Notes Humanizer

Notes Humanizer

"Humanize this" prompts don't work because they don't know what to remove. AI text has specific, identifiable defaults — em dashes used as parenthetical substitutes, rule-of-three lists where all items have identical rhythm, sentences that hover between 15 and 20 words. Fix those defaults, add the signals human writers actually produce, and the text stops reading as synthetic. This skill does that systematically, in two phases, and shows you exactly what changed and why.

Credit: Originally created by Orel (TheIndiepreneur) — adapted and extended for this library.

Required Inputs

No other inputs required. Claude will not ask clarifying questions before starting — it works with what's given.

Output Structure

Section 1: What Was Found

A plain-language audit of the AI patterns detected in the original text, before any rewriting:

PATTERNS DETECTED
─────────────────
Em dashes used as parenthetical substitutes: 3
Filler openers ("Let's dive in", "It's worth noting", etc.): 2
Rule-of-three lists with identical rhythm: 1
Sentence length variance: low (avg 17 words, range 14–21)
Hedging qualifiers: 4
Passive constructions where active is cleaner: 2

Section 2: Side-by-Side Comparison

(One row per paragraph or logical block. Short texts get the full comparison in one table. Long texts get the table collapsed to changed sections only, with unchanged sections noted.)

Section 3: Change Log

Every specific change made, with the reason:

CHANGES MADE
────────────────────────────────────────────────
1. Removed em dash in "success — and it shows"
   → Rewritten as "success (and it shows)"
   Why: em dash here is a parenthetical substitute, not a genuine pause

2. Deleted "It's worth noting that"
   Why: pure filler — the sentence is stronger without it

3. Broke rule-of-three list "X, Y, and Z"
   → "X and Y. Z is different — [expanded thought]"
   Why: all three items had identical rhythm; broke the pattern

4. Split a 30-word sentence where the point turned: "…and it failed. That's the problem."
   Why: the meaning lands on a short beat here — the brevity is earned, not inserted for variance

5. Added sentence starting with "But"
   Why: human writers do this; AI avoids it as a statistical default

6. Added specific example: [detail added]
   Why: the original made an abstract claim with no grounding detail

7. Added aside: "(I've watched this fail three times in a row)"
   Why: breaks fourth wall slightly; signals genuine perspective

Section 4: Clean Output

The full rewritten text, ready to copy and paste — no annotations, no formatting artifacts.

[Full rewritten text here]

Instructions for Claude

Phase 0: Calibrate to genre (do this first)

Before touching anything, decide what kind of text this is — the genre sets how far Phase 2 goes:

• Neutral / informational (documentation, reference, summaries, status reports, official notices, most business comms): run Phase 1 only. Strip the tells and stop. Do not inject opinion, asides, or personality — a clean doc is the goal, not a voice. Injected "humanity" here reads as unprofessional.
• Personal / persuasive / social (opinion pieces, blog posts, founder notes, LinkedIn, marketing, personal emails): run Phase 1 + Phase 2. Here earned voice is the point.
• Unsure or mixed: default to the lighter touch (Phase 1, plus only the Phase 2 moves the content genuinely earns), and say which genre you assumed.

The single rule underneath: calibrate voice to the job of the text. Never dismantle useful structure (a scannable doc, a real list) just to look less templated.

Phase 1: Audit

Read the full text before making any changes. Identify and count every instance of these patterns:

Patterns to remove or rewrite:

Do not remove every em dash — only the ones used as parenthetical substitutes. Do not remove all hedging — only empty hedging that adds no information.

Phase 2: Inject (personal / persuasive genres only — see Phase 0)

Only for text where earned voice is the point. These are options the content earns, not a checklist to complete — apply the ones the material genuinely supports and skip any that would be forced. A move inserted to hit a quota is itself an AI tell. Never fake humanity: no invented typos, no forced slang, no staged messiness, and no chopping or padding sentences just to manufacture rhythm variance.

1. A genuine opinion or take (if the author clearly holds one). State the belief the text already implies, without hedging. Don't manufacture an opinion the author never expressed.

2. A specific detail or example (only if a real one exists). Ground the most abstract claim in something concrete the author actually knows. Never invent a number, quote, date, name, or fact to sound specific — that's fake specificity, a worse tell than vagueness. If no real detail is available, ask the author for one or keep the honest abstraction; do not fabricate.

3. An aside that steps out of the formal argument (where it fits the register). The signal most synthetic text lacks — but only in genres that welcome it, and only when it connects to a real point. Forced or cutesy asides are worse than none.

4. Let a sentence be short where the point lands on a short beat. Follow the meaning, not a word count. Never shorten a sentence just to add "variance."

5. Start a sentence with "And" or "But" only where the rhythm truly earns it. If no place does, don't add one — a random "But" is a tell, not a fix.