tei-xml

What problem does it solve?

This Skill helps you turn historical materials into standardized TEI P5 XML so you can add scholarly metadata, represent manuscript witnesses and variant readings, and reliably query and transform the result for digital editions and downstream analysis.

Core Features & Use Cases

• Build TEI P5 edition structure: generate a TEI document with a teiHeader (fileDesc, encodingDesc, profileDesc) and a text body with divisions and paragraphs.
• Model historical scholarship in XML: encode critical apparatus using app/lem/rdg and mark named entities with persName/placeName/orgName plus authority links (e.g., VIAF).
• Query and transform for analysis and publishing: run XPath queries with lxml to extract named entities and frequency tables, extract apparatus tables, produce plain text, and transform TEI with XSLT/Saxon-HE for HTML or other formats.
• Use Case: You have a corpus of Latin manuscripts and want an AI-assisted pipeline that builds TEI, links persons and places to authority URIs, extracts entity frequency per document, and exports clean plain text for NLP.

Quick Start

Use the tei-xml skill to encode your historical text as TEI P5, link persName/placeName to VIAF or Wikidata URIs, extract named-entity frequency tables with XPath, and transform the TEI into plain text or HTML-ready output.