菜单
Create a DOI-ready scholarly edition of a translated book. Use when asked to publish, create an edition, mint a DOI, or prepare a book for scholarly publication. Generates front matter, creates versioned editions, builds EPUBs, and mints DOIs via Zenodo.
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
| name | scholarly-edition |
| description | Create a DOI-ready scholarly edition of a translated book. Use when asked to publish, create an edition, mint a DOI, or prepare a book for scholarly publication. Generates front matter, creates versioned editions, builds EPUBs, and mints DOIs via Zenodo. |
Create a complete, citable scholarly edition of a translated historical text with DOI.
Before starting, verify the book has:
Authentication: Steps 2, 3, and 5 require admin authentication. When running as a Claude Code agent, requests go through the local dev server or use session cookies automatically. For manual curl commands, you need an authenticated session.
First, get the book ID and check its readiness:
# Get book details and page statistics
curl -s "https://sourcelibrary.org/api/books/BOOK_ID" | jq '{
title: .title,
display_title: .display_title,
author: .author,
language: .language,
published: .published,
pages_count: .pages_count,
pages_translated: .pages_translated
}'
The book API returns pages_count and pages_translated as cached counts. Confirm pages_translated equals pages_count before proceeding. For detailed page-level text, use /api/books/BOOK_ID/text?content=translation.
Generate the scholarly Introduction and Methodology sections:
curl -X POST "https://sourcelibrary.org/api/books/BOOK_ID/editions/front-matter" \
-H "Content-Type: application/json" \
-d '{}'
This creates:
Save the response to use when creating the edition.
Create a versioned edition with the generated front matter:
curl -X POST "https://sourcelibrary.org/api/books/BOOK_ID/editions" \
-H "Content-Type: application/json" \
-d '{
"version_label": "First Edition",
"license": "CC-BY-4.0",
"changelog": "Initial scholarly edition with AI-assisted translation.",
"contributors": [
{"name": "Source Library", "role": "editor", "type": "ai"},
{"name": "ORGANIZATION_NAME", "role": "editor", "type": "human"}
],
"front_matter": {
"introduction": "INTRODUCTION_TEXT",
"methodology": "METHODOLOGY_TEXT",
"generated_at": "ISO_DATE",
"generated_by": "gemini-3-flash-preview"
}
}'
Note the returned edition_id for the next step.
Test the scholarly EPUB download:
curl -sL "https://sourcelibrary.org/api/books/BOOK_ID/download?format=epub-scholarly" \
-o /tmp/scholarly-test.epub
# Check file size
ls -lh /tmp/scholarly-test.epub
The EPUB should include:
Mint a permanent DOI for the edition:
curl -X POST "https://sourcelibrary.org/api/books/BOOK_ID/editions/mint-doi" \
-H "Content-Type: application/json" \
-d '{"edition_id": "EDITION_ID"}'
This will:
The response includes:
doi: The permanent DOI (e.g., 10.5281/zenodo.12345678)doi_url: The resolvable DOI URLzenodo_url: Direct link to Zenodo recordValid SPDX license identifiers:
CC-BY-4.0 - Attribution (recommended for scholarly work)CC-BY-SA-4.0 - Attribution-ShareAlikeCC-BY-NC-4.0 - Attribution-NonCommercialCC-BY-NC-SA-4.0 - Attribution-NonCommercial-ShareAlikeCC0-1.0 - Public DomainFollow semantic versioning:
1.0.0 - First published edition1.1.0 - Minor corrections, improved translations2.0.0 - Major revision, new translationsAfter completion, provide:
| Field | Value |
|---|---|
| Book | [Title] |
| Edition | [Version] - [Label] |
| Pages | [Count] translated |
| DOI | [DOI] |
| DOI URL | [URL] |
| Zenodo Record | [URL] |
| License | [License] |
| EPUB Download | ?format=scholarly |
Run OCR and translation quality evaluations across scripts and languages. Produces research-grade reports with MCR, cross-model agreement, embedding-space hallucination detection, and corpus readiness scores.
Run a Glass Bead Game session — a parlor game played against the Source Library corpus. Players connect verified passages from different books, times, and traditions into a growing string of 'beads,' with Claude as librarian, verifier, and scribe. Trigger when the user says 'glass bead game,' 'let's play beads,' or asks to start/resume/publish a game session. Claude runs the search-verify-display loop; humans do the noticing, choosing, and judging.
Stage-2 verification of first-translation flips using INDEPENDENT Claude subagents (subscription, not API key) with full evidence capture. Use to verify proposed badge changes (demotes/promotes) before writing any public claim — the binding step that catches AI-fabricated priors. Each subagent reports its actual search queries + sources, persisted to the first_translation_attempts provenance log.
Triage and respond to the user-feedback queue — pull open feedback, detect items already fixed but never marked, route translation-requests and metadata-corrections, mark items resolved, and (on approval) email submitters. Use when asked to check/triage/answer/clear feedback, "what are people saying?", or "respond to feedback."
Sweep Claude's private per-machine memory for team-relevant operational knowledge and propose moving it into the shared repo (or the private ops repo) as draft PRs. Use to promote lessons that accreted privately, or run on a schedule. Never auto-merges; never leaks.
One-shot audience & usage report — signups, DAU/MAU, time on-site, traffic, top content, search behavior, referrers, countries, and user journeys. Use when asked "what's our usage?", "how many signups?", "time on site?", "traffic?", or any audience/engagement metrics question.