By philipnickel
Search, read, and compare content from your Zotero library — papers, books, and references organized in collections.
npx claudepluginhub philipnickel/zotero-research-pluginCompare, contrast, or synthesize content across multiple papers or books from the user's Zotero library. Use this skill when the user wants to compare approaches between papers, synthesize findings across multiple sources, understand how different authors treat the same topic, or build a literature overview. Triggers on: "compare these papers", "how do X and Y differ in their approach to Z", "summarize what my papers say about X", "literature review on X", or any request requiring cross-document analysis of Zotero items.
Find papers, books, and references in the user's Zotero library by topic, author, or title. Use this skill whenever the user wants to find, locate, or discover items in their research library. Triggers on: "find papers about X", "what do I have on X", "search my library", "which paper covers X", "do I have anything by [author]", "that paper about X", or any question that requires identifying which items in Zotero are relevant — even if the user doesn't say "Zotero" explicitly. Also triggers when the user asks a content question like "which paper explains how to do X" — that requires searching inside documents, not just metadata.
Read and extract content from a specific paper or book in the user's Zotero library. Use this skill when the user wants to know what a specific item says about a topic, needs content from particular sections/pages, or asks questions that require reading the actual document. Triggers on: "what does [paper] say about X", "read chapter 3", "find the section on X in [book]", "extract the equation for X", "summarize [paper]", or any request that requires extracting content from a known Zotero item. This skill assumes the item is already identified — if the user hasn't specified which paper/book, use zotero-find first.
A Claude Code plugin for searching, reading, and comparing papers and books in your Zotero library. Uses the Zotero MCP server for library access and the zot CLI for targeted PDF extraction.
The plugin provides three skills that trigger automatically based on your query:
Discover items in your library by topic, author, or title. Runs parallel semantic + keyword searches and ranks results by confidence.
"Which papers do I have about p-multigrid methods?"
"Do I have anything by Stomakhin?"
"What do I have on artificial compressibility for incompressible flow?"
Extract content from a specific paper or book with precise page/section references. Direct quotes are always separated from AI-generated summaries so you can verify claims.
"What does the Hesthaven book say about boundary conditions for DG methods?"
"Read section 5 of the Stomakhin snow paper"
"Extract the constitutive model equations from that paper"
Compare and synthesize content across multiple items. Reads relevant sections in parallel and produces structured comparisons with source attribution.
"Compare the constitutive models in the Stomakhin and Hu papers"
"How do these two papers differ in their approach to time integration?"
Zotero must be running locally.
Zotero MCP server — install and configure:
pip install zotero-mcp
Add to your ~/.claude.json under mcpServers:
{
"mcpServers": {
"zotero": {
"type": "stdio",
"command": "zotero-mcp",
"args": [],
"env": {
"ZOTERO_LOCAL": "true",
"ZOTERO_API_KEY": "<your-api-key>",
"ZOTERO_LIBRARY_ID": "<your-library-id>",
"ZOTERO_LIBRARY_TYPE": "user"
}
}
}
}
Get your API key at https://www.zotero.org/settings/keys. Your library ID is visible in your Zotero web library URL.
zot CLI (required for reading specific pages from large documents):
uv tool install zotero-cli-cc
Option A: From GitHub (recommended)
/plugin marketplace add github:philipnickel/zotero-research-plugin
/plugin install zotero-research@philipnickel-zotero-research-plugin
Option B: Local development
claude --plugin-dir /path/to/zotero-research-plugin
zotero-find classifies your query (author, topic, title, or content) and runs only the relevant search modes:
Results are cross-validated: items found by multiple search modes rank higher.
zotero-read uses a two-phase approach to control cost:
All extracted content follows a strict presentation rule: direct quotes from the source appear in blockquotes with exact page references, clearly separated from AI-generated summaries. This ensures you can always verify what the document actually says vs. what the AI interpreted.
To allow subagents (parallel search, background tasks) to use Zotero tools without interactive approval, add this to ~/.claude/settings.json:
{
"permissions": {
"allow": [
"mcp__zotero__zotero_search_items",
"mcp__zotero__zotero_semantic_search",
"mcp__zotero__zotero_advanced_search",
"mcp__zotero__zotero_get_collections",
"mcp__zotero__zotero_search_collections",
"mcp__zotero__zotero_get_collection_items",
"mcp__zotero__zotero_get_item_metadata",
"mcp__zotero__zotero_get_pdf_outline",
"mcp__zotero__zotero_get_item_fulltext",
"mcp__zotero__zotero_get_annotations",
"mcp__zotero__zotero_get_notes",
"mcp__zotero__zotero_search_by_citation_key",
"Bash(zot:*)"
]
}
}
MIT
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.