菜单
Extract structured data and entities from existing HTML, Markdown, or text files to audit metadata availability.
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
Normalize named entities and concept variants into canonical forms using controlled vocabularies or standard taxonomies.
Analyze vocabulary overlap and identify named entities unique to domain/document corpora.
Transform lengthy documents into a semantic tree structure. It extracts sections, summaries, and hierarchies optimized for use with Large Language Models (LLMs).
Design formal ontologies using OWL/RDFS. Defines classes, properties, and relationships for complex semantic modeling.
Systematic cataloging of information assets. Creates comprehensive inventories or card sorting materials from content.
Generate JSON-LD structured data for web content. Maps content to Schema.org types to improve search engine understanding and rich result eligibility.
| name | semantic-extract |
| description | Extract structured data and entities from existing HTML, Markdown, or text files to audit metadata availability. |
| required_roles | {"scribe":"roles/scribe.editor"} |
| personas | ["content-strategist","data-analyst"] |
Parse documents to identify and extract existing structured data (tables, lists, headers) and potential entities, converting them into a raw structured format for audit or migration.
PATH - The source document to process.OUTPUT_FORMAT - (Optional) "json", "csv", "yaml" (default: "json").PATH.OUTPUT_FORMAT.A structured object containing the extracted data, keyed by the source element (e.g., "Table 1", "Frontmatter").