Strip AI tells from a draft blog post before publishing
Quando usar: You drafted a post with Claude, and it reads like every LinkedIn thought-leader post from 2025.
Pré-requisitos
- Skill installed — git clone https://github.com/blader/humanizer ~/.claude/skills/humanizer
Fluxo
-
DiagnoseUse humanizer. Analyze /drafts/post.md. List the AI tells — em-dashes, rule-of-three, hedged opener, generic adjectives — with counts.✓ Copiado→ Concrete tell inventory, not vibes
-
Rewrite conservativelyRewrite paragraph by paragraph. Change only the AI tells. Keep my voice. Show diff.✓ Copiado→ Minimal diff, voice preserved
-
Spot-checkRead the revised version aloud (just the first 200 words). Does it still sound like me?✓ Copiado→ Sampled read; flag anything that drifted
Resultado: A post that doesn't trigger the AI-detection reflex in readers.
Armadilhas
- Over-aggressive rewrite flattens your actual voice — Run conservatively first; only escalate sentence-by-sentence on problem areas