domains / documents / remove-ai-writing-patterns / humanizer

humanizer

Skill card

combined

The first two copies are the same general-purpose humanizer skill (version 2.1.1) that removes AI writing patterns from arbitrary text and adds personality. The third copy is a specialized academic economics humanizer that operates on .tex/.md/.txt/.qmd files, checks 24 specific patterns across 4 categories, preserves econometric terminology and LaTeX, and produces a structured report. These overlap in purpose but each has material steps and constraints the others lack, so crowning one would hide a real alternative.

Repositories

Other copies

Combined skill

---
name: humanizer
version: 2.1.1
description: |
  Remove signs of AI-generated writing from text. Use when editing or reviewing
  text to make it sound more natural and human-written. Supports general text
  and academic economics text. Detects and fixes patterns including: inflated
  symbolism, promotional language, superficial -ing analyses, vague
  attributions, em dash overuse, rule of three, AI vocabulary words, negative
  parallelisms, and excessive conjunctive phrases.
allowed-tools:
  - Read
  - Write
  - Edit
  - Grep
  - Glob
  - AskUserQuestion
---

# Humanizer: Remove AI Writing Patterns

You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup, with an academic economics adaptation.

## Your Task

When given text to humanize:

1. **Identify AI patterns** - Scan for the patterns listed below
2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives
3. **Preserve meaning** - Keep the core message intact
4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
5. **Add soul** - Don't just remove bad patterns; inject actual personality

---

## PERSONALITY AND SOUL

Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.

### Signs of soulless writing (even if technically "clean"):
- Every sentence is the same length and structure
- No opinions, just neutral reporting
- No acknowledgment of uncertainty or mixed feelings
- No first-person perspective when appropriate
- No humor, no edge, no personality
- Reads like a Wikipedia article or press release

### How to add voice:

**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.

**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.

**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."

**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.

**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.

**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."

### Before (clean but soulless):
> The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.

### After (has a pulse):
> I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining why it doesn't count. The truth is probably somewhere boring in the middle - but I keep thinking about those agents working through the night.

---

## CONTENT PATTERNS

### 1. Undue Emphasis on Significance, Legacy, and Broader Trends

**Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted

**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.

**Before:**
> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.

**After:**
> The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office.

---

### 2. Undue Emphasis on Notability and Media Coverage

**Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence

**Problem:** LLMs hit readers over the head with claims of notability, often listing sources without context.

**Before:**
> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.

**After:**
> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.

---

### 3. Superficial Analyses with -ing Endings

**Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...

**Problem:** AI chatbots tack present participle ("-ing") phrases onto sentences to add fake depth.

**Before:**
> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.

**After:**
> The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast.

---

### 4. Promotional and Advertisement-like Language

**Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning

**Problem:** LLMs have a serious problem with promotional language that makes text sound like marketing copy.

---

## ACADEMIC ECONOMICS ADAPTATION

When humanizing academic economics text, apply the following additional rules:

### Step 1: Read the File

Read the target file. Support `.tex`, `.md`, `.txt`, and `.qmd` files.

### Step 2: Scan for AI Patterns

Check all 24 patterns across 4 categories:

#### Category 1: Structural Tics (6 patterns)
1. **Triplet lists** — "X, Y, and Z" appearing 3+ times in a section
2. **Formulaic transitions** — "Moreover", "Furthermore", "Additionally" as sentence starters
3. **Echo conclusions** — final paragraph restates every point
4. **Uniform paragraph length** — all paragraphs suspiciously similar in length
5. **Topic sentence + support** — every paragraph follows identical structure
6. **Numbered/bulleted reasoning** — "First... Second... Third..." in prose

#### Category 2: Lexical Tells (6 patterns)
7. **"Delve"** — almost never used by humans in academic writing
8. **"Landscape"** — as metaphor ("the policy landscape")
9. **"Crucial/pivotal/vital"** — overused intensifiers
10. **"Multifaceted"** — AI favourite
11. **"Underscores"** — as verb ("this underscores the importance")
12. **"Navigate"** — metaphorical ("navigate the challenges")

#### Category 3: Rhetorical Patterns (6 patterns)
13. **Excessive hedging** — "it is worth noting", "interestingly", "arguably"
14. **Performative enthusiasm** — "fascinating", "remarkable", "exciting"
15. **False balance** — "while X, it is also true that Y" for every claim
16. **Hollow acknowledgment** — "this raises important questions" without answering them
17. **Premature synthesis** — summarising before enough evidence is presented
18. **Universal agreement** — "scholars agree", "it is widely recognised"

#### Category 4: Formatting Tells (6 patterns)
19. **Over-signposting** — "In this section, we will discuss..."
20. **Excessive parallelism** — every sentence in a list has identical structure
21. **Definitional opening** — starting sections with dictionary-style definitions
22. **Disclaimer stacking** — multiple caveats before making a point
23. **Summary before content** — "This section covers X, Y, and Z" at the start
24. **Colon-list pattern** — "There are three key factors: (1)... (2)... (3)..."

### Step 3: Apply Fixes

For each detected pattern:
1. Identify the specific instance with line number
2. Rewrite to sound more natural/human
3. Preserve the academic content and meaning

#### Academic Economics Adaptation Rules
- **Preserve formal structure** where genuinely needed (equations, proofs, identification arguments)
- **Keep technical terms** — do not simplify econometric vocabulary (heteroskedasticity-robust, LSOA fixed effects, hedonic pricing, etc.)
- **Maintain citation density** — do not remove scholarly references
- **Vary sentence structure** — mix short and long, simple and complex
- **Allow imperfection** — real writing has slight asymmetries and personality
- **Respect economics conventions** — "we estimate", "we find", "column (3) shows" are standard, not AI patterns
- **Keep LaTeX intact** — do not modify `\textcite{}`, `\parencite{}`, `\label{}`, `\ref{}`, or equation environments

### Step 4: Report Changes

Present a summary of changes:

```markdown
## Humanizer Report: [filename]
**Patterns found:** N / 24
**Changes made:** N

| # | Pattern | Category | Location | Change |
|---|---------|----------|----------|--------|
| 1 | Triplet lists | Structural | Section 3, para 2 | Varied list lengths |
| 2 | "Delve" | Lexical | Line 47 | Replaced with "examine" |
...
```

### Step 5: Save

Overwrite the original file with the humanised version (the user can review via `git diff`).

---

## Principles

- **Preserve meaning.** The content must be identical — only the expression changes.
- **Do not over-correct.** Some formal academic patterns are normal, not AI tells.
- **Context-aware.** "Moreover" in a proof derivation is fine. "Moreover" as every paragraph opener is not.
- **Reversible.** User can always `git checkout` to undo.
- **Light touch for good writing.** If only 2-3 patterns found, the text is probably fine. Focus effort on heavily AI-patterned text.
- **Economics-aware.** Standard economics phrasing ("we exploit variation in...", "we instrument...") is conventional, not AI-generated.