← 返回 Skills 市场
wps-ocr
作者
randyliu111
· GitHub ↗
· v1.0.1
· MIT-0
256
总下载
2
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install wps-ocr
功能描述
A lightweight, high-performance file parsing tool that can quickly and accurately extract text, handwritten text, formulas, tables, documents and seals from...
安全使用建议
This skill will upload any file you provide to Kingsoft/WPS (aiwrite.wps.cn) for OCR and requires you to set a WPS_OCR_ACCESS_KEY environment variable. If you plan to install or use it: (1) only use a key you control and are willing to have used for cloud processing, (2) do not upload sensitive or confidential files you wouldn't want sent to an external service, (3) be aware the script will read local files you point it at (it enforces existence, extension, and a 10MB size limit), and (4) note the minor doc inconsistency (SKILL_zh mentions a different env var name) — the implementation uses WPS_OCR_ACCESS_KEY. If you need higher assurance, review the full script locally or run it in a sandboxed environment and monitor network calls, or obtain an ephemeral API key you can revoke after testing.
功能分析
Type: OpenClaw Skill
Name: wps-ocr
Version: 1.0.1
The wps-ocr skill is a legitimate tool for performing OCR via the Kingsoft (WPS) API. The implementation in scripts/wps_ocr.py is exceptionally secure, featuring robust protections against Server-Side Request Forgery (SSRF) and DNS rebinding by validating resolved IP addresses against private ranges and disabling HTTP redirects. It follows best practices by using environment variables for credentials and providing clear privacy warnings in SKILL.md regarding data transmission to external servers.
能力评估
Purpose & Capability
Name/description state an OCR connector for WPS OCR; the runtime instructions and included Python client send files to aiwrite.wps.cn and require a single env var (WPS_OCR_ACCESS_KEY). Requiring one service credential and the requests library is proportionate to the stated purpose.
Instruction Scope
SKILL.md explicitly warns that the file will be sent to Kingsoft servers and instructs running the bundled script with a URL or local path — this matches the code. Minor inconsistency: the docs say 'only verify the file type without performing any verification on the path', while the script actually checks file existence, type, and size before reading. The skill will read and base64-encode local files provided by the user and transmit them to the WPS endpoint, which is expected behavior for an OCR client but has privacy implications the user should understand.
Install Mechanism
No install specification (instruction-only install) and only a small Python script is included. Dependencies are limited to the requests package. No remote download/install of arbitrary archives or third-party binaries is present.
Credentials
The code uses a single environment variable WPS_OCR_ACCESS_KEY for the Authorization header, which is appropriate. Minor documentation inconsistency: the Chinese SKILL_zh metadata references WPS_OCR_CLIENT_SECRET while the code and English SKILL.md use WPS_OCR_ACCESS_KEY — the code expects WPS_OCR_ACCESS_KEY. No other unrelated secrets are requested.
Persistence & Privilege
The skill does not request always: true or any special persistent privileges, nor does it modify other skills or system-wide settings. The SKILL.md suggests storing the env var in ~/.openclaw/env which is a normal convenience step.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install wps-ocr - 安装完成后，直接呼叫该 Skill 的名称或使用
/wps-ocr触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
wps-ocr 1.0.0
- Initial release of the skill.
- Supports high-performance extraction of text, handwriting, formulas, tables, documents, and seals from files into Markdown.
- Compatible with JPG, PNG, BMP, HEIF, and WEBP image formats.
- Sends files to Kingsoft Office server (aiwrite.wps.cn) for OCR processing.
- Uses WPS_OCR_ACCESS_KEY as the required environment variable.
- Included privacy and data flow notice; supports both URL and local file recognition.
v1.0.0
wps-ocr 1.0.0
- Initial release of a lightweight, high-performance OCR file parsing tool.
- Quickly and accurately extracts text, handwriting, formulas, tables, documents, and seals into Markdown structure.
- Supports scanned documents, screenshots, and photos in JPG, PNG, BMP, HEIF, and WEBP formats.
- Sends files to Kingsoft Office Cloud Service (aiwrite.wps.cn) for recognition; API key required via environment variable.
- Returns extracted text and detailed detection info, with clear error messages on failure.
元数据
常见问题
wps-ocr 是什么？
A lightweight, high-performance file parsing tool that can quickly and accurately extract text, handwritten text, formulas, tables, documents and seals from... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 256 次。
如何安装 wps-ocr？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install wps-ocr」即可一键安装，无需额外配置。
wps-ocr 是免费的吗？
是的，wps-ocr 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
wps-ocr 支持哪些平台？
wps-ocr 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 wps-ocr？
由 randyliu111（@randyliu111）开发并维护，当前版本 v1.0.1。
推荐 Skills