skills/43-wentorai-research-plugins/skills/writing/citation/zotero-api/SKILL.md
Reference management library and collections API
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research zotero-apiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Zotero is a free, open-source reference management software designed to help researchers collect, organize, cite, and share bibliographic references. The Zotero Web API provides programmatic access to user and group libraries stored on Zotero servers, enabling integration with research workflows, automated bibliography management, and custom tool development.
The API supports reading and writing items (books, journal articles, conference papers, web pages, and dozens of other item types), organizing items into collections, managing tags, retrieving attachment metadata, and accessing shared group libraries. It follows RESTful conventions and supports JSON and Atom response formats, making it straightforward to integrate with existing research infrastructure.
Researchers, librarians, research software developers, and digital humanities scholars use the Zotero API to build literature review tools, automate citation workflows, synchronize reference libraries across platforms, generate bibliographies programmatically, and create custom research management dashboards. The API is particularly popular in digital humanities projects where large bibliographic datasets need programmatic manipulation.
Authentication is optional for reading public libraries but required for accessing private libraries and all write operations. Zotero uses API keys for authentication.
Zotero-API-Key header# Authenticated request
curl -H "Zotero-API-Key: YOUR_API_KEY" "https://api.zotero.org/users/USER_ID/items"
# Public group library (no auth needed)
curl "https://api.zotero.org/groups/GROUP_ID/items"
Your user ID can be found at https://www.zotero.org/settings/keys alongside your API key settings.
Retrieve, search, and manage items in a user's personal Zotero library.
GET https://api.zotero.org/users/{userID}/items| Parameter | Type | Required | Description |
|------------|--------|----------|----------------------------------------------------------|
| userID | int | Yes | Zotero user ID (in URL path) |
| q | string | No | Quick search query (searches title, creator, year) |
| qmode | string | No | Search mode: titleCreatorYear or everything |
| itemType | string | No | Filter by type: journalArticle, book, conferencePaper, etc. |
| tag | string | No | Filter by tag (can be repeated for multiple tags) |
| sort | string | No | Sort field: dateAdded, dateModified, title, creator |
| direction | string | No | Sort direction: asc or desc |
| limit | int | No | Results per request (default 25, max 100) |
| start | int | No | Pagination offset |
| format | string | No | Response format: json (default), atom, bib, keys |
# Get all journal articles tagged "machine learning"
curl -H "Zotero-API-Key: YOUR_KEY" \
"https://api.zotero.org/users/12345/items?itemType=journalArticle&tag=machine+learning&format=json"
# Search for items by keyword
curl -H "Zotero-API-Key: YOUR_KEY" \
"https://api.zotero.org/users/12345/items?q=neural+networks&format=json"
key, version, data (with itemType, title, creators, abstractNote, date, DOI, url, tags, collections, relations), and links.Access items in shared group libraries, which are commonly used for collaborative research projects and reading groups.
GET https://api.zotero.org/groups/{groupID}/items| Parameter | Type | Required | Description |
|-----------|--------|----------|-----------------------------------------------------|
| groupID | int | Yes | Zotero group ID (in URL path) |
| q | string | No | Quick search query |
| itemType | string | No | Filter by item type |
| tag | string | No | Filter by tag |
| sort | string | No | Sort field |
| limit | int | No | Results per request (max 100) |
| start | int | No | Pagination offset |
| format | string | No | Response format: json, atom, bib, keys |
# List items in a public group library
curl "https://api.zotero.org/groups/67890/items?format=json&limit=50"
# Get formatted bibliography from a group
curl "https://api.zotero.org/groups/67890/items?format=bib&style=apa"
No strict rate limits are enforced, but Zotero asks users to limit requests to a reasonable rate. The API uses conditional requests via If-Modified-Since-Version headers for efficient synchronization. Responses include a Last-Modified-Version header that should be stored and used in subsequent requests to only retrieve changed items. Batch operations are supported for creating/updating multiple items in a single request (up to 50 items per write request).
Generate a formatted bibliography from a Zotero collection:
import requests
headers = {"Zotero-API-Key": "YOUR_KEY"}
# Get items formatted as APA bibliography
resp = requests.get(
"https://api.zotero.org/users/12345/collections/ABCDEF/items",
headers=headers,
params={"format": "bib", "style": "apa", "limit": 100}
)
print(resp.text)
Efficiently synchronize Zotero items using version tracking:
import requests
headers = {"Zotero-API-Key": "YOUR_KEY"}
last_version = 0 # Store this between syncs
resp = requests.get(
"https://api.zotero.org/users/12345/items",
headers={**headers, "If-Modified-Since-Version": str(last_version)},
params={"format": "json", "limit": 100}
)
if resp.status_code == 200:
items = resp.json()
last_version = resp.headers["Last-Modified-Version"]
for item in items:
print(f"Updated: {item['data'].get('title', 'No title')} (v{item['version']})")
elif resp.status_code == 304:
print("No changes since last sync")
Explore the thematic distribution of a research library:
import requests
from collections import Counter
headers = {"Zotero-API-Key": "YOUR_KEY"}
resp = requests.get(
"https://api.zotero.org/users/12345/items",
headers=headers,
params={"format": "json", "limit": 100, "itemType": "journalArticle"}
)
tag_counts = Counter()
for item in resp.json():
for tag in item["data"].get("tags", []):
tag_counts[tag["tag"]] += 1
for tag, count in tag_counts.most_common(20):
print(f" {tag}: {count}")
tools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.