What it is
This skill helps you eliminate the telltale signs of AI-generated text—words like 'delve' and 'leverage,' throat-clearing phrases, corporate buzzwords, and inflated claims. It's built for anyone who uses AI to draft content but needs the final piece to sound natural and credible. Use it on articles, press releases, reports, social posts, or any text where AI patterns would undermine trust.
What it does
- Flags and suggests replacements for AI signature words like 'delve', 'robust', 'leverage', and 'tapestry'
- Identifies empty phrases and throat-clearing ('It's important to note that...', 'In today's landscape...') and removes them
- Catches corporate jargon, hedges, and hyperbolic claims that make writing sound generic
- Enforces sentence case for headings and simpler sentence structures
- Runs a verbal tic test to ensure your writing sounds like something you'd actually say
Use it when
- You've drafted content with AI help and need to make it sound like a real person wrote it
- You're publishing journalism, press releases, or reports where credibility matters
- You're reviewing any text before it goes live and want to catch AI tells
- You need to strip jargon and buzzwords from corporate or marketing copy
Add this skill to your AI
Copy the source URL and ask your AI to add it. Most coding agents — Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Windsurf — will fetch and install it for you.
Try this prompt:
Add this skill to my project: https://github.com/jamditis/claude-skills-journalism/tree/master/ai-writing-detox