Tell Desk - find what makes your draft read as machine-generated, then fix it

Paste a README, changelog, PR description, blog post, investor update or LinkedIn post. Free in your browser: every pattern that makes prose read as machine-generated - tiered vocabulary (delve, seamless, pivotal), em dashes, hedge stacks, "it's not X, it's Y", chatbot sign-offs, vague attributions, unfilled placeholders, leaked citation tokens and utm_source=chatgpt.com links, uniform sentence rhythm - flagged with its quoted evidence, marked in your text and weighted for the context you write in; quotations and code are never flagged. Then an audit lane answers every flag and finds what a pattern cannot, and a rewrite lane removes the tells without adding a first person, a dash or an invented fact - rescanned by the page. Every flag is a writing-quality signal; it classifies nothing. Derived from @wshobson/avoid-ai-writing (Seth Hobson, wshobson/agents, MIT; catalogue from conorbronsdon/avoid-ai-writing, MIT).

Every public app is built from a security-scanned skill and must pass a clean scan — skill and frontend — before it can be listed. Have a skill of your own? Turn it into an app — or read the step-by-step walkthrough.