← Back to Skills Marketplace
300
Downloads
0
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install paper-reader
Description
Comprehensive PDF paper reader for academic research. Extracts text, figures, tables, and structured content from research papers with support for multimodal...
Usage Guidance
Do not run the example commands or pip-install things on the basis of this package alone. The SKILL.md references scripts and a Python module (read_paper.py, paper_reader) that are not included — ask the publisher for the missing code or a proper install spec before installing. If you still want to use it, request: (1) the actual code files or a reproducible install (GitHub repo or PyPI package), (2) a clear statement of whether the tool performs any network calls and to which endpoints, and (3) a signed or verifiable author/source. If you must test now, do so in a restricted sandbox and inspect any downloaded/extracted files before running them. Because the package is incoherent as distributed, treat it as untrusted until the missing pieces are resolved.
Capability Analysis
Type: OpenClaw Skill
Name: paper-reader
Version: 1.0.0
The skill bundle contains metadata and documentation for an academic PDF processing tool. The documentation (SKILL.md) describes legitimate functionality for extracting text, images, and tables using standard Python libraries (pdfplumber, pymupdf, Pillow). There are no signs of malicious intent, data exfiltration, or prompt injection within the provided files.
Capability Assessment
Purpose & Capability
The SKILL.md describes a full CLI and Python API and lists Python dependencies (pdfplumber, pymupdf, Pillow) that are appropriate for a PDF reader, but the package contains no code files (no read_paper.py, no paper_reader module). That mismatch means the skill can't perform the claimed capabilities as distributed.
Instruction Scope
Runtime instructions explicitly tell the agent/user to run python3 ~/.openclaw/skills/paper-reader/read_paper.py and to import paper_reader — paths and modules that do not exist in this bundle. The instructions also direct reading PDFs and writing extracted outputs to arbitrary filesystem locations (e.g., ~/..., ./figures), which is expected for a paper-processing tool but should only be done by code you can inspect. There is no guidance about network activity (no explicit exfiltration), but the missing code makes it impossible to verify behavior.
Install Mechanism
There is no install spec (instruction-only), which is lower risk in itself. The README suggests running pip install pdfplumber pymupdf Pillow manually; that is reasonable for the declared dependencies, but because no code is bundled, there's nothing to install or verify from this skill package.
Credentials
The skill does not request environment variables, credentials, or config paths. The declared Python packages are appropriate for the stated purpose and do not imply additional secrets or cloud access.
Persistence & Privilege
The skill does not request always:true or other elevated persistent privileges. Model invocation is enabled by default (normal). The skill does not attempt to modify other skills or system-wide settings in the included materials.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install paper-reader - After installation, invoke the skill by name or use
/paper-reader - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of paper-reader, a comprehensive PDF tool for academic research.
- Extracts full text, figures, tables, and structured content from research papers.
- Supports metadata extraction: title, authors, abstract, keywords.
- Recognizes and organizes text by academic sections (e.g., Introduction, Methods).
- Batch processes entire folders of papers for large-scale workflows.
- Offers both command-line tool and Python API for flexible usage.
- Outputs organized files: plain text, images, tables (CSV), sectioned chapters, and metadata.
Metadata
Frequently Asked Questions
What is Paper Reader?
Comprehensive PDF paper reader for academic research. Extracts text, figures, tables, and structured content from research papers with support for multimodal... It is an AI Agent Skill for Claude Code / OpenClaw, with 300 downloads so far.
How do I install Paper Reader?
Run "/install paper-reader" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Paper Reader free?
Yes, Paper Reader is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Paper Reader support?
Paper Reader is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Paper Reader?
It is built and maintained by 崔之行 (@changer-changer); the current version is v1.0.0.
More Skills