Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/papersgpt-zotero-guide
AI plugin for Zotero with ChatGPT, Claude, and DeepSeek support
Passed 20 of 22 test cases with the skill, and 14 of 22 without it.
and 5 more in the full report
6 fixed14 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
When using AI to process a batch of 20 newly downloaded arXiv papers in Zotero, I want to quickly bucket them into standardized reading priorities. What specific three sorting categories should I assign to these items after generating short summaries?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies sorting papers into read now, read later, and archive categories. | Passed | Passed |
| Recommends saving AI-generated tags directly onto Zotero items for filtering. | Missed | Passed |
The instructions your model reads when the skill loads.
A skill for using the PapersGPT plugin to integrate AI assistants (ChatGPT, Claude, DeepSeek) directly into the Zotero reference management workflow for paper summarization, question-answering, and research analysis. Based on papersgpt-for-zotero (2K stars), this skill transforms Zotero from a passive reference store into an active research intelligence tool.
Researchers accumulate large Zotero libraries but often lack time to deeply read every paper. PapersGPT addresses this by bringing AI analysis capabilities directly into the Zotero interface. Without leaving the reference manager, researchers can generate summaries, ask specific questions about paper content, compare papers, extract key findings, and get AI-assisted insights that accelerate the literature review process.
The plugin supports multiple AI backends, allowing researchers to choose based on quality, cost, and privacy preferences. All interactions happen in context of the selected paper's full text, ensuring responses are grounded in the actual document rather than the model's general knowledge.
Installation
Backend Configuration
Privacy Considerations
Paper Summarization
test cases passed, vs 14 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.