Skip to content

LeoYeAI/agent-master-skills / skills/ai-humanizer

humanizer

Verified

Humanize 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.

FileKindSize
README.mdmarkdown15.8 KB
SKILL.mdskill md7.8 KB
assets/banner.mdmarkdown331 B
docs/CONTRIBUTING.mdmarkdown2.0 KB
docs/EXAMPLES.mdmarkdown5.3 KB
docs/PATTERNS.mdmarkdown2.4 KB
eslint.config.jsscript559 B
package.jsonmanifest1.3 KB
references/ai-vocabulary.mdmarkdown5.5 KB
references/patterns.mdmarkdown10.0 KB
references/style-guide.mdmarkdown3.9 KB
scripts/analyze.shscript301 B
scripts/humanize.shscript315 B
src/analyzer.jsscript14.8 KB
src/cli.jsscript19.6 KB
src/humanizer.jsscript14.2 KB
src/patterns.jsscript28.1 KB
src/stats.jsscript9.5 KB
src/vocabulary.jsscript15.1 KB
tests/analyzer.test.jsscript13.2 KB
tests/calibration.test.jsscript7.2 KB
tests/edge-cases.test.jsscript7.1 KB
tests/fixtures/ai-sample-1.txtmarkdown2.2 KB
tests/fixtures/ai-sample-2.txtmarkdown1.1 KB
tests/fixtures/human-sample-1.txtmarkdown1.1 KB
tests/humanizer.test.jsscript6.4 KB
tests/performance.test.jsscript3.2 KB
tests/statistics.test.jsscript7.9 KB
vitest.config.jsscript152 B

docs/CONTRIBUTING.md

View on GitHub
# Contributing to humanizer

Thanks for your interest in improving AI writing detection.

## Getting started

```bash
git clone https://github.com/brandonwise/humanizer.git
cd humanizer
npm install
npm test
```

## What to work on

- **New patterns** — Found an AI writing pattern not covered? Add it
- **Better detection** — Improve regex accuracy, reduce false positives
- **More vocabulary** — Expand the AI word/phrase lists
- **Test cases** — Add fixtures that expose detection gaps
- **Documentation** — Improve examples, add before/after pairs

## Adding a new pattern

1. Add the pattern definition to `src/patterns.js` (see `docs/PATTERNS.md` for the format)
2. Write tests in `tests/analyzer.test.js`
3. Add documentation to `references/patterns.md`
4. Run `npm test` — everything must pass

## Improving detection

The main source of false positives is overly broad regex. When tightening patterns:

- Add word boundary markers (`\b`)
- Use context-aware matching (surrounding words matter)
- Test against both AI samples and human samples
- Check that human text doesn't get flagged unfairly

## Code style

- Pure Node.js, no external runtime dependencies
- CommonJS modules (`require`/`module.exports`)
- No build step — the code runs directly
- Comments explain *why*, not *what*
- Functions are small and single-purpose

## Tests

- All tests use vitest
- Run with `npm test`
- Test each pattern detector individually
- Include both positive matches (should detect) and negative cases (should not detect)
- Test fixtures go in `tests/fixtures/`

## Pull request process

1. Fork the repo and create a branch (`git checkout -b add-pattern-25`)
2. Make your changes
3. Run `npm test` — all tests must pass
4. Open a PR with a clear description of what changed and why
5. Include before/after examples for any new patterns

## Reporting issues

Found a false positive? A missed pattern? Open an issue with:

- The text that was incorrectly flagged (or missed)
- Which pattern is involved
- What you expected to happen
- What actually happened
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 implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall