← Back to Skills Marketplace
0
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install read-pdf
Description
一个支持AI助手读取和分析PDF文件的MCP服务器，提供PDF元数据提取、页面范围阅读和关键词搜索等功能。
Usage Guidance
Review this carefully before installing. Use it only for PDFs, URLs, and search terms you are comfortable sending to the XiaoBenYang API service, and avoid confidential local file paths or private document URLs. If you proceed, treat the API key as a persistent local secret because the skill writes it to .env in plaintext.
Capability Assessment
Purpose & Capability
The advertised PDF functions match the implemented tool names, but every operation is a remote API call to mcp.xiaobenyang.com and the documentation still contains unrelated gaokao/school-search references, weakening confidence that the behavior is tightly scoped and reviewed.
Instruction Scope
The skill tells the agent to collect an API key, save it, and send raw tool results back, while not clearly warning users that local paths, remote URLs, page ranges, and search terms are transmitted to the external service.
Install Mechanism
The package uses ordinary Python files and common dependencies such as requests and pydantic-settings; no unusual installer, obfuscation, or hidden install-time execution was found.
Credentials
Network use is coherent for an API-backed PDF service, but accepting both local paths and URLs without visible domain, size, or sensitivity controls is broader than a simple local PDF reader would imply.
Persistence & Privilege
The skill persists XBY_APIKEY into a plaintext .env file and reads it back from .env or the environment; this is service-specific rather than broad credential harvesting, but the retention and storage location are not clearly consented to in user-facing terms.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install read-pdf - After installation, invoke the skill by name or use
/read-pdf - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
PDF阅读服务 v1.0.0 初始发布
- 提供PDF全文内容和元数据提取、页面范围阅读、关键词搜索等功能。
- 严格要求用户提供 API 密钥，无密钥时强制用 AskUserQuestion 工具询问。
- 明确工具调用及参数提取流程，支持根据用户需求选择对应PDF操作工具。
- 所有工具均支持本地文件或URL输入，返回结构化数据结果。
Metadata
Frequently Asked Questions
What is Read Pdf?
一个支持AI助手读取和分析PDF文件的MCP服务器，提供PDF元数据提取、页面范围阅读和关键词搜索等功能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 0 downloads so far.
How do I install Read Pdf?
Run "/install read-pdf" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Read Pdf free?
Yes, Read Pdf is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Read Pdf support?
Read Pdf is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Read Pdf?
It is built and maintained by ALinkLab (@alinklab); the current version is v1.0.0.
More Skills