npx skills add smithery/FuZhiyu --skill zotero-paper-reader
fuzhiyu/superra · Archived
zotero-paper-reader
Use Zotero to find, read, summarize, cite, or export academic papers. Use for paper lookup, library searches, attachments, BibTeX, and draft citation work.
Installation
npx skills add fuzhiyu/superra --skill zotero-paper-reader
Stronger alternatives
This repository is archived — consider an actively maintained alternative.
Install or refresh generated superRA named Codex agents in project (.codex/agents) or global (~…
2 installsEconomic data-analysis discipline. Use for importing, cleaning, merging, filtering, variables, …
1 installsCoordinate superRA agents and handoffs. Requires superRA:using-superra. Use to dispatch roles, …
1 installsMarkdown style guide for task files, status reports, and standalone reports. Use when writing o…
1 installsSimilar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Interact with Zotero reference management libraries using the pyzotero Python client. Retrieve,…
1.4K installsRead and analyze academic papers from Zotero library. Use when the user requests to read, acces…
598 installs>- CLI harness for Zotero.
464 installsUse this skill when Zotero is the literature source of truth and the project KB should receive …
415 installsInteract with your Zotero library to sync references, add citations by DOI/ISBN/PMID, and manag…
209 installsAlso in this package
Other skills from fuzhiyu/superra · top by installs.
npx skills add fuzhiyu/superra
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Also listed on
Alternate registries and mirrors of this skill.
Repository health
main
Package contents
Files included with this skill beyond the listing page.
-
skill md
SKILL.md4,617 B -
docs
SUMMARY.md182 B
History
- First seen on skills.sh
- First recorded snapshot · 1 installs
SKILL.md
Zotero Paper Reader
Search, retrieve, and analyze papers from a Zotero library via pyzotero. Defaults to the Zotero Desktop local API; falls back to the Zotero Web API when local Zotero is unavailable.
Access Model
Run the bundled tool with uv run --script <skill-dir>/scripts/zotero_tool.py, where <skill-dir> is the directory containing this SKILL.md — substitute the real path. It detects the access mode automatically.
Load [references/access-modes.md](references/access-modes.md) for fallback rules, credential setup, or access-mode troubleshooting.
Paper-Reading Workflow
Load [references/paper-reading.md](references/paper-reading.md) for exact invocations, JSON field names, disambiguation logic, parent-item hydration on full-text hits, and troubleshooting.
- Search:
zotero_tool.py search "query"— plain metadata search;--fulltextfor indexed content (local or web). - Identify top-level item: inspect
data.itemTypeon each hit; attachment hits from--fulltextneed parent hydration viadata.parentItem. - Choose: present concise metadata when multiple top-level papers match; ask the user only if the intended paper cannot be inferred.
- Get PDF attachment key:
zoterotool.py children ITEMKEY→ find child withdata.contentType == "application/pdf". - Get PDF path:
zoterotool.py pdf ATTACHMENTKEY→ emits{"source": ..., "path": ...}. - Convert to markdown: invoke the
mistral-pdf-to-markdownskill with the PDF path; save toNotes/PaperInMarkdown/AuthorYearShortTitle.md. - Read and analyze: in sections — abstract and introduction first, then targeted sections.
Library Query Commands
| Goal | Command |
|---|---|
| List libraries (user + groups) | libraries |
| Metadata search (title/creator/year) | search "query" |
| Full-text search (indexed content; local or web) | search "query" --fulltext |
| Single item | item ITEM_KEY |
| Child items / attachments | children ITEM_KEY |
| Attachment full-text retrieval (one attachment) | fulltext ATTACHMENT_KEY |
| PDF path or download | pdf ATTACHMENT_KEY |
| All collections | collections |
| All tags | tags |
| DOI-to-key index | doiindex |
BibTeX export + master-.bib sync |
bibtex --item-key KEY (or --query "text" / --doi DOI) |
Insert a citation into a draft + sync .bib |
cite --item-key KEY --tex FILE --bib PATH (or --markdown FILE) |
| Render formatted references | bibliography --item-key KEY (default APA) |
| Health / access check | health |
All commands emit JSON. Add --help to any subcommand for parameter details.
Targeting a library. Commands default to the user's own library ("My Library"). For a group library, run libraries first to get the group ids, then pass --library <group-id> (or --library group:<id>) — e.g. search "your query" --library <group-id>. Works on search, item, children, collections, tags, fulltext, doiindex, pdf, bibtex, cite, and bibliography.
Citations & BibTeX
bibtex, cite, and bibliography generate citations from selected library items. Citekeys come from the researcher's Better BibTeX (BBT) by default, falling back to Zotero's built-in translator — with a key-mismatch warning — when BBT is unreachable. All three share the --item-key / --query / --doi selection flags, --library targeting, and the dedup-append .bib sync.
Load [references/bibtex-citations.md](references/bibtex-citations.md) for command examples, the full flag list (--bib / --tex / --markdown / --marker / --style), the BBT-vs-built-in key model and fallback semantics, JSON fields, and troubleshooting.
Configuration
Credentials come from environment variables, else Notes/.env; they are never printed to the agent transcript. Web API mode needs ZOTEROLIBRARYID, ZOTEROLIBRARYTYPE (default user), ZOTEROAPIKEY. Local mode needs none. Details in [references/access-modes.md](references/access-modes.md).
Resources
- [
scripts/zoterotool.py](scripts/zoterotool.py) — unified pyzotero command surface (pinned to pyzotero 1.13.0 via PEP 723 inline metadata) - References — [
paper-reading.md](references/paper-reading.md), [access-modes.md](references/access-modes.md), [bibtex-citations.md](references/bibtex-citations.md); load conditions in the sections above