humanizer

Detect and rewrite AI-generated writing patterns to produce natural human-sounding text.

Updated May 27, 2026
One-click install
npx skills add https://github.com/baljinnyamday/autonomous-red-team-agent --skill humanizer-baljinnyamday
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: humanizer
Source: https://github.com/baljinnyamday/autonomous-red-team-agent/tree/main/paper/.agents/skills/humanizer
Command: npx skills add https://github.com/baljinnyamday/autonomous-red-team-agent --skill humanizer-baljinnyamday

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated text carries recognizable tells—inflated significance, promotional language, em dash overuse, rule-of-three lists, chatbot artifacts—that make writing sound robotic and erode reader trust. This Skill systematically detects and rewrites those patterns so text reads as naturally human. ## Core Features & Use Cases - 30-Pattern Detection: Identifies content, language, style, and communication patterns from Wikipedia's "Signs of AI writing" guide, each with before/after examples. - Draft-Audit-Final Loop: Produces a draft rewrite, runs an "obviously AI generated" audit pass, then delivers a final revision with no em or en dashes. - Voice Calibration: Analyzes a sample of your own writing to match your sentence rhythm, word choice, and quirks instead of producing generic output. - Use Case: Paste an AI-drafted blog post or essay and receive a rewrite that preserves meaning and structure while removing chatbot artifacts, filler phrases, and formulaic constructions. ## Quick Start Ask the agent to humanize your pasted text, optionally including a sample of your own writing for voice matching.

Frequently Asked Questions about humanizer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make AI-generated text sound more human?

Paste the text and invoke the humanizer skill. It scans for 30 known AI writing patterns, produces a draft rewrite, audits the draft for remaining tells, and delivers a final version that preserves your meaning and paragraph structure.

What AI writing patterns does this detect?

It detects 30 patterns across content, language, style, and communication categories, including significance inflation, vague attributions, AI vocabulary words, em dash overuse, rule of three, chatbot artifacts, and filler phrases, based on Wikipedia's Signs of AI writing guide.

Can I match my own writing style when humanizing text?

Yes, provide 2-3 paragraphs of your own writing as a voice sample. The skill analyzes your sentence rhythm, word choices, and punctuation habits, then applies them to the rewrite instead of producing generic clean output.

Does humanizing text work with Claude Code and OpenCode?

Yes, the skill is compatible with both Claude Code and OpenCode. Install it by cloning into ~/.claude/skills/humanizer or ~/.config/opencode/skills/humanizer; OpenCode also scans the Claude skills directory.

Will humanizing remove legitimate human writing quirks?

The skill includes false-positive guidance to avoid gutting legitimate prose. It looks for clusters of tells rather than isolated ones and preserves human signals like specific details, mixed feelings, varied sentence length, and genuine asides.