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.

86

1.09x
Quality

78%

Does it follow best practices?

Impact

100%

1.09x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./prompts/humanizer/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

Editing a Community Arts Festival Profile

Personality injection and content pattern removal

Criteria
Without context
With context

Personality present

100%

100%

Varied sentence rhythm

100%

100%

Complexity acknowledged

100%

100%

Significance puffery removed

100%

100%

Promotional language removed

100%

100%

Participial phrase cleanup

100%

100%

Vague attribution removed

100%

100%

Challenges section rewritten

100%

100%

Generic conclusion replaced

100%

100%

AI vocabulary removed

100%

100%

Rule of three broken up

100%

100%

Changes documented

100%

100%

100%

6%

Cleaning Up a Product Announcement Blog Post

Language and grammar pattern removal

Criteria
Without context
With context

AI vocabulary removed

100%

100%

Copula avoidance fixed

70%

100%

Negative parallelism removed

100%

100%

False range removed

62%

100%

Vague attribution removed

100%

100%

Synonym cycling fixed

100%

100%

Rule of three reduced

100%

100%

Filler phrases removed

100%

100%

Copula restored in specific cases

100%

100%

Changes documented

100%

100%

100%

19%

Polishing an Internal Newsletter Section

Style, formatting, and communication pattern cleanup

Criteria
Without context
With context

Emojis removed

100%

100%

Inline-header list converted

0%

100%

Title case headings fixed

25%

100%

Collaborative artifacts removed

100%

100%

Sycophantic tone removed

100%

100%

Knowledge-cutoff disclaimer removed

100%

100%

Excessive hedging removed

100%

100%

Em dash overuse reduced

62%

100%

Generic conclusion replaced

100%

100%

Challenges section rewritten

100%

100%

Changes documented

100%

100%

Repository
jdrhyne/agent-skills
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.