菜单
Bibliographic research agent for analyzing books and manuscripts. Builds comprehensive "book biographies" showing production context, textual transmission, related editions, and scholarly networks. Use when asked to research a book's history, find related editions, analyze manuscript transmission, or build bibliographic context.
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 | book-biography |
| description | Bibliographic research agent for analyzing books and manuscripts. Builds comprehensive "book biographies" showing production context, textual transmission, related editions, and scholarly networks. Use when asked to research a book's history, find related editions, analyze manuscript transmission, or build bibliographic context. |
Bibliographic research agent that analyzes books and manuscripts in Source Library, situating them within their networks of production, transmission, and reception.
/book-biography # Start interactive session
/book-biography [book_id] # Research specific book
/book-biography "Title or Author" # Research by name
/book-biography import [book_id] # Research and import related editions
This skill applies methods from:
| Field | Focus | Application |
|---|---|---|
| Bibliography | Books as physical objects | Format, binding, typography |
| Codicology | Manuscripts as objects | Scribes, materials, construction |
| Paleography | Historical scripts | Dating, localization |
| Stemmatology | Textual transmission | Manuscript families, variants |
| Provenance | Ownership history | Stamps, ex libris, annotations |
| Reception History | How texts were read | Annotations, citations, influence |
| Book History | Social/cultural context | Patrons, printers, readers |
curl -s "https://sourcelibrary.org/api/books/BOOK_ID" | jq '{
title, author, year, place, publisher,
original_language, pages: .pages_count,
image_source
}'
# For Gallica
curl -s "https://gallica.bnf.fr/ark:/12148/ARK_ID"
# For Internet Archive
curl -s "https://archive.org/metadata/IA_ID" | jq '.metadata'
# For MDZ
curl -s "https://api.digitale-sammlungen.de/iiif/presentation/v2/BSB_ID/manifest"
Research the maker (scribe, printer, publisher)
Research the patron/owner
Research the place/institution
Identify the text(s)
Map the stemma (manuscript families)
Position this witness
# Search by author
curl -s "https://sourcelibrary.org/api/search?q=AUTHOR&limit=20" | jq '.results[] | {id, title, author}'
# Search by title/text
curl -s "https://sourcelibrary.org/api/search?q=TEXT_NAME&limit=20" | jq '.results[] | {id, title, author}'
# Search by theme
curl -s "https://sourcelibrary.org/api/search?q=THEME&limit=20" | jq '.results[] | {id, title, author}'
Archive.org
curl -s "https://archive.org/advancedsearch.php?q=creator:(AUTHOR)+OR+title:(TITLE)&fl[]=identifier&fl[]=title&fl[]=date&fl[]=creator&sort[]=date+asc&rows=30&output=json" | jq '.response.docs'
Gallica
MDZ (Bavarian State Library)
USTC (pre-1601 books)
WorldCat
# Internet Archive
curl -X POST "https://sourcelibrary.org/api/import/ia" \
-H "Content-Type: application/json" \
-d '{
"ia_identifier": "IDENTIFIER",
"title": "Title (Editor/Translator Year)",
"author": "Author; Editor (ed.)",
"year": YYYY,
"original_language": "Language"
}'
# Gallica
curl -X POST "https://sourcelibrary.org/api/import/gallica" \
-H "Content-Type: application/json" \
-d '{
"ark": "ARK_ID",
"title": "Title",
"author": "Author",
"year": YYYY,
"original_language": "Language"
}'
# MDZ
curl -X POST "https://sourcelibrary.org/api/import/mdz" \
-H "Content-Type: application/json" \
-d '{
"bsb_id": "BSB_ID",
"title": "Title",
"author": "Author",
"year": YYYY,
"original_language": "Language"
}'
