← 返回 Skills 市场
124
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install pdf-to-text
功能描述
Extract plain text from PDF documents using the MinerU API. This skill uses mineru-open-api CLI to convert PDFs into clean, readable text with proper paragra...
安全使用建议
This skill is coherent: it tells the agent to use the mineru-open-api CLI to extract text from PDFs. Before installing or running it, do the following: (1) inspect the mineru-open-api package on npm (publisher, download counts, source repo) to ensure it's trustworthy; (2) be aware `npm install -g` writes global binaries and may run install scripts—prefer a sandbox or local install (no -g) if you want to be cautious; (3) check MinerU's privacy/terms because using OCR/batch likely uploads document contents to mineru.net (sensitive documents may be exposed); (4) confirm how the MinerU token is stored by the CLI (env var vs config file) before supplying credentials; (5) test with non-sensitive PDFs first. If any of these checks raise concerns (no source repo, questionable publisher, or unclear token handling), do not install or run the CLI.
功能分析
Type: OpenClaw Skill
Name: pdf-to-text
Version: 0.2.0
The skill provides instructions for using the 'mineru-open-api' CLI tool to extract text from PDF documents. The commands and workflows described in SKILL.md are consistent with the tool's legitimate purpose, including support for OCR and batch processing. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
The name/description (PDF to Text via MinerU) match the SKILL.md: all runtime steps call the mineru-open-api CLI to extract text/OCR. There are no requests for unrelated cloud credentials, config paths, or unrelated binaries.
Instruction Scope
Runtime instructions are limited to installing and running mineru-open-api, checking file sizes, and writing output directories. They operate on user-supplied PDF files and do not instruct the agent to read unrelated system files, exfiltrate data, or call unexpected external endpoints beyond the MinerU service referenced.
Install Mechanism
There is no formal install spec in registry metadata; the SKILL.md instructs users to run `npm install -g mineru-open-api`. Installing a global npm package is a reasonable way to get a CLI but carries the usual npm risks (postinstall scripts, privilege elevation to write global binaries). Recommend reviewing the mineru-open-api npm package and its maintainer before running global install.
Credentials
The skill declares no required environment variables or credentials, which is consistent with 'flash-extract' being tokenless for small files. SKILL.md does mention that OCR/batch modes require configuring a MinerU token (link provided). The skill does not declare how that token is provided (env var, config file, or interactive login), so users should verify how the CLI stores/reads tokens before providing sensitive credentials.
Persistence & Privilege
The skill is instruction-only and not always-enabled. It does not request system-wide persistent privileges or modify other skills' configs. Agent autonomous invocation is allowed (platform default) but not exceptional 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 pdf-to-text - 安装完成后，直接呼叫该 Skill 的名称或使用
/pdf-to-text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
v0.2.0
Added MinerU API integration via mineru-open-api CLI for PDF text extraction
v0.1.0
Initial release - PDF text extraction
元数据
常见问题
PDF to Text 是什么？
Extract plain text from PDF documents using the MinerU API. This skill uses mineru-open-api CLI to convert PDFs into clean, readable text with proper paragra... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 124 次。
如何安装 PDF to Text？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pdf-to-text」即可一键安装，无需额外配置。
PDF to Text 是免费的吗？
是的，PDF to Text 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
PDF to Text 支持哪些平台？
PDF to Text 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 PDF to Text？
由 veeicwgy（@veeicwgy）开发并维护，当前版本 v0.2.0。
推荐 Skills