菜单
Create a new document version, diff against the prior version, or roll back to a previous version.
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 | document-version |
| description | Create a new document version, diff against the prior version, or roll back to a previous version. |
| inputs | [{"name":"document_id","type":"string","required":true,"description":"UUID of the Document to version."},{"name":"action","type":"string","required":true,"description":"One of \"create\", \"diff\", or \"rollback\"."},{"name":"target_version","type":"integer","required":false,"description":"Version number to diff against or roll back to. Required for \"diff\" and \"rollback\"."}] |
| outputs | [{"name":"version_number","type":"integer","description":"Version number created or active after the operation."},{"name":"diff_summary","type":"string","description":"Human-readable diff summary; populated for \"diff\" action only."}] |
| tools | ["db-query","diff-engine"] |
Invoke this skill when the user wants to checkpoint a document after edits, compare two versions, or undo a recent change. It should be called after any bulk mutation (summarize, redact, extract) if the user requested version tracking.
Document, Chapter, Section, and Page state into
a new DocumentInstance row tagged with an incremented version number via db-query.DocumentInstance snapshots and pass their text to diff-engine;
return a structured change set.DocumentInstance snapshot to the current working
state by overwriting the live Document rows via db-query.Document.current_version after each write.Emits one ExecutionHistory row with event_type=DOCUMENT_EDITED and actor_type=agent
for "create" and "rollback" actions. "diff" is read-only and emits no row.
Generate a Word document from ingested source documents using the agnostic Document tree (CommonMark/Pandoc-aligned)
Generate a single Document (Word/PowerPoint) from all source documents in a collection, with attributions back to each source
Generate a PDF from ingested source documents using the agnostic Document tree
Generate a PowerPoint deck from ingested source documents using the agnostic Document tree (parametrised by slide_count, style, audience, tone)
Generate an Excel workbook (.xlsx) from ingested source documents — tabular with charts, formulas, KPI cells
Find PII (emails, phones, SSN, credit cards, IBANs, names, addresses, DOB) in an ingested document; return redaction plan