一键导入
zotero-bib-sync
Use when user wants to sync, push, or add BibTeX entries to a Zotero collection/folder. Handles deduplication by DOI, arXiv ID, or title.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when user wants to sync, push, or add BibTeX entries to a Zotero collection/folder. Handles deduplication by DOI, arXiv ID, or title.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Update skills with concise concrete practices, keeping SKILL.md minimal
Log ML experiments with hyperparameters, metrics, and plots; human interprets results and plans next experiments
Evaluate necessity and difficulty of issues, polish body, and create on GitHub with AI-assisted triage
Research academic papers and questions, write typst documents with cetz visualizations, teach until human understands
Autonomous daily digest of relevant arxiv papers in physics and ML based on your interests
Find, format, and manage academic citations in BibTeX and typst formats
| name | zotero-bib-sync |
| description | Use when user wants to sync, push, or add BibTeX entries to a Zotero collection/folder. Handles deduplication by DOI, arXiv ID, or title. |
Syncs a .bib file to a Zotero collection — creates missing items, skips duplicates.
Add "api_key" to ~/.config/zotero-mcp/config.json:
{
"library_id": "...",
"library_type": "user",
"api_key": "YOUR_KEY_HERE"
}
Generate a key at https://www.zotero.org/settings/keys (enable library write access).
Find the collection key using the mcp__zotero__zotero_get_collections tool — each collection has a Key field.
Run the sync:
cd ~/.claude/skills/zotero-bib-sync && uv run sync.py --bib <path-to-bib> --collection <collection-key>
Dry run (preview without writing):
cd ~/.claude/skills/zotero-bib-sync && uv run sync.py --bib <path-to-bib> --collection <collection-key> --dry-run
Before syncing, always check that each BibTeX entry has a url field. Zotero cannot fetch full text without it. For arXiv papers, add url = {https://arxiv.org/abs/<ID>} derived from the eprint field. For published papers, use the DOI link url = {https://doi.org/<DOI>}.
If items were already synced without URLs, run the add_urls.py script to backfill them:
cd ~/.claude/skills/zotero-bib-sync && uv run add_urls.py
Items are matched by: DOI → arXiv ID (from eprint field) → normalized title. Existing matches are skipped.
| BibTeX | Zotero |
|---|---|
@article | journalArticle |
@inproceedings | conferencePaper |
@book | book |
author | creators |
journal | publicationTitle |
doi | DOI |
eprint | extra (arXiv: ...) |
ID (cite key) | extra (Citation Key: ...) |