← 返回 Skills 市场
114
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install academic-reader
功能描述
PDF to Markdown converter - extract text, tables and formulas from PDF files to clean Markdown. Use when converting PDF documents, extracting PDF content, pa...
使用说明 (SKILL.md)
\r \r
Academic Reader - Scientific Paper Parser\r
\r Convert PDF files to clean Markdown using MinerU Open API. No API key required.\r \r
Quick Start\r
\r
# Academic Reader - Scientific Paper Parser\r
mineru-open-api flash-extract report.pdf\r
\r
# Academic Reader - Scientific Paper Parser\r
mineru-open-api flash-extract https://cdn-mineru.openxlab.org.cn/demo/example.pdf\r
\r
# Academic Reader - Scientific Paper Parser\r
mineru-open-api flash-extract report.pdf -o ./output/\r
\r
# Academic Reader - Scientific Paper Parser\r
mineru-open-api flash-extract report.pdf --pages 1-10\r
```\r
\r
## Language Rule\r
\r
You MUST reply to the user in the SAME language they use. This is non-negotiable.\r
\r
## Capabilities\r
\r
- Extracts text, tables, and formulas from PDF\r
- Supports both local files and URLs directly\r
- Page range selection with `--pages`\r
- Language hint with `--language` (default: `ch`, use `en` for English)\r
- No API key, no signup, no authentication\r
- Max 10MB / 20 pages per document\r
\r
## When to Use\r
\r
- User asks to "read", "extract", "convert", or "parse" a PDF\r
- User shares a PDF file or PDF link and asks for its content\r
- User wants to summarize or analyze a PDF document\r
- User needs PDF content in Markdown format\r
\r
## CLI Reference\r
\r
Run `mineru-open-api flash-extract --help` for all available options.\r
\r
## Data Flow\r
\r
`flash-extract` sends the document to the MinerU API (mineru.net) for processing and returns Markdown. This is a stateless API call — no account, no persistent storage. MinerU is an open-source project by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU\r
\r
## Notes\r
\r
- Output is Markdown only; images/tables/formulas may be replaced with placeholders\r
- For larger files (up to 200MB/600 pages) or precision extraction with full assets, use `mineru-open-api extract` (requires auth via `mineru-open-api auth`)\r
- If the CLI cannot be installed via npm/uv/go, download it from https://mineru.net/ecosystem?tab=cli\r
安全使用建议
This skill appears to do what it says, but it uploads documents to the MinerU API (mineru.net) for processing. Before installing or using it, avoid sending sensitive or confidential PDFs; verify the mineru-open-api package source (npm page and the GitHub repo referenced), inspect package contents or source code if possible, and install/run it in a controlled environment (or sandbox) if you have privacy concerns. Check the CLI's version, publisher, and checksum, and prefer an on-device extractor if you cannot accept external upload of your documents.
功能分析
Type: OpenClaw Skill
Name: academic-reader
Version: 1.0.0
The skill facilitates PDF-to-Markdown conversion by uploading local documents to a remote third-party API (mineru.net). While this aligns with the stated purpose of the 'Academic Reader,' the automated transmission of potentially sensitive user files to an external endpoint (OpenDataLab/Shanghai AI Lab) constitutes a high-risk data flow. The SKILL.md also includes a 'non-negotiable' behavioral instruction regarding language usage, but no evidence of intentional malice, such as credential theft or obfuscated payloads, was found.
能力评估
Purpose & Capability
The name/description (PDF to Markdown converter) aligns with the declared binary (mineru-open-api) and the SKILL.md examples (mineru-open-api flash-extract). Required binaries and install methods are consistent with the stated purpose.
Instruction Scope
SKILL.md instructs using the mineru-open-api CLI to send local files or URLs to the MinerU service for extraction. It does not direct the agent to read unrelated files, environment variables, or system configuration. The documented data flow explicitly sends the document to mineru.net, which is consistent with a cloud-based extraction tool.
Install Mechanism
Installers are npm / uv / go package installs for a CLI named mineru-open-api. Using public package managers is typical but does involve executing third-party code on the host. No direct-download URLs or obscure hosts are used in the install spec, which lowers but does not eliminate install risk.
Credentials
The skill requests no environment variables, credentials, or config paths. That is proportional for a tool that claims 'no API key required.' The only sensitive action is uploading user-provided PDFs to an external API, which is justified by the stated functionality but has privacy implications.
Persistence & Privilege
always:false and no config paths or cross-skill config modifications are requested. The skill does not request permanent presence or elevated platform privileges beyond installing/using its CLI binary.
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 academic-reader - 安装完成后，直接呼叫该 Skill 的名称或使用
/academic-reader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
v1.0.0
Academic Reader 1.0.0
- Initial release: convert PDF files to clean Markdown with MinerU Open API.
- Extracts text, tables, and formulas from local PDFs or URLs.
- Supports page range selection and language hints.
- No API key, signup, or authentication required.
- Limit of 10MB or 20 pages per document.
- Output is Markdown only; images/tables/formulas may be replaced with placeholders.
元数据
常见问题
Academic Reader 是什么？
PDF to Markdown converter - extract text, tables and formulas from PDF files to clean Markdown. Use when converting PDF documents, extracting PDF content, pa... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 114 次。
如何安装 Academic Reader？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install academic-reader」即可一键安装，无需额外配置。
Academic Reader 是免费的吗？
是的，Academic Reader 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Academic Reader 支持哪些平台？
Academic Reader 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 Academic Reader？
由 tanis90（@tanis90）开发并维护，当前版本 v1.0.0。
推荐 Skills