zotero-management
Skill68 starsChanged 7 months agoMITView on GitHub
Manages a Zotero academic reference library through both the local API (localhost:23119, read-only) and the Web API (api.zotero.org, read-write), using a structured collection hierarchy (Inbox / Active Projects / Background / Reading Queue / Archive / Meta) plus project, status, priority, and type tags. Handles adding papers with full metadata, deduplication, attaching provenance notes, moving items between collections, updating tags after reading, listing the prioritized reading queue, and setting up the literature scaffold for a new project. Use when the user asks to add / save / file / organize a paper in Zotero, check / list / clean up the reading queue, move papers between collections, tag papers for a project, query their library ("what do I have on X?"), or set up Zotero for a new research project.
- Reads credentials
In this repository6 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
Use tags to cross-cut the collection hierarchy:
- Distinctive: line 75
Check for duplicates: Search existing library by title
- Distinctive: line 76
Present summary to user: Don't auto-add — confirm first
- Distinctive: line 79
All available metadata fields
- Very specific: line 109
Update tag: #to-read → #read or #summarized
- Distinctive: line 110
Add reading notes as a child note item
- Distinctive: line 115
When starting a new project:
- Very specific: line 116
Create a project tag (e.g., #NewProject)
- Distinctive: line 117
Do initial literature search (use literature-search skill)
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Zotero Library Management
Systematic management of an academic literature library via Zotero.
When to Use
- User asks to add a paper to Zotero
- User asks to check their reading queue
- User wants to organize papers for a project
- User asks "what's in my library about X?"
- User asks to clean up or reorganize collections
Library Structure
Standard collection hierarchy:
00_Inbox → Newly added, unprocessed papers
10_Active Projects → Papers actively being used in current work
20_Background → General domain knowledge, surveys, textbooks
30_Reading Queue → Papers to read, prioritized
40_Archive → Completed projects, historical reference
90_Meta → Templates, style guides, writing resourcesTag System
Use tags to cross-cut the collection hierarchy:
- Project tags:
#Inception,#AI-Scientist-BioAge,#ChemRetro,#CAST - Status tags:
#to-read,#reading,#read,#summarized - Priority tags:
#urgent,#high,#low - Type tags:
#survey,#method,#benchmark,#position-paper
API Access
Two access modes:
| Mode | Endpoint | Capability |
| Local API | localhost:23119 | Read-only, fast, requires Zotero running |
| Web API | api.zotero.org | Read-write, works always, needs API key |
# Check if Zotero is running locally
curl -s http://localhost:23119/api/users/0/items?limit=1
# Web API (read-write)
curl -s -H "Zotero-API-Key: $ZOTERO_API_KEY" \
"https://api.zotero.org/users/$ZOTERO_USER_ID/items?limit=5"Workflows
Adding a Paper
- Find metadata: Get title, authors, year, venue, DOI/arXiv ID
- Check for duplicates: Search existing library by title
- Present summary to user: Don't auto-add — confirm first
- Add to Zotero via Web API with:
- Correct item type (journalArticle, conferencePaper, preprint)
- All available metadata fields
- Collection:
30_Reading Queue(default) or user-specified - Tags: project tag +
#to-read
- Attach notes: Source link (social media post, blog, etc.) as a note
Checking Reading Queue
# Get items in Reading Queue collection
curl -s -H "Zotero-API-Key: $ZOTERO_API_KEY" \
"https://api.zotero.org/users/$ZOTERO_USER_ID/collections/<COLLECTION_KEY>/items?limit=50"Present as a prioritized list:
📚 Reading Queue (N papers)
🔴 Urgent:
1. [Paper Title] — added [date], tagged #Inception
🟡 High priority:
2. [Paper Title] — added [date], tagged #AI-Scientist-BioAge
⚪ Normal:
3. ...After Reading a Paper
- Move from
30_Reading Queueto10_Active Projectsor20_Background - Update tag:
#to-read→#reador#summarized - Add reading notes as a child note item
- Link to project if relevant
Project Literature Setup
When starting a new project:
- Create a project tag (e.g.,
#NewProject) - Do initial literature search (use literature-search skill)
- Batch-add relevant papers to
30_Reading Queuewith project tag - Prioritize: which papers must be read first?
Key Principles
- Confirm before adding — always show summary, let user decide
- Preserve provenance — record where you found the paper (social media link, search query)
- One source of truth — Zotero is the canonical library; don't maintain parallel lists
- Tags cross-cut collections — a paper can be in one collection but tagged for multiple projects
- Regular maintenance — periodically review Inbox and Reading Queue for stale items
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

