py consistently implement a document OCR skill that calls the netocr.com API. The script sends base64-encoded file data to https://netocr.com/api/recog_table_base64 and expects netocr_key/netocr_secret credentials — this is coherent with the stated purpose.
Instruction Scope
SKILL.md instructs the agent to scan folders or single files and to ask the user for netocr_key/netocr_secret or guide them to run the script with --config. The runtime instructions and code operate only on files the user points the script at and the NetOCR endpoint. Note: the skill's instructions explicitly recommend 'proactively asking the user' for credentials (see risk section).
Install Mechanism
No install spec; this is an instruction + local Python script. No external downloads or package installs are performed automatically. The only optional dependency is Pillow (PIL) for image conversion, which is documented in the script.
Credentials
The skill does not request unrelated environment variables. It requires the NetOCR API key and secret, which is appropriate. However, credentials are saved in a local config.json inside the skill directory in plaintext (unencrypted). SKILL.md encourages the agent to 'actively ask' the user for credentials in conversation — this risks credential disclosure into chat logs or conversation history. Prefer local --config usage rather than pasting secrets into chat.
Persistence & Privilege
Skill is user-invocable and not always-enabled; it does not request elevated privileges, does not modify other skills, and stores config only in its own skill directory. No persistent system-wide changes detected.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install doc-ocr-xy - After installation, invoke the skill by name or use
/doc-ocr-xy - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of doc-ocr: batch OCR document recognition using the Xiangyun OCR API.
- Supports PDF, OFD, and common image formats (.jpg, .png, .tif, etc.).
- Requires users to configure Xiangyun API credentials (netocr_key and netocr_secret) before first use.
- Supports multiple languages, including Simplified/Traditional Chinese (print/handwriting), English, Arabic, Cyrillic, Japanese, Korean, and more.
- Includes configuration commands for credential management and usage instructions.
- Credentials and configuration are stored locally in the skill's directory.
Metadata
Frequently Asked Questions
What is 文档识别-表格识别（invoice-ocr-xy）翔云平台?
文档 OCR 识别技能。扫描文件夹中的文档（PDF/图片），调用翔云 OCR API 识别文档信息。**重要：首次使用必须先配置翔云凭证，主动向用户索要 netocr_key 和 netocr_secret，或引导用户运行 --config 命令自行配置。**. It is an AI Agent Skill for Claude Code / OpenClaw, with 74 downloads so far.
How do I install 文档识别-表格识别（invoice-ocr-xy）翔云平台?
Run "/install doc-ocr-xy" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 文档识别-表格识别（invoice-ocr-xy）翔云平台 free?
Yes, 文档识别-表格识别（invoice-ocr-xy）翔云平台 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 文档识别-表格识别（invoice-ocr-xy）翔云平台 support?
文档识别-表格识别（invoice-ocr-xy）翔云平台 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 文档识别-表格识别（invoice-ocr-xy）翔云平台?
It is built and maintained by liudengkui (@liudengkui); the current version is v1.0.0.
More Skills