Zotero Analytical Workflow Skills
Seven skills and scripts for the chain Zotero, full text through MinerU, analytical notes in Obsidian and literature search
- 731 ★ on the repository
- Last commit
Extended access
Why this level
- The skills read the local Zotero database and write notes and full texts into the vault, and the converter runs an external utility.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/zotero-analytical-workflow-skillsDetects 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.
- The skills read the local Zotero database and write notes and full texts into the vault, and the converter runs an external utility.
This is third-party code. Review the repository files before installing.
What it does
The set takes an article through the chain Zotero, full text via MinerU, analytical note, knowledge base and literature retrieval. Seven skills divide the work: `zotero-data-fetcher` pulls metadata, annotations and text by a Zotero item key, `zotero-fulltext-archiver` moves the converted PDF into the vault, `zotero-analytical-writer` writes the note, and `zotero-collection-manager` runs a collection in batches with resumption after a failure. Three more belong to the vault: an ingest orchestrator for one paper, knowledge base maintenance and literature retrieval. The research vault has one layout: `01knowledge/` for knowledge, `02vault/` for notes, `03fulltext/` for full texts and a templates folder. The `tools/init_vault.py` script creates missing directories and templates and touches nothing in existing files. Zotero is read through its local SQLite database in read-only mode, and PDF conversion is run by the optional MinerU utility with a timeout and a check that the Markdown is not empty. Validators check the knowledge page schema, Zotero keys, reciprocal links between a note and its full text and file placement. The skills run from Codex and compatible agents, and there is no single command for the whole process.
Who it is for. Researchers and graduate students who keep a paper library in Zotero and notes in Obsidian and want an agent to analyze papers with checks against the full text.
Good fit when
- A Zotero collection has piled up unreviewed papers that have to become analytical notes in batches
- A note needs full text in Markdown while the PDF sits in Zotero attachments
- An interrupted collection run has to continue from where it stopped rather than start over
- A literature question is answered through notes with a step into full text and a return to the PDF for verification
- Before changing the vault you need to check links between a note and its full text with a validator
Not a fit when
- You need to translate or briefly retell a paper: the data fetching skill does not translate or replace the full text
- You do not use Zotero and Obsidian: the chain is built around their structure and keys
- You need a one-shot run without setup: before work you create the vault and set paths in `config.toml`
- You need a summary of someone else's library without access to its files: data comes only from the local Zotero database
Example request
Add the paper with Zotero key ABCD1234 to the vault: fetch the metadata and PDF, prepare the full text and write an analytical note.Limitations
Python 3.11 or newer is required and the bundled scripts use only the standard library. Reading the local database needs Zotero Desktop, while MinerU and ripgrep are optional. The Zotero database can be locked during sync, in which case close Zotero and retry.
The skills are designed as a set for an agent rather than a single program. The process goes paper by paper with a check at each step. The new vault layout uses the `01knowledge/`, `02vault/` and `03fulltext/` directories, and older layouts are moved by hand after a backup.
The author states that the version received skill packaging but no cross-platform acceptance on a live Zotero profile. The scenario descriptions are mostly in English, while some templates and directory names are Chinese. The repository contains no Zotero database, PDFs or keys.
How to disable. Delete the skill folders from the agent's skills directory. The research vault and the `config.toml` file stay with you and the skills do not remove them.
FAQ
Where do I start?
Clone the repository, create a Python 3.11 environment and run `python tools/init_vault.py --vault-root <path>`. Then enter the Zotero and MinerU paths in `config.toml` and run `python tools/check_environment.py`.
Does the set change my Zotero database?
No. The helper reads the local SQLite database in read-only mode and edits nothing in it.
Do I need MinerU?
Only to convert PDFs to Markdown. It is installed separately and its executable path is set in the config.
How do I check the vault?
With the `validate_research_vault_knowledge.py` and `validate_research_vault_literature_links.py` validators. Both are read-only.
Is there a standalone literature retrieval skill?
Yes, it is published in the Research-Vault-Literature-Retrieval repository, and the canonical version also lives in this set.
Discussion
No questions or reviews yet.
Related
SkillsA plugin for academic work: dozens of skills for literature review, experiments, data analysis and paper writing
A CLI that builds a local notes index with catalyst questions so the agent finds material faster than plain grep search
An Obsidian vault with skills for work meetings: Gmail transcripts, participants, follow-up tasks and weekly recaps.
A plugin and skill set that turns an Obsidian vault into a knowledge base with sources, links and grounded answers
Eight Claude Code skills for Obsidian: Granola notes, NotebookLM imports, TaskNotes tasks, recall of past sessions, chat export
Obsidian skills
Obsidian Skills
Skills for agents working with Obsidian: Markdown with wikilinks, Bases, JSON Canvas, Obsidian CLI, Defuddle and Knap
README in short
The README describes requirements, installation, configuration, the vault layout, a quick start with Zotero and MinerU helpers, migration from older layouts and a troubleshooting table. The tests run without a live Zotero profile.