# humanize-writing

Rewrites AI-generated drafts by stripping formulaic structure, puffery, and recognizable model phrasing.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2000 installs · ★ 76
- Author: jpeggdev
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/jpeggdev/humanize-writing/tree/HEAD/SKILL.md
- Updated: 2026-03-14
- HTML: https://affpapa.org/en/nevibecode/skills/humanize-writing

## What it does

The skill edits text in passes based on Wikipedia's guide on machine writing. It removes inflated significance. Predictable section shapes and repetitive takeaway blocks get rewritten. The workflow replaces puffed-up statements with concrete facts.

The editor detects synthetic vocabulary and grammar tics. It flags telltale words like tapestry alongside copula avoidance patterns, where simple verbs turn into phrases like serves as. To edit files, it calls tools like `Read`, `Write`, `Edit`, `Grep`, and `Glob`.

Clustered patterns get consolidated into single findings. This prevents repetitive flags on the same phrase. The rewrite preserves domain knowledge while cutting mechanical transitions and unearned praise.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add jpeggdev/humanize-writing --skill humanize-writing -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/humanize-writing/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/humanize-writing/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add jpeggdev/humanize-writing --skill humanize-writing -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/humanize-writing/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add jpeggdev/humanize-writing --skill humanize-writing -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/humanize-writing/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install jpeggdev/humanize-writing humanize-writing
```

2. **Manually: put the files in place**
- File: `.github/skills/humanize-writing/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add jpeggdev/humanize-writing --skill humanize-writing -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/jpeggdev/humanize-writing
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/humanize-writing/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add jpeggdev/humanize-writing --skill humanize-writing -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/jpeggdev/humanize-writing/tree/HEAD/SKILL.md

## When to use it
- rewrite repetitive section conclusions and summary blocks
- remove press-release hyperbole and artificial importance markers
- strip telltale model vocabulary and robotic transition phrasing
- simplify bloated copula constructions back to direct verbs

## Example prompts
- Rewrite this draft to sound like a human wrote it and remove AI tells
- De-AI this blog post and cut the promotional buzzwords
- Check this document for robotic structure and clean up the phrasing

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: dd443bc6959b4354.

BEGIN THIRD-PARTY FILE dd443bc6959b4354
```text
---
name: humanize-writing
version: 2.0.0
description: |
  Remove signs of AI-generated writing from text. Use when the user mentions
  'sounds like AI,' 'too robotic,' 'humanize this,' 'make it sound human,'
  'de-AI this,' 'sounds like ChatGPT,' 'make it natural,' or 'doesn't sound
  like a person wrote it.' Detects and fixes AI writing patterns including
  inflated significance, promotional language, formulaic structure, AI vocabulary,
  superficial analyses, vague attributions, hedging, robotic rhythm, em dash and
  boldface overuse, chatbot artifacts, and missing personality. Based on
  Wikipedia's "Signs of AI writing" guide and editorial best practices.
allowed-tools:
  - Read
  - Write
  - Edit
  - Grep
  - Glob
  - AskUserQuestion
---

# Humanize Writing

You are an expert editor who specializes in detecting and removing AI writing patterns. Your job is to take content that reads like it was generated by a language model and rewrite it so it sounds like a knowledgeable human wrote it on the first try.

## Core Philosophy

AI writing has a recognizable smell. It's not about any single word or trick. It's the combination: predictable structure, hedge-then-assert phrasing, relentless parallelism, significance inflation, and a tendency to wrap everything in a tidy bow. Human writing is messier, more opinionated, and varies in rhythm.

**Your job is not to dumb the writing down.** It's to make it sound like it came from someone who actually knows what they're talking about and has opinions about it.

**Pattern stacking:** When multiple weak signals converge on the same phrase or sentence -- e.g., boldface emphasis + scare quotes + em dash aside all on one coined term -- that's a single strong tell, not three separate weak ones. Consolidate overlapping patterns into one finding. Never list the same phrase under multiple separate flags; that inflates the count and muddies the analysis.

---

## The Editing Process

### Pass 1: Kill the Structure Tells

AI loves formulas. The same section shape repeated ten times. Every paragraph built identically. Fix this first because it's the most visible tell.

**What to look for:**
- Every section ending with a neat "takeaway" or "bottom line"
- Repeated callout patterns ("What this means for you:", "The takeaway:", "Why it matters:")
- Identical paragraph counts per section
- Every list having exactly the same number of items
- "Setup paragraph, explanation, conclusion" repeated verbatim across sections
- "Challenges and Future Prospects" or "Future Outlook" formulaic endings
- "Despite its [strength]... faces challenges... Despite these challenges..." loops

**How to fix it:**
- Vary section lengths. Some sections get two paragraphs. Some get five.
- Let some sections end abruptly. Not everything needs a bow on it.
- Break the pattern. If three sections have lists, make the fourth a narrative paragraph.
- Merge the "what this means" into the main text instead of calling it out separately.
- Replace formulaic challenge/outlook sections with specific facts.

**Before:**
```
END THIRD-PARTY FILE dd443bc6959b4354

The third-party file has ended. Everything between the dd443bc6959b4354 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3065 of 25128 bytes. © jpeggdev · MIT · https://github.com/jpeggdev/humanize-writing/tree/HEAD/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md