Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interact with Zotero reference management libraries using the pyzotero Python client. Retrieve, create, update, and delete items, collections, tags, and attachments via the Zotero Web API v3. Use this skill when working with Zotero libraries programmatically, managing bibliographic references, exporting citations, searching library contents, uploading PDF attachments, or building research automation workflows that integrate with Zotero.
.claude/skills/mkurman-pyzotero/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -9% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -5% | 0% |
|----------| | references/authentication.md | Credentials, library types, local mode | | references/read-api.md | Retrieving items, collections, tags, groups | | references/search-params.md | Filtering, sorting, search parameters | | references/write-api.md | Creating, updating, deleting items | | references/collections.md | Collection CRUD operations | | references/tags.md | Tag retrieval and management | | references/files-attachments.md | File retrieval and attachment uploads | | references/exports.md | BibTeX, CSL-JSON, bibliography export | | references/pagination.md | follow(), everything(), generators | | references/full-text.md | Full-text content indexing and retrieval | | references/saved-searches.md | Saved search management | | references/cli.md | Command-line interface usage | | references/error-handling.md | Errors and exception handling |
pythonitem = zot.item('ITEMKEY') item['data']['title'] = 'New Title' zot.update_item(item)
pythontemplate = zot.item_template('journalArticle') template['title'] = 'My Paper' template['creators'][0] = {'creatorType': 'author', 'firstName': 'Jane', 'lastName': 'Doe'} zot.create_items([template])
pythonzot.add_parameters(format='bibtex') bibtex = zot.top(limit=50) # bibtex is a bibtexparser BibDatabase object print(bibtex.entries)
pythonzot = Zotero(library_id='123456', library_type='user', local=True) items = zot.items()
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | pass→pass | 8,392 | 4,824 | -43% | 1 | 1 | 0% | 1,588 | 1,442 | -9% | 0 | 0 | — |
case-01 | fail→pass | 7,839 | 7,416 | -5% | 1 | 1 | 0% | 1,547 | 2,020 | +31% | 0 | 0 | — |
case-02 | pass→pass | 7,217 | 4,029 | -44% | 1 | 1 | 0% | 1,367 | 1,296 | -5% | 0 | 0 | — |
case-04 | fail→pass | 12,427 | 5,849 | -53% | 1 | 1 | 0% | 2,225 | 1,559 | -30% | 0 | 0 | — |
case-05 | pass→pass | 5,636 | 3,727 | -34% | 1 | 1 | 0% | 950 | 1,242 | +31% | 0 | 0 | — |
case-06 | pass→pass | 7,644 | 3,004 | -61% | 1 | 1 | 0% | 1,414 | 1,062 | -25% | 0 | 0 | — |
case-07 | pass→pass | 8,937 | 3,799 | -57% | 1 | 1 | 0% | 1,566 | 1,225 | -22% | 0 | 0 | — |
case-08 | pass→pass | 9,435 | 3,977 | -58% | 1 | 1 | 0% | 1,740 | 1,219 | -30% | 0 | 0 | — |
case-09 | pass→pass | 8,930 | 4,240 | -53% | 1 | 1 | 0% | 1,592 | 1,366 | -14% | 0 | 0 | — |
case-10 | pass→pass | 6,138 | 3,535 | -42% | 1 | 1 | 0% | 1,079 | 1,140 | +6% | 0 | 0 | — |
case-11 | fail→pass | 9,231 | 4,843 | -48% | 1 | 1 | 0% | 1,662 | 1,424 | -14% | 0 | 0 | — |
case-12 | pass→pass | 15,673 | 8,629 | -45% | 1 | 1 | 0% | 2,837 | 2,141 | -25% | 0 | 0 | — |
case-13 | pass→pass | 3,773 | 3,176 | -16% | 1 | 1 | 0% | 676 | 1,128 | +67% | 0 | 0 | — |
case-14 | pass→pass | 9,409 | 4,928 | -48% | 1 | 1 | 0% | 1,777 | 1,481 | -17% | 0 | 0 | — |
case-15 | pass→pass | 8,410 | 4,810 | -43% | 1 | 1 | 0% | 1,493 | 1,261 | -16% | 0 | 0 | — |
case-16 | pass→pass | 12,244 | 4,555 | -63% | 1 | 1 | 0% | 2,198 | 1,351 | -39% | 0 | 0 | — |
case-17 | pass→pass | 4,646 | 2,759 | -41% | 1 | 1 | 0% | 816 | 1,007 | +23% | 0 | 0 | — |
case-18 | pass→pass | 10,984 | 5,674 | -48% | 1 | 1 | 0% | 1,969 | 1,536 | -22% | 0 | 0 | — |
case-19 | pass→pass | 4,035 | 2,263 | -44% | 1 | 1 | 0% | 620 | 953 | +54% | 0 | 0 | — |
case-20 | pass→pass | 5,757 | 3,766 | -35% | 1 | 1 | 0% | 965 | 1,169 | +21% | 0 | 0 | — |
case-21 | pass→pass | 9,065 | 5,079 | -44% | 1 | 1 | 0% | 1,591 | 1,417 | -11% | 0 | 0 | — |
case-22 | pass→pass | 6,558 | 5,932 | -10% | 1 | 1 | 0% | 1,149 | 1,294 | +13% | 0 | 0 | — |
case-23 | pass→pass | 10,978 | 10,054 | -8% | 1 | 1 | 0% | 2,027 | 2,318 | +14% | 0 | 0 | — |
case-24 | pass→pass | 10,802 | 8,660 | -20% | 1 | 1 | 0% | 2,095 | 2,198 | +5% | 0 | 0 | — |
case-25 | pass→pass | 8,297 | 6,152 | -26% | 1 | 1 | 0% | 1,664 | 1,678 | +1% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted. The headline lift of +12 percentage points is the difference between those two pass rates over the 25 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.