LeoYeAI/agent-master-skills / skills/ai-humanizer
humanizer
VerifiedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 24 pattern detectors, 500+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 15.8 KB |
| SKILL.md | skill md | 7.8 KB |
| assets/banner.md | markdown | 331 B |
| docs/CONTRIBUTING.md | markdown | 2.0 KB |
| docs/EXAMPLES.md | markdown | 5.3 KB |
| docs/PATTERNS.md | markdown | 2.4 KB |
| eslint.config.js | script | 559 B |
| package.json | manifest | 1.3 KB |
| references/ai-vocabulary.md | markdown | 5.5 KB |
| references/patterns.md | markdown | 10.0 KB |
| references/style-guide.md | markdown | 3.9 KB |
| scripts/analyze.sh | script | 301 B |
| scripts/humanize.sh | script | 315 B |
| src/analyzer.js | script | 14.8 KB |
| src/cli.js | script | 19.6 KB |
| src/humanizer.js | script | 14.2 KB |
| src/patterns.js | script | 28.1 KB |
| src/stats.js | script | 9.5 KB |
| src/vocabulary.js | script | 15.1 KB |
| tests/analyzer.test.js | script | 13.2 KB |
| tests/calibration.test.js | script | 7.2 KB |
| tests/edge-cases.test.js | script | 7.1 KB |
| tests/fixtures/ai-sample-1.txt | markdown | 2.2 KB |
| tests/fixtures/ai-sample-2.txt | markdown | 1.1 KB |
| tests/fixtures/human-sample-1.txt | markdown | 1.1 KB |
| tests/humanizer.test.js | script | 6.4 KB |
| tests/performance.test.js | script | 3.2 KB |
| tests/statistics.test.js | script | 7.9 KB |
| vitest.config.js | script | 152 B |
docs/PATTERNS.md
View on GitHub# Pattern documentation
Detailed technical documentation for all 24 AI writing patterns detected by humanizer.
## How detection works
Each pattern has a `detect(text)` function that returns an array of matches. Detection uses:
- **Regex matching** for vocabulary words, phrases, and structural patterns
- **Density analysis** for patterns that depend on frequency (em dashes, AI vocab)
- **Heuristic checks** for structural patterns (synonym cycling, rule of three)
## Pattern weights
Patterns are weighted 1-5 based on how strongly they signal AI-generated text:
| Weight | Meaning | Patterns |
|--------|---------|----------|
| 5 | Dead giveaway | AI vocabulary (7), Chatbot artifacts (19) |
| 4 | Strong signal | Significance inflation (1), -ing analyses (3), Vague attributions (5), Cutoff disclaimers (20), Sycophantic tone (21) |
| 3 | Moderate signal | Notability (2), Promotional language (4), Formulaic challenges (6), Copula avoidance (8), Negative parallelisms (9), Inline-header lists (15), Filler phrases (22), Hedging (23), Generic conclusions (24) |
| 2 | Weak signal | Rule of three (10), Synonym cycling (11), False ranges (12), Em dash overuse (13), Boldface overuse (14), Emoji overuse (17) |
| 1 | Minor tell | Title Case headings (16), Curly quotes (18) |
## Scoring algorithm
The AI score (0-100) combines three components:
1. **Density score** (up to 65 points): Weighted matches per 100 words, on a logarithmic scale
2. **Breadth bonus** (up to 20 points): 2 points per unique pattern type detected
3. **Category bonus** (up to 15 points): 3 points per category with hits
The logarithmic curve prevents long texts from getting inflated scores just by having more words to match against.
## Adding new patterns
To add a new pattern to `src/patterns.js`:
1. Define the pattern object with `id`, `name`, `category`, `description`, `weight`, and `detect(text)` function
2. The detect function must return `{ match, index, line, column, suggestion }`
3. Use the `findMatches()` helper for regex-based detection
4. Add tests in `tests/analyzer.test.js`
5. Document in `references/patterns.md`
Example:
```javascript
{
id: 25,
name: 'New pattern name',
category: 'content', // or language, style, communication, filler
description: 'What this pattern is and why it matters.',
weight: 3,
detect(text) {
const regex = /your-pattern-here/gi;
return findMatches(text, regex, 'Suggestion for fixing this pattern.');
},
}
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |