Use when designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when converting an API or SDK into an agent-usable CLI interface.
日本語の概要は準備中です。原文の説明を表示しています。
Developing with Zotero: Web API v3 (read/write, file upload, sync, OAuth, item types/fields), the desktop client's JS API, plugin development (7-10), translators (web/import/export/search), and CSL/citeproc-js styles. Use when scripting Zotero or building or debugging a plugin, translator, or citation style.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Zotero is an open-source reference manager. Developers extend it three ways: the Web API
(https://api.zotero.org) for online libraries, plugins / the internal JavaScript API for the
desktop client, and translators (JS scrapers/converters). Citations come from CSL styles via
citeproc-js. This skill mirrors https://www.zotero.org/support/dev so you can answer Zotero dev
questions and build integrations without re-fetching.
| File | Covers |
|---|---|
references/web-api.md | Base URL, auth/API keys, versioning, read requests, write requests, batch, file upload, item types/fields, syncing algorithm, streaming API, OAuth |
references/client-and-plugins.md | Internal JavaScript API (Zotero.Items/Item/Search/DB/Notifier), Run JavaScript, plugin development (Zotero 7 bootstrap/manifest), Zotero 10 migration notes, client coding entry points |
references/translators.md | Translator metadata block, detectWeb/doWeb/doImport/doExport/doSearch, scraping helpers (text/attr/ZU), HTTP requests, calling other translators, Scaffold/testing |
references/citation-styles.md | CSL, citeproc-js / citeproc-node, style repository, style editing, type mapping |
references/plugin-gallery.md | Snapshot of the zotero-chinese plugin-store registry (137 plugins by tag + deprecated list) — find similar open-source plugins and study their code before building |
# Read (public library needs no key). HTTPS only. Always pin the version.
curl -H "Zotero-API-Version: 3" -H "Zotero-API-Key: <KEY>" \
"https://api.zotero.org/users/<userID>/items?format=json&limit=25"
# Library prefix: /users/<userID> or /groups/<groupID>
# Common params: format=json|atom|bib|keys|versions, include=bib,citation, q=, itemType=, tag=,
# sort=, direction=, limit=1..100 (def 25), start=, since=<version>
# Response headers: Last-Modified-Version, Total-Results, Link (rel=next/last), Backoff
# Rate limits: honor Backoff; on 429 wait per Retry-After.
# Write (key with write access). Up to 50 objects/request. Must carry a version.
curl -X POST -H "Zotero-API-Key: <KEY>" -H "Content-Type: application/json" \
-H "If-Unmodified-Since-Version: <libVersion>" \
-d '[{"itemType":"book","title":"..."}]' \
"https://api.zotero.org/users/<userID>/items"
# PUT replaces (omitted fields cleared); PATCH merges (only changed fields). 412 = version mismatch.
// Client internal JS API (Run JavaScript / plugin). Most DB/disk/network calls are async.
let item = new Zotero.Item('journalArticle');
item.setField('title', 'Example');
item.setCreators([{ creatorType: 'author', firstName: 'Jane', lastName: 'Doe' }]);
await item.saveTx(); // async, own transaction
let items = ZoteroPane.getSelectedItems(); // window scope
Key endpoints: /itemTypes /itemFields /itemTypeFields?itemType= /itemTypeCreatorTypes?itemType=
/creatorFields /items/new?itemType= · full schema: https://api.zotero.org/schema.
Zotero-API-Version: 3 (production) — never rely on the default.
Pass keys via the Zotero-API-Key header (or Authorization: Bearer), not the key= query param.If-Unmodified-Since-Version header or per-object version).
Missing → 428; mismatch → 412 Precondition Failed (re-fetch, merge, retry). Batch max 50 objects.Backoff header proactively; on 429 wait Retry-After and slow down.mtime is in milliseconds, not seconds. File upload is a 3-step flow (authorize → S3 → register);
new attachment uses If-None-Match: *, replacement uses If-Match: <previous-md5>.await saveTx() / getAsync() / Zotero.DB.executeTransaction(...).
Use saveTx() for single saves; wrap batches in one transaction. Get the Zotero object via
chrome://zotero/content/include.js.detectWeb returns a type / "multiple" /
false; finish items with item.complete(). Use promise helpers (requestText/JSON/Document).
Licensed AGPL v3; submit via PR to zotero/translators. Test in Scaffold.?format=versions + ?since= to diff, store pristine JSON snapshots for 3-way merge, restart the
pass if Last-Modified-Version changes mid-sync. New local objects start at version 0.citation-style-language/styles repo
per its CONTRIBUTING guidelines — don't hand-roll a citation formatter.まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Use when designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when converting an API or SDK into an agent-usable CLI interface.
日本語の概要は準備中です。原文の説明を表示しています。
Search free commercial-use creative assets across multiple online sources — photos, illustrations, icons, video footage, music, sound effects, and fonts. Use when the user needs to find assets for videos, PPTs, articles, or any content creation. Trigger on phrases like "find me a photo of", "search for icons", "I need background music", "find video footage", "search fonts", "找一张图片", "搜素材", "帮我找图标/视频/音乐/字体". Covers Pexels, Unsplash, Pixabay, Iconify, Freesound, Google Fonts and more — with API-backed search where available.
日本語の概要は準備中です。原文の説明を表示しています。
Query the Semantic Scholar academic corpus through AI2's Asta MCP server: keyword or title search with venue and date filters, who-cited-a-paper traversal, author profiles and publications, DOI/arXiv/PMID lookup, and ~500-word full-text snippets for evidence, with citation counts and h-index. Use when the user asks for papers on a topic, who cited a paper, an author's work, recent literature since a date, or a venue-scoped paper list. Requires the Asta MCP server.
日本語の概要は準備中です。原文の説明を表示しています。
Extract and organize frames from a Bilibili video (bangumi episode, UP upload, or a local file) into scenery shots and per-character image groups, using anime-specific person detection + CCIP character-identity embeddings. Two modes — cluster everyone, or pull out one (or several) named characters via reference folders. Use when the user wants to collect, extract, or organize anime frames/screenshots by character or by scenery from a Bilibili video. Read-only download for personal viewing/analysis; uploads nothing.
日本語の概要は準備中です。原文の説明を表示しています。
Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (sentiment, keywords, audience trends). Read-only; does not post/edit/delete.
日本語の概要は準備中です。原文の説明を表示しています。
Use when user requests diagrams, flowcharts, architecture charts, or visualizations. Also use proactively when explaining systems with 3+ components, complex data flows, or relationships that benefit from visual representation. Generates .excalidraw files and exports to PNG/SVG via Kroki API or locally using excalidraw-brute-export-cli.
日本語の概要は準備中です。原文の説明を表示しています。