humanise-docx-reportlisted

# Humanise a DOCX report Turn a machine-generated report into one that reads and inspects as human-written, without changing a single fact. Three layers, in order. Do not skip the audit; the audit is what tells you which layers are actually needed. 1. **Audit** - measure before touching anything 2. **Content** - prose, tables, captions 3. **Container and layout** - metadata, embedded media, page geometry Then verify. The verification step is not optional: a rewrite that silently drops a number is worse than no rewrite. ## 0. Always do this first Copy the input to a scratch backup before any write. Work on a copy named `*_humanised.docx` unless the user asks for in-place. Never overwrite the user's original. ```bash python scripts/audit_docx.py INPUT.docx ``` This reports character-level tells, phrase-level tics, sentence rhythm, container fingerprints and layout defects. Read it before deciding what to change. ## 1. Layer A - deterministic character cleanup Verifiable, so state the counts honestly. | Tell | Fix | Why it matters | | --- | --- | --- | | U+2212 MINUS SIGN | `-` (hyphen-minus) | A person typing in Word produces a hyphen. A typesetting engine produces U+2212. Usually the loudest signal in the file. | | Em dash `—` | period, comma, colon or parentheses | Highest-profile AI tell. Target zero in body prose. | | En dash `–` | `to` in numeric ranges, `-` in proper-name compounds | Keep in reference-list page ranges, where it is correct style. | | Invisible /