← 返回 Skills 市场
228
总下载
0
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install table-ocr
功能描述
OCR and extract tables from scanned PDFs and images using MinerU. Recognizes table structures in image-based documents and converts them to structured Markdo...
安全使用建议
This skill appears coherent, but before installing: verify you trust mineru.net and the npm/GitHub packages (review package source if possible), because installing a global CLI runs third-party code on your system. The MINERU_TOKEN permits the MinerU service to process your files — avoid uploading sensitive documents unless you trust the service and its privacy policy. Use a limited/revocable token, rotate it if needed, and prefer running the CLI locally on non-sensitive data if you cannot confirm the provider's practices.
功能分析
Type: OpenClaw Skill
Name: table-ocr
Version: 0.4.0
The skill bundle provides instructions and metadata for using the MinerU OCR and table extraction service via the 'mineru-open-api' CLI. It correctly identifies dependencies, requires a legitimate API token (MINERU_TOKEN), and points to official resources from OpenDataLab (mineru.net). No malicious code, data exfiltration patterns, or prompt injection attempts were found.
能力评估
Purpose & Capability
Name/description request OCR table extraction via MinerU; required binary (mineru-open-api) and the MINERU_TOKEN credential directly match that purpose and are expected.
Instruction Scope
SKILL.md only instructs the agent to run the MinerU CLI (extract, auth) against user-provided files or URLs and to set MINERU_TOKEN. It does not instruct reading unrelated system files or other environment variables.
Install Mechanism
Install options are standard: npm package and a go install from a GitHub repo. Both are typical for distributing a CLI; no arbitrary downloads or extract-from-unknown-URL steps are present.
Credentials
Only MINERU_TOKEN is required and is declared as the primary credential. That is proportional for a CLI that authenticates to a remote MinerU service.
Persistence & Privilege
Skill is not always-enabled and does not request system-wide persistence or access to other skills' configs. Autonomous invocation is allowed (platform default) but not combined with other concerning privileges.
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 table-ocr - 安装完成后，直接呼叫该 Skill 的名称或使用
/table-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
v0.4.0
SEO: expand description for better ClawHub vector search discovery
v0.3.0
Rollback to original version
v0.2.1
SEO optimization v0.2.1
v0.2.0
SEO optimization v0.2.0
v1.0.1
Fix: declare MINERU_TOKEN credential in metadata
v1.0.0
Extract tables from scanned PDFs or images using MinerU OCR with table recognition
元数据
常见问题
Table Ocr 是什么？
OCR and extract tables from scanned PDFs and images using MinerU. Recognizes table structures in image-based documents and converts them to structured Markdo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 228 次。
如何安装 Table Ocr？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install table-ocr」即可一键安装，无需额外配置。
Table Ocr 是免费的吗？
是的，Table Ocr 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Table Ocr 支持哪些平台？
Table 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 Table Ocr？
由 mzlzyCA（@mzlzyca）开发并维护，当前版本 v0.4.0。
推荐 Skills