zotero-literature-visualizer skill
The Zotero Literature Visualizer skill finds papers, organizes a Zotero library and builds an interactive literature dashboard.
- 115 ★ on the repository
- Last commit
Extended access
Why this level
- Scripts call external services and write tags and notes into your Zotero library.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/zotero-literature-visualizerDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Scripts call external services and write tags and notes into your Zotero library.
This is third-party code. Review the repository files before installing.
What it does
Zotero Literature Visualizer, a skill for Codex and Claude Code, carries a literature review from topic to dashboard. It searches papers, checks journal quality, reads local Zotero PDFs and writes short summaries in two languages. The finished dashboard is a single HTML file: topic ring, method hotspots, timeline, journals, paper cards and a citation graph from OpenAlex data. Reading marks live in the browser, and `zotero_api_import.py` writes tags and notes back to Zotero.
Who it is for. Researchers and students who keep a literature review in Zotero and want it as a map.
Good fit when
- A Zotero library has grown and topics and methods need grouping.
- A supervisor or group needs an offline single-file dashboard.
- Marks and notes from the dashboard are written back to Zotero.
- Each week you look for new papers added to the collection.
Not a fit when
- You need a citation manager inside Word rather than a review.
- The library is not in Zotero.
- Paper full texts are paywalled and no local PDFs exist.
Example request
Take my Zotero collection on bearing diagnostics, group papers by method and build a single-file HTML dashboard.Limitations
Python 3.10 or newer is required, and `pypdf` is installed separately for PDF reading. The citation graph uses open OpenAlex data, so network access is needed. Impact factor values in the dashboard should be matched against the official source. Write-back to Zotero goes through the API with your key. Agent answers about journals and paper classification should be matched against the primary source before submitting work. The dashboard keeps reading marks in browser localStorage, so switching browsers or clearing site data erases them until exported.
How to disable. Delete the `zotero-literature-visualizer` folder from the skills directory, for example `~/.claude/skills/`. Remove generated dashboards and `SLR:` tags in Zotero separately.
FAQ
How do I install it in Claude Code?
Copy the whole `zotero-literature-visualizer/` folder into `$HOME/.claude/skills/` and open a new session.
Are external libraries required?
Scripts run on the Python 3.10 или новее standard library. Only full-text PDF reading needs `pip install pypdf`.
Can I send the dashboard to a colleague?
Yes. Building with `--inline` produces one self-contained HTML file.
In which languages are summaries and the dashboard?
The dashboard UI switches between Chinese, English and bilingual mode, with light and dark themes.
How do I return marks to Zotero?
Export the write-back package from the dashboard and run `zotero_api_import.py write-back`: the script writes tags in the `SLR:` namespace and item notes.
Discussion
No questions or reviews yet.
Related
SkillsA skill that manages a Zotero library from the terminal: search, adding, notes, collections and merging duplicates.
A Claude Code skill for literature surveys: from a pile of papers to a view of the field via NotebookLM and /survey modes.
A Codex skill that guides a social science paper from topic to citation checks and marks weak spots with risk labels.
A skill that links the agent to your Zotero library through a local JSON CLI with no MCP server: search, PDFs, annotations, notes.
litdb keeps your scientific literature in a local database with semantic search and gives an agent a skill and an MCP server
35 skills for Claude Code and Codex lead a social scientist from idea to a journal manuscript, with scans of participant data.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| zotero-literature-visualizer (this card) | no | 115 | ||
| Zotero MCP | no | not required | 1,278 | gives an agent access to a Zotero library over MCP; this skill builds a literature review dashboard from it |
| Zotero MCP | no | key is optional | 5,884 | searches and reads Zotero items; this adds topic analysis, a citation graph and tag write-back |
README in short
The README presents the skill as a full literature review cycle with a dashboard, a v2 release with reading tracking and instructions for Codex and Claude Code.