Zotero Connect logo

Zotero Connect

Community
sagirimo
zotero-connect

Read and extend the user's own Zotero 7 library through the local desktop app — search papers, list collections and tags, pull PDF full text for summarising, add references by DOI/PMID, and export BibTeX/RIS/CSL-JSON. Never deletes or edits existing items.

Overview

Publishersagirimo
RepositoryBioDSH
Skill namezotero-connect
Stars
65
Forks
2
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by sagirimo on GitHub. Read the source before you install it.

Installation

Install the Zotero Connect AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/sagirimo/BioDSH/tree/main/biodsh-core/skills/zotero-connect
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/sagirimo/BioDSH.git /tmp/BioDSH
mkdir -p .claude/skills
cp -r /tmp/BioDSH/biodsh-core/skills/zotero-connect .claude/skills/zotero-connect
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Zotero Connect in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Zotero Connect on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Zotero Connect is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Zotero connect (local library)

Use this skill when the user talks about their own reference library: "帮我在 Zotero 里找…", "把这篇加到 Zotero", "总结我库里关于 X 的 PDF", "导出这几篇的 BibTeX", or when a literature-review task should end with references saved into Zotero. It talks only to the Zotero desktop app on this computer (http://127.0.0.1:23119) — no cloud account, no API key.

Prerequisite (tell the user if ping fails): Zotero 7 must be open, and in Zotero → Settings(设置) → Advanced(高级) the option "Allow other applications on this computer to communicate with Zotero" (允许本机其他应用与 Zotero 通信) must be checked. Adding items uses the Zotero Connector endpoint, which is always on while Zotero runs.

Commands

All commands print JSON to stdout; on failure they print {"error": ...} and exit 1.

bash
python "<skill dir>/zotero.py" ping                                   # is Zotero running + local API enabled?
python "<skill dir>/zotero.py" search --q "PD-1 melanoma" [--limit 50] [--collection KEY] [--everything]
python "<skill dir>/zotero.py" collections                            # key, name, parent, item count
python "<skill dir>/zotero.py" tags
python "<skill dir>/zotero.py" item --key ABCD1234                    # full record + attachments with local PDF paths
python "<skill dir>/zotero.py" pdf-text --key ABCD1234 [--max-chars 20000]
python "<skill dir>/zotero.py" add --doi 10.1038/s41586-020-2649-2    # Crossref → Zotero
python "<skill dir>/zotero.py" add --pmid 32939066                    # PubMed (E-utilities) → Zotero
python "<skill dir>/zotero.py" add --json items.json [--yes]          # list of Zotero items or {"doi":..}/{"pmid":..}
python "<skill dir>/zotero.py" resolve --doi 10.xxxx/yyy              # metadata preview only, Zotero not needed
python "<skill dir>/zotero.py" export --keys K1,K2 --format bibtex|csljson|ris --out exports/refs.bib

search returns compact rows: key, title, authors, year, journal, DOI, tags, has_pdf, date_added. Default matching is title/creator/year; add --everything to also match abstracts, notes and indexed full text. --collection KEY restricts to one collection (get keys from collections).

pdf-text needs pymupdf; if the error says so, run uv pip install pymupdf and retry. It reads the PDF straight from the Zotero storage folder (~/Zotero/storage/<key>/…; override with ZOTERO_DATA_DIR if the user moved it).

The loop

  1. ping — if it errors, stop and tell the user exactly how to enable the local API (the error text already contains the settings path in English and Chinese).
  2. search (optionally collections first, then --collection) — report the hits with their Zotero keys.
  3. item / pdf-text for the papers the user picks — summarise from the extracted text, quoting the item key.
  4. add / export as the task requires — report every new item key and the collection it landed in.

Rules

  • Never delete or modify existing items. This script has no delete/update commands; do not try to work around that with other tools.
  • add skips DOIs already in the library (reported as already_in_library with the existing key). Use --force only if the user explicitly wants a duplicate.
  • Confirm with the user before adding more than 10 items. The script refuses >10 without --yes; ask, show the candidate list, then rerun with --yes.
  • New items are saved into the collection currently selected in the Zotero window (or My Library). Tell the user this, and report the new item keys (add returns them; if it says sent_to_zotero, run search --q "<title>" a few seconds later to fetch the key).
  • Always report Zotero item keys when you cite library items, so the user can find them (Zotero: search the key, or item --key).
  • For literature-review tasks combine with web search: find candidate papers online → present title/journal/year/DOI to the user → after confirmation, add --doi … (or --pmid …) for each → finish with export if the user needs a bibliography.
  • Metadata sources are Crossref (api.crossref.org) and NCBI E-utilities; both are public and need no key (NCBI_API_KEY / CROSSREF_MAILTO are optional env vars for polite rate limits). Nothing in this skill uploads the user's library anywhere.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Zotero Connect AI skill do?

Read and extend the user's own Zotero 7 library through the local desktop app — search papers, list collections and tags, pull PDF full text for summarising, add references by DOI/PMID, and export BibTeX/RIS/CSL-JSON. Never deletes or edits existing items.

Why use Zotero Connect on TypingMind?

Because you install it once and use it with any model. Zotero Connect is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Zotero Connect in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sagirimo/BioDSH/tree/main/biodsh-core/skills/zotero-connect. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Zotero Connect?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Zotero Connect?

As many as you like. As long as a model supports skills, you can use Zotero Connect with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Zotero Connect AI skill free?

Yes. It is published on GitHub by sagirimo under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