humanizer

Rewrites text to remove AI-generated writing patterns and restore natural human voice.

Updated Aug 6, 2026
One-click install
npx skills add https://github.com/ferrarifankid04/ai-skills-public --skill humanizer-ferrarifankid04
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: humanizer
Source: https://github.com/ferrarifankid04/ai-skills-public/tree/main/claude-code/skills/humanizer
Command: npx skills add https://github.com/ferrarifankid04/ai-skills-public --skill humanizer-ferrarifankid04

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 detects and rewrites 29 documented AI writing patterns so edited text reads as naturally human. ## Core Features & Use Cases - 29-pattern detection and rewrite: Identifies and fixes content, language, style, and communication patterns from Wikipedia's "Signs of AI writing" guide, with before/after examples for each. - Voice calibration: Analyzes a sample of your own writing to match your sentence rhythm, word choice, and quirks instead of producing generic clean output. - Two-pass anti-AI audit: After a draft rewrite, runs a "what makes this obviously AI generated" review and a second revision to catch lingering tells. - Use Case: Paste an AI-drafted blog post full of "pivotal moments" and "Let's dive in" signposting, and receive a rewritten version with varied rhythm, specific details, and genuine personality. ## Quick Start Ask the assistant 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 ask for it to be humanized. The skill scans for 29 known AI writing patterns—like significance inflation, rule-of-three lists, and chatbot artifacts—rewrites each problem section, then runs a second audit pass to catch remaining tells.

What AI writing patterns does humanizer detect?

It detects 29 patterns from Wikipedia's Signs of AI writing guide, covering content issues (promotional language, vague attributions), language issues (AI vocabulary, copula avoidance, negative parallelisms), style issues (em dash overuse, boldface, emojis), and filler or hedging phrases.

Can humanizer match my personal writing style?

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

Does humanizer work with Claude Code and OpenCode?

Yes. The skill installs into ~/.claude/skills/humanizer for Claude Code or ~/.config/opencode/skills for OpenCode. OpenCode also scans the Claude skills directory, so one clone works for both tools.

Will humanizing text change its meaning?

No. The process explicitly preserves the core message and intended tone while replacing AI-isms with natural alternatives. It favors specific details over vague claims and keeps the rewrite faithful to the original content.