text-humanizer-instruction-based
Detect and rewrite AI-generated writing patterns, em dashes, rule-of-three lists, sycophantic openers, hollow buzzwords like "delve" and "landscape", and replace them with direct, human-sounding prose.
Best for Job application prepWorks with GitHubLow risk
⌘source
- author
@LeoYeAI- language
- Python
★2kstars
306forks
May 6, 2026
✦overview.md
Key Features
- ·Detects AI writing tells
- ·Rewrites to human-sounding prose
- ·No external API calls
- ·Applies paired rewrite rules
Use Cases
- →When user pastes text and asks to 'humanize' or 'de-AI'
- →When user mentions specific AI tells like 'delve' or em dashes
- →When content is for a job application or academic submission
Best for
- ✓Job application prep
- ✓Academic writing cleanup
Not ideal for
- !Creative writing
- !Technical documentation
name
text-humanizer-Instruction-based
description
Detect and rewrite AI-generated writing patterns, em dashes, rule-of-three lists, sycophantic openers, hollow buzzwords like "delve" and "landscape", and replace them with direct, human-sounding prose.
version:1.0.0
homepage:https://github.com/arbazex/text-humanizer-Instruction-based
metadata:{"openclaw":{"emoji":"✍️"}}
Overview
This skill detects AI writing "tells", specific words, phrases, punctuation habits, and structural patterns that consistently appear in LLM-generated text, and rewrites them to sound like a human wrote them. It does not call any external API. The agent's own language capability reads the text, identifies the patterns from the master list below, applies the paired rewrite rule for each hit, and returns clean prose. Use this whenever someone asks to "humanize," "de-AI," or "make this sound less like a bot."
When to use this skill
Trigger when the user:
- Says "humanize this," "make this sound human," "de-AI this," or "this sounds like ChatGPT"
- Pastes text and asks to "rewrite," "clean up," or "edit" it and the text shows two or more patterns from the master list below
- Asks to "remove AI words," "fix the robot-speak," or "make this sound like I wrote it"
- Mentions specific tells: "too many em dashes," "sounds too formal," "why does it say 'delve,'" "every list has three things," "it keeps saying 'certainly'"
- Submits content for a job application, article, academic work, or social post and wants it to sound authentic
Do NOT trigger this skill for:
$install
1-click copynpx skills add LeoYeAI/openclaw-master-skills --skill text-humanizer-instruction-basedSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
4/ 5
highMostly actionable with clear steps; only a few small gaps remain.