← Back to Skills Marketplace
298
Downloads
1
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install research-paper-compare
Description
Compare research papers by retrieving full PDFs from titles, URLs, or files and synthesizing differences, strengths, weaknesses, and evidence-backed trade-offs.
Usage Guidance
This skill appears coherent with its purpose, but check a few operational points before installing: 1) Confirm the agent environment has a safe, local PDF extraction capability (or understand which external service would be used) because the skill assumes full-text extraction but declares no tooling. 2) Verify network policies and sandboxing—the skill will download PDFs from arbitrary URLs and may attempt to fetch from publisher sites; ensure downloads are allowed and handled safely. 3) If you expect paywalled PDFs, decide whether you'll provide credentials; the skill does not request them and will stop if full text is unavailable. 4) Confirm the agent will not upload PDF contents to third-party services unless you approve that data flow. If these operational details are acceptable, the skill is internally consistent with its description.
Capability Analysis
Type: OpenClaw Skill
Name: research-paper-compare
Version: 1.0.0
The skill is a legitimate tool designed to compare research papers by retrieving full PDF texts from academic sources like arXiv and OpenReview. The instructions across all files (SKILL.md, input-handling.md, evidence-policy.md) focus on data extraction, evidence quality, and structured synthesis without any indicators of malicious intent, data exfiltration, or unauthorized execution.
Capability Assessment
Purpose & Capability
The name and description (compare research papers by obtaining full PDFs and synthesizing differences) match the instructions: the SKILL.md explicitly describes resolving titles/URLs/local PDFs, downloading PDF full text, normalizing records, and performing structured comparison. No unrelated credentials, binaries, or installs are requested, so required capabilities are proportionate to the stated purpose.
Instruction Scope
The SKILL.md requires web search and downloading arbitrary PDF URLs to obtain full text (expected for this purpose). It correctly enforces a policy to stop if full PDF text is unobtainable. However, it does not specify operational guardrails: it doesn't state whether PDF parsing is local vs sent to third-party services, whether downloads are sandboxed, or how to handle paywalled content or copyright-restricted PDFs. It also assumes the runtime can extract readable text from PDFs but does not declare the needed extraction tooling.
Install Mechanism
Instruction-only skill with no install spec and no code files—this is low-risk from an installation perspective (nothing will be written to disk or downloaded as part of a packaged install).
Credentials
The skill declares no environment variables or credentials (proportional). That said, in practice retrieving PDFs from publisher sites may require credentials or access tokens; the skill does not request these and states it will stop if full text isn't accessible. Verify whether your platform's agent will attempt to use any agent-level credentials for retrieval or will upload PDFs to external extraction services—those behaviors are not described by the skill.
Persistence & Privilege
always is false and the skill does not request persistent presence or elevated privileges. It does not attempt to modify other skills or system-wide settings based on the provided files.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install research-paper-compare - After installation, invoke the skill by name or use
/research-paper-compare - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of paper-compare skill with core framework for side-by-side research paper analysis.
- Added structured input handling guide for DOIs, URLs, search, and PDF files (`input-handling.md`).
- Defined standard comparison schema and output patterns for clarity and consistency.
- Introduced evidence policies and memory dimensions referenced in outputs.
- Implemented rule: always use PDF full text before analysis; block and report any papers missing full PDF access.
- Removed legacy metadata file (`_meta.json`).
Metadata
Frequently Asked Questions
What is Research Paper Compare?
Compare research papers by retrieving full PDFs from titles, URLs, or files and synthesizing differences, strengths, weaknesses, and evidence-backed trade-offs. It is an AI Agent Skill for Claude Code / OpenClaw, with 298 downloads so far.
How do I install Research Paper Compare?
Run "/install research-paper-compare" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Research Paper Compare free?
Yes, Research Paper Compare is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Research Paper Compare support?
Research Paper Compare is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Research Paper Compare?
It is built and maintained by quqxui (@quqxui); the current version is v1.0.0.
More Skills