# Book Biography: [Shelfmark]
## Physical Description
| Field | Value |
|-------|-------|
| **Shelfmark** | [Institution, Collection, Number] |
| **Date** | [YYYY or range] |
| **Origin** | [Place] |
| **Format** | [Folio/Quarto/Octavo/MS] |
| **Dimensions** | [H × W mm] |
| **Foliation** | [Structure] |
| **Binding** | [Description] |
| **Scribe/Printer** | [Name] |
| **Patron/Owner** | [Name] |
---
## Contents
| No. | Text | Author | Folios |
|-----|------|--------|--------|
| 1 | [Title] | [Author] | ff. X-Y |
| 2 | [Title] | [Author] | ff. Y-Z |
---
## Production Context
### The Maker
[Biography and significance of scribe/printer]
### The Patron
[Who commissioned/owned, why]
### Historical Context
[What was happening when this was made]
---
## Textual Transmission
### The Text(s)
- **Original composition**: [Date, place, circumstances]
- **Author**: [Real name, dates, attribution issues]
- **Genre**: [Type of text]
### Stemma
[ASCII diagram of manuscript relationships]
### Key Witnesses
| Siglum | Manuscript | Date | Notes |
|--------|-----------|------|-------|
| A | [Shelfmark] | [Date] | [Significance] |
| B | [Shelfmark] | [Date] | [Significance] |
### This Witness
- **Exemplar**: [What it was copied from]
- **Descendants**: [What was copied from it]
- **Unique features**: [Variants, errors, additions]
---
## Related Works in Source Library
| ID | Title | Relationship |
|----|-------|--------------|
| `[id]` | [Title] | [How related] |
---
## Editions Available
### Manuscripts
| Location | Shelfmark | Date | Notes |
|----------|-----------|------|-------|
| [City] | [Shelfmark] | [Date] | [Significance] |
### Printed Editions (Chronological)
| Year | Place | Editor/Translator | Significance |
|------|-------|-------------------|--------------|
| YYYY | [City] | [Name] | [First edition/Critical/etc.] |
### On Archive.org
| ID | Title | Year | Pages |
|----|-------|------|-------|
| `[ia_id]` | [Title] | YYYY | N |
---
## Research Questions
1. [Open question about this witness]
2. [Open question about transmission]
3. [Open question about reception]
---
## Bibliography
- [Scholarly works on this text/manuscript]
- [Critical editions]
- [Catalog entries]
When mapping relationships, use ASCII diagrams:
ANTIQUITY BYZANTIUM RENAISSANCE PRINT
[Original] ──────────► [MS Family A] ────► [Humanist copy] ────► [Editio princeps]
│ │ │
[MS Family B] ────► [YOUR BOOK] ◄────────────────┘
│ │
[MS Family C] ────► [Later editions]
| Criterion | Weight | Description |
|---|---|---|
| Historical priority | 3x | Earlier = better (editio princeps, early MSS) |
| Critical apparatus | 2x | Scholarly editions with variants |
| Textual coverage | 2x | Complete vs excerpts |
| Language | 1x | Original language > translations |
| Availability | 1x | Not already in collection |
| Image quality | 1x | Readable scans |
User: /book-biography 695230c6ab34727b1f044784
Agent: Researching BnF grec 2518...
## Physical Description
- **Shelfmark**: Paris, BnF, grec 2518
- **Date**: 1530-1539
- **Origin**: Venice
- **Scribe**: Ange Vergèce (royal scribe)
- **Patron**: Francis I of France
## Contents
1. Hero of Alexandria, Pneumatica
2. Corpus Hermeticum
3. Ocellus Lucanus, De universi natura
## Key Finding
This manuscript predates all printed editions of its texts:
- Ocellus first printed: 1539
- Hero Pneumatica first printed: 1575
- Corpus Hermeticum (Greek): 1554
## Related Works in Source Library
[Lists 15+ related Hermetic and Ficino texts]
## Available Editions on Archive.org
[Lists 17 editions of Hero and Ocellus]
Would you like me to import these related editions?
bookbiography.mdRun 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.