← 返回 Skills 市场
212
总下载
0
收藏
1
当前安装
5
版本数
在 OpenClaw 中安装
/install ocr-pro
功能描述
Professional-grade OCR for PDFs and images using MinerU. Advanced text recognition with VLM (Vision Language Model) support for complex layouts, mixed conten...
安全使用建议
This skill appears coherent, but before installing: (1) verify the mineru-open-api npm package and the GitHub repo to ensure they are the official MinerU distribution; (2) confirm whether OCR is performed locally or uploaded to mineru.net (the token and token creation URL imply remote API use) and avoid sending sensitive documents until you understand the service's data handling and retention; (3) use a least-privilege MINERU_TOKEN and rotate it if necessary; (4) inspect the package source if you have strict security requirements or run in a high-risk environment.
功能分析
Type: OpenClaw Skill
Name: ocr-pro
Version: 0.4.0
The ocr-pro skill is a legitimate wrapper for the MinerU OCR service by OpenDataLab. It facilitates document and image text extraction by interfacing with the 'mineru-open-api' CLI tool. While it requires an external API token (MINERU_TOKEN) and sends data to mineru.net for processing, these actions are transparently documented and essential for the skill's stated purpose. No malicious patterns, obfuscation, or prompt-injection attacks were identified in SKILL.md or the metadata.
能力评估
Purpose & Capability
Name/description, required binary (mineru-open-api), install instructions (npm/go), and required env var (MINERU_TOKEN) all align with a MinerU-based OCR CLI. Required items are proportionate to the stated OCR purpose.
Instruction Scope
SKILL.md is instruction-only and instructs the agent to run mineru-open-api commands and set MINERU_TOKEN. It does not ask for unrelated files or credentials. Note: processing likely involves the MinerU service (token + token creation URL are provided), so document data may be uploaded to mineru.net — confirm this if you need local-only processing or have sensitive data.
Install Mechanism
Install uses standard package mechanisms: npm package mineru-open-api or go install from the project's GitHub path. No ad-hoc downloads/extractions or suspicious URLs are present. Recommend verifying the npm package and GitHub repo before installing.
Credentials
Only a single credential (MINERU_TOKEN) is required and is declared as the primary credential. This is proportionate for a networked OCR API. Users should ensure the token's scope/permissions are minimal and treat it as sensitive.
Persistence & Privilege
The skill does not request always: true and is not trying to change other skills or system-wide settings. It relies on the mineru-open-api binary and a token; autonomous invocation is allowed by default but is not an unusual privilege here.
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 ocr-pro - 安装完成后，直接呼叫该 Skill 的名称或使用
/ocr-pro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
v0.4.0
SEO: expand description for better ClawHub vector search discovery
v0.3.0
Rollback to original version
v0.2.0
SEO optimization v0.2.0
v1.0.1
Minor update
v1.0.0
Initial release
元数据
常见问题
Ocr Pro 是什么？
Professional-grade OCR for PDFs and images using MinerU. Advanced text recognition with VLM (Vision Language Model) support for complex layouts, mixed conten... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 212 次。
如何安装 Ocr Pro？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ocr-pro」即可一键安装，无需额外配置。
Ocr Pro 是免费的吗？
是的，Ocr Pro 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Ocr Pro 支持哪些平台？
Ocr Pro 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 Ocr Pro？
由 mzlzyCA（@mzlzyca）开发并维护，当前版本 v0.4.0。
推荐 Skills