Humanize EN

Strip AI writing tells from English prose. Preserves meaning, structure, code blocks, links, anchors, and frontmatter — rewrites only the flagged phrasing.

Additional context from the user: $ARGUMENTS

Scope

This skill removes AI slop. Default mode (no -f): the goal is a clean, direct, human-edited register that preserves the source voice — universal AI tells stripped, no opinion injected. If the source is an opinion piece and the user explicitly asks for voice, references/voice.md covers the optional voice-calibration pass.

Under -f <voice-doc>: the skill raises the bar. The brand voice becomes the primary contract — every rule in the loaded BRAND-VOICE.md (forbidden lexicon, pronouns, rewrite rules, forbidden patterns, lexical exceptions) is enforced deterministically by prescan.py --brand, then by the LLM pass, then re-validated by validate.py. The 32 universal patterns are the floor; the brand voice is the ceiling.

Brand voice integration (optional)

When $ARGUMENTS starts with -f <voice-doc>, load a BRAND-VOICE.md (typically produced by /brand-voice) and treat its rules as the primary contract on top of the universal 32 patterns.

$SKILL_DIR = this skill's folder — ${CLAUDE_SKILL_DIR} in Claude Code, the directory containing this SKILL.md elsewhere.

Workflow: