zotero-llm-wiki: Paper Chat and literature skills

Repository-documented Zotero and Claude tools: Paper Chat provides PDF questions with linked quotations and highlights; paper-ask supports library questions; paper-search uses OpenAlex; the full Claude Code plugin maintains an Obsidian literature database. These are documented capabilities, not guarantees of accurate citation or exhaustive retrieval.

Workflow level n/a Source Repository-documented Outcome Not empirically evaluated here

Evidence & verification

Source level

Repository-documented
Grounded in a maintainer repository/README. Availability, stars and forks do not establish research benefit or correctness.

Outcome verification

Not empirically evaluated here
A documented resource or intended workflow, not a demonstrated academic outcome. No empirical benefit is established by its inclusion.

Sources checked

2026-10-17 (UTC)

README sections distinguish Paper Chat, two skills and the full plugin. paper-ask was formerly zotero-ask; these are bundled components of the same resource, not separate directory entries. OpenAlex, Zotero, Obsidian, Claudian, and the screenshot example paper are dependencies/example material, not identity aliases. Absolute no-made-up-DOI wording is not adopted as a verified outcome.

Source-checked does not mean independently reproduced. See the Method page for how these labels are assigned.

Sources (1)

Research applicability

Direct literature discovery, source-grounded reading and research-note management workflows for academic papers; researcher verification remains necessary.

Getting started

Editorial suggestion, not executed: choose one documented installation path, start with a non-sensitive paper, inspect quotations in the PDF and verify bibliographic metadata. Back up the literature database before allowing generated updates.

Maintenance

Mutable documentation captured at access time; future compatibility not established.

License

Check original license and dependency/data rights before reuse; no independent legal audit.

Workflow & human oversight

Resource-level automation unspecified; researchers define aims and verify outputs. No autonomous end-to-end outcome claimed.

Workflow level is not an evidence score; higher is not better evidence.

Limitations

README-only substantive review plus repository identity metadata; no installation or outcome tests. Paper Chat sends the whole PDF text to Anthropic, cannot see figures and needs OCR for scanned PDFs. The README says Paper Chat was tested on macOS but not Windows; this is the author’s statement. Full-version generated fields are currently Chinese, and rebuilding generated pages can overwrite edits. Whole-text transmission applies in either authentication mode: do not use documents that must remain confidential or local. Paper Chat rereads the whole text per question; subscription quotas or per-use API costs apply.

Reproducibility

Source review by AI agent only; no installation, experiment or claimed outcome reproduced.

Adoption requirements

Paper Chat requires Zotero and Claude Code or an Anthropic API key. Skills require Claude Code and Python; the full setup adds Obsidian and Better BibTeX. Review subscription/API costs, document rights, provider transmission and Zotero permissions before adoption.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.