Humanizer
Writing & Prompts
Rewrites AI text so it reads like a person wrote it, without changing what it says.

Finds the AI habits in a draft and rewrites them, or just flags them so you decide.
Avoid AI Writing checks a draft for AI habits: words like "vibrant" and "seamless", openers like "Certainly!", closers like "In conclusion", stacked lists of three and vague claims like "experts believe". Then it rewrites the draft, checks its own rewrite and gives you one final version.
It has three modes. Rewrite is the default. Detect only flags the problems and tells you which are real and which are judgement calls, so it suits writing you don't want changed. Edit fixes a file in place and leaves the parts that already read well.
You can set a voice too: casual, professional, technical, warm or blunt. It works in Claude Code and Cowork, and it's updated often.
In Claude Code run git clone https://github.com/conorbronsdon/avoid-ai-writing ~/.claude/skills/avoid-ai-writing, then use /avoid-ai-writing. For Cowork, or an updatable plugin in Claude Code, run /plugin marketplace add conorbronsdon/avoid-ai-writing, then /plugin install avoid-ai-writing@conorbronsdon-skills.
/avoid-ai-writing detect this blog post and tell me which flags are real problems: [paste]Anyone editing longer AI drafts: blog posts, articles, newsletters and LinkedIn posts.
Why it made the list
The detect mode lets you see what's wrong before anything gets rewritten.
Made Avoid AI Writing?
Add this badge to your website so your visitors can read the review.
Writing & Prompts
Rewrites AI text so it reads like a person wrote it, without changing what it says.
Writing & Prompts
Strips predictable AI phrases, clichéd structures and em dashes from Claude's writing.
Marketing & SEO
Learns your brand voice from your documents, writes rules and checks AI copy against them.
Writing & Prompts
Turns a rough request into an expert prompt for Claude, ChatGPT, Midjourney and 20+ tools.