CtrlK
BlogDocsLog inGet started
Tessl Logo

humanizer

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer

Invalid
This skill can't be scored yet
Validation errors are blocking scoring. Review and fix them to unlock Quality, Impact and Security scores. See what needs fixing →
SKILL.md
Quality
Evals
Security

Evaluation results

90%

Tech Blog Post Edit

AI vocabulary and soul injection

Criteria
Without context
With context

AI vocabulary removed

100%

100%

Negative parallelisms removed

100%

100%

Rule of three broken up

100%

100%

Challenges section removed

100%

100%

Generic positive conclusion removed

100%

100%

Vague expert attribution removed

100%

100%

Personality injected

100%

100%

Sentence rhythm varied

100%

100%

Inline-header bullet list converted

100%

100%

Promotional language removed

100%

100%

Em dash reduced

0%

0%

100%

26%

Wikipedia Article Cleanup

Wikipedia-style AI pattern removal

Criteria
Without context
With context

Significance inflation removed

100%

100%

Promotional language removed

100%

100%

Vague attributions replaced

100%

100%

-ing padding removed

100%

100%

Challenges section removed

0%

100%

Copula avoidance fixed

70%

100%

Inline-header list converted

0%

100%

Sentence-case headings

70%

100%

Media notability claim removed

100%

100%

Generic positive conclusion removed

100%

100%

100%

23%

Customer FAQ Cleanup

Chatbot artifact and formatting cleanup

Criteria
Without context
With context

Collaborative artifacts removed

100%

100%

Sycophantic openers removed

100%

100%

Knowledge-cutoff disclaimers removed

100%

100%

Decorative emojis removed

0%

100%

Inline-header lists converted

50%

100%

Negative parallelisms removed

100%

100%

Vague attributions removed

100%

100%

False range removed

100%

100%

Copula substitutes fixed

100%

100%

Sentence-case headings

0%

100%

Repository
softaworks/agent-toolkit
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.