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 |
tests/edge-cases.test.js
View on GitHub/**
* edge-cases.test.js — Edge case tests.
*
* Empty text, single word, unicode, non-English, very long text.
*/
import { describe, it, expect } from 'vitest';
import { analyze, score } from '../src/analyzer.js';
import { computeStats } from '../src/stats.js';
// ─── Empty / Minimal Input ───────────────────────────────
describe('empty and minimal input', () => {
it('handles empty string', () => {
const result = analyze('');
expect(result.score).toBe(0);
expect(result.totalMatches).toBe(0);
expect(result.wordCount).toBe(0);
});
it('handles whitespace-only string', () => {
const result = analyze(' \n\n\t ');
expect(result.score).toBe(0);
});
it('handles null', () => {
const result = analyze(null);
expect(result.score).toBe(0);
});
it('handles undefined', () => {
const result = analyze(undefined);
expect(result.score).toBe(0);
});
it('handles single word — score is low', () => {
const result = analyze('hello');
expect(result.score).toBeLessThanOrEqual(15);
expect(result.wordCount).toBe(1);
});
it('handles single character — score is low', () => {
const result = analyze('x');
expect(result.score).toBeLessThanOrEqual(15);
});
it('handles number-only input — score is low', () => {
const result = analyze('12345');
expect(result.score).toBeLessThanOrEqual(15);
});
it('statistics handles empty string', () => {
const stats = computeStats('');
expect(stats.sentenceCount).toBe(0);
expect(stats.wordCount).toBe(0);
});
it('statistics handles single word', () => {
const stats = computeStats('hello');
expect(stats.wordCount).toBe(1);
expect(stats.typeTokenRatio).toBe(1);
});
});
// ─── Unicode & Special Characters ────────────────────────
describe('unicode and special characters', () => {
it('handles emoji text', () => {
const result = analyze('🎉 Hello world! 🚀 Great day! ✅ Done!');
expect(result.score).toBeGreaterThanOrEqual(0);
expect(result.score).toBeLessThanOrEqual(100);
});
it('handles Chinese text', () => {
const result = analyze('这是一个测试。人工智能正在改变世界。');
expect(result.score).toBeGreaterThanOrEqual(0);
});
it('handles Japanese text', () => {
const result = analyze('これはテストです。AIは世界を変えています。');
expect(result.score).toBeGreaterThanOrEqual(0);
});
it('handles Arabic text', () => {
const result = analyze('هذا اختبار. الذكاء الاصطناعي يغير العالم.');
expect(result.score).toBeGreaterThanOrEqual(0);
});
it('handles mixed unicode and ASCII', () => {
const text = 'The café is très bien. Über cool. Naïve approach.';
const result = analyze(text);
expect(result.score).toBeGreaterThanOrEqual(0);
});
it('handles HTML entities', () => {
const result = analyze('This & that <tag> content.');
expect(result.score).toBeGreaterThanOrEqual(0);
});
it('handles special whitespace characters', () => {
const result = analyze('Hello\u00A0world\u2003test\u200Bhidden');
expect(result.score).toBeGreaterThanOrEqual(0);
});
it('statistics handles non-English gracefully', () => {
const stats = computeStats('这是一个测试。人工智能正在改变世界。');
expect(stats.sentenceCount).toBeGreaterThanOrEqual(0);
});
});
// ─── Very Long Text ──────────────────────────────────────
describe('very long text', () => {
it('handles 1000 identical sentences', () => {
const text = Array(1000).fill('The cat sat on the mat.').join(' ');
const result = analyze(text);
expect(result.score).toBeGreaterThanOrEqual(0);
expect(result.score).toBeLessThanOrEqual(100);
});
it('handles text with thousands of newlines', () => {
const text = Array(500).fill('Line of text.\n').join('');
const result = analyze(text);
expect(result.score).toBeGreaterThanOrEqual(0);
});
it('statistics handles very long text', () => {
const text = Array(500).fill('The cat sat on the mat.').join(' ');
const stats = computeStats(text);
expect(stats.wordCount).toBeGreaterThan(100);
expect(stats.typeTokenRatio).toBeLessThan(0.1);
});
});
// ─── Malformed Input ─────────────────────────────────────
describe('malformed input', () => {
it('handles text with only punctuation — score is low', () => {
const result = analyze('...!!!???---');
expect(result.score).toBeLessThanOrEqual(15);
});
it('handles extremely long single word', () => {
const word = 'a'.repeat(10000);
const result = analyze(word);
expect(result.score).toBeGreaterThanOrEqual(0);
});
it('handles text with excessive whitespace', () => {
const result = analyze('Hello world this is spaced');
expect(result.wordCount).toBeGreaterThanOrEqual(4);
});
it('handles markdown-heavy text', () => {
const text =
'# Heading\n\n**bold** _italic_ ~~strike~~ `code`\n\n- item 1\n- item 2\n- item 3\n\n> blockquote\n\n```\ncode block\n```';
const result = analyze(text);
expect(result.score).toBeGreaterThanOrEqual(0);
});
it('handles text with URLs', () => {
const text =
'Check out https://example.com and http://test.org/path?query=1&foo=bar for more info.';
const result = analyze(text);
expect(result.score).toBeGreaterThanOrEqual(0);
});
});
// ─── Score Bounds ────────────────────────────────────────
describe('score bounds', () => {
it('score is always 0-100', () => {
const inputs = [
'',
'hello',
'The cat sat.',
'Additionally, this serves as a testament.',
'Great question! I hope this helps! Let me know!',
];
for (const input of inputs) {
const s = score(input);
expect(s).toBeGreaterThanOrEqual(0);
expect(s).toBeLessThanOrEqual(100);
}
});
it('maximum AI text does not exceed 100', () => {
const text = `Great question! Here is a comprehensive overview.
Additionally, this serves as a testament to the transformative tapestry of the evolving landscape. In today's rapidly evolving digital age, these groundbreaking tools — nestled at the forefront of innovation — are showcasing the vibrant interplay of technology, highlighting its pivotal role and underscoring the crucial importance of seamless synergy.
Experts believe it plays a crucial role. Studies show improvement. Industry reports suggest growth. Despite challenges, the ecosystem continues to thrive. It's not just a tool, it's a revolution.
In order to help, due to the fact that you asked, at this point in time, it is important to note that the future looks bright. Exciting times lie ahead. I hope this helps! Let me know if you'd like me to expand.`;
const s = score(text);
expect(s).toBeLessThanOrEqual(100);
expect(s).toBeGreaterThanOrEqual(60);
});
});
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 |