Compare, 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.
Compare, contrast, and synthesize content across multiple items in the user's Zotero library.
zotero-find or named by the user).zot CLI required for page extraction from large documents.Clarify:
If the comparison dimension is vague, ask — a focused comparison is far more useful than "compare everything."
Extract content from all items in parallel using tool calls:
zot pdf <KEY> --pages X-Y for large docs, zotero_get_item_fulltext for short papers)Budget: ~15 pages per item, max ~40 pages total. This keeps token usage reasonable. The user can ask for more depth on specific aspects.
For short papers (< 20 pages), fulltext is fine — no need to target sections.
Choose the format that fits:
| Aspect | Paper A (Author, Year) | Paper B (Author, Year) |
|---|---|---|
| Method | ... (Section X, p. N) | ... (Section Y, p. M) |
On time integration: Hesthaven & Warburton (2008, Section 4.3, pp. 89-95) use explicit RK methods... By contrast, Ferrer (2012, Section 3.1, pp. 12-14) employs implicit-explicit splitting...
Summary table first, then narrative on the most interesting differences.
| Tool | Purpose |
|---|---|
zotero_search_items | Resolve title/author to item key |
zotero_get_pdf_outline | Get document structure |
zotero_get_item_fulltext | Full text (short papers only) |
zotero_get_item_metadata | Metadata and BibTeX |
zot pdf <KEY> --pages X-Y | Targeted page extraction |