← Back to Skills Marketplace
Paper Parse
by
Sterlingfrank1
· GitHub ↗
· v1.0.0
4558
Downloads
9
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install paper-parse
Description
对用户提供的任何学术论文（PDF附件或URL）进行双模式深度研读。当用户请求分析、研读、解读或总结一篇学术论文时，使用此技能。一次性生成两份报告：Part A 面向研究者的深度专业解析，Part B 面向快速理解的核心逻辑与价值提炼。
Usage Guidance
Install only if you want an agent to fetch or process paper PDFs and convert them to text. Prefer explicit prompts that name the PDF or URL, avoid sensitive unpublished documents unless you trust the runtime, and ensure paths/URLs are handled safely by the platform or shell wrapper.
Capability Analysis
Type: OpenClaw Skill
Name: paper-parse
Version: 1.0.0
The skill is classified as suspicious due to the potential for shell injection. The `SKILL.md` file instructs the AI agent to use the `pdftotext` command-line utility to process user-provided PDF files or URLs. If the input (filename or URL) is not rigorously sanitized by the OpenClaw platform before being passed to `pdftotext`, this could allow an attacker to inject arbitrary shell commands, leading to Remote Code Execution (RCE). While `pdftotext` is a legitimate tool for the skill's stated purpose, the method of its invocation represents a significant vulnerability.
Capability Assessment
Purpose & Capability
Parsing user-provided academic papers with PDF text extraction is coherent with the stated paper-parse purpose; use of pdftotext and PDF/URL inputs is expected for that workflow.
Instruction Scope
The trigger appears broad enough to activate for general academic-paper analysis, and the skill reportedly mandates Chinese output; these are scope and usability issues, not evidence of hidden or purpose-mismatched behavior.
Install Mechanism
No deceptive installer or persistence mechanism is indicated, though users should expect the runtime to need a PDF text extraction utility such as pdftotext.
Credentials
The described behavior uses local file/URL processing that is proportionate for paper parsing and does not indicate credential use, profile access, broad local indexing, or unrelated data collection.
Persistence & Privilege
No background service, privilege escalation, persistent worker, destructive action, or account mutation behavior is indicated by the supplied evidence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install paper-parse - After installation, invoke the skill by name or use
/paper-parse - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of paper-parse skill:
- Deeply analyzes any academic paper (PDF or URL) and generates two types of reports in one file.
- Part A: Provides a detailed, professional, researcher-focused analysis.
- Part B: Extracts the core logic, key findings, and value in a concise, insight-driven summary.
- Ensures academic rigor, theoretical depth, and complete reproduction of the paper’s arguments and data.
- Reports always follow a dual-mode output format separated by '---' and are delivered as a single Markdown file.
- Clear workflow with mandatory full-paper read, interim structured analysis, and templated final report.
Metadata
Frequently Asked Questions
What is Paper Parse?
对用户提供的任何学术论文（PDF附件或URL）进行双模式深度研读。当用户请求分析、研读、解读或总结一篇学术论文时，使用此技能。一次性生成两份报告：Part A 面向研究者的深度专业解析，Part B 面向快速理解的核心逻辑与价值提炼。 It is an AI Agent Skill for Claude Code / OpenClaw, with 4558 downloads so far.
How do I install Paper Parse?
Run "/install paper-parse" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Paper Parse free?
Yes, Paper Parse is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Paper Parse support?
Paper Parse is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Paper Parse?
It is built and maintained by Sterlingfrank1 (@sterlingfrank1); the current version is v1.0.0.
More Skills