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

tests/fixtures/human-sample-1.txt

View on GitHub
I keep going back and forth on AI coding tools. Last week I mass-accepted a bunch of Copilot suggestions in a config file and didn't notice until two days later that one of them referenced a package we'd already ripped out.

The thing is, they're genuinely useful for boilerplate. Test scaffolding, repetitive CRUD endpoints, config files you've written a hundred times before. I wrote a React form component last month that took maybe ten minutes with Copilot where it would've taken thirty without. Fine.

But I've also watched a junior dev on my team accept suggestions for three weeks straight and end up with code that worked, passed CI, and was completely unmaintainable. Nobody caught it until code review, and by then it was a 2000-line PR.

The productivity numbers are squishy. GitHub says 30% of suggestions get accepted, but that's not the same as 30% improvement. Some of those accepted suggestions still need editing. The Uplevel study from last year found basically no difference in PR throughput between teams with and without Copilot.

I still use it. I just don't trust it.
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