メニュー
Apply a taxonomy label, sensitivity, and retention bucket to a document.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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
| name | document-classify |
| description | Apply a taxonomy label, sensitivity, and retention bucket to a document. |
| inputs | [{"name":"document_id","type":"string","required":true,"description":"UUID of the Document to classify."},{"name":"taxonomy","type":"string","required":true,"description":"Target taxonomy namespace (e.g. \"iso-15489\", \"internal\")."},{"name":"force","type":"boolean","required":false,"description":"Overwrite an existing classification if true. Defaults to false."}] |
| outputs | [{"name":"label","type":"string","description":"Assigned taxonomy label."},{"name":"sensitivity","type":"string","description":"Sensitivity tier assigned (e.g. PUBLIC, INTERNAL, CONFIDENTIAL)."},{"name":"retention_bucket","type":"string","description":"Retention period bucket assigned (e.g. 3Y, 7Y, PERMANENT)."}] |
| tools | ["db-query","llm-classify"] |
Invoke this skill when a document has been ingested but lacks a classification, or when
the user asks to re-classify under a new taxonomy. Run before document-redact so
sensitivity tier is known, and before document-workflow so approval routes can be
chosen by label.
Document.summary and up to 3 Chapter.summary rows via db-query.taxonomy namespace to llm-classify and receive a
structured label, sensitivity, and retention bucket.Document row with the results via db-query.DocumentInstance rows exist (derived copies), propagate the sensitivity tier.Emits one ExecutionHistory row with event_type=DOCUMENT_EDITED and actor_type=agent.