copy-editing improves copy that already exists. The agent first picks a mode: rebuild from the facts, restore a real voice, or make a point edit to one line. Full edits run seven sweeps in order: clarity, voice and tone, so what, prove it, specificity, heightened emotion and zero risk, looping back after each.
It also runs an AI-tell check on every edit and offers a content refresh routine for pages whose stats or examples have gone stale.
What You Get
- Edits from seven single-purpose sweeps, each with a clear reason
- Point edits that return only the changed lines with a one-line reason
- A multi-persona expert panel score for launch, pricing and landing copy
- A quick-pass list of words to cut and weak words to replace
- A refresh plan for outdated pages with a refresh or rewrite decision
Common Use Cases
- Tightening a landing page draft before launch
- Fixing one headline without touching the rest of the page
- Removing contrast reveals and stacked negation lists from AI-written copy
- Refreshing an old post whose traffic is falling
What Makes It Unique
A point edit skips the sweeps and changes only the requested line. The AI-tell check names the shapes that give machine writing away (contrast reveals, negation lists, trailing clauses, colon reveals) and fixes them from the underlying facts. A missing fact is marked as a need the author fills in. An expert panel gate sets a bar of 7 per persona and 8 on average.
Under The Hood
The SKILL.md and three reference files are loaded as context. It ships no scripts and runs no commands. The only file it reads on its own is the product marketing context file in your project. Edits are returned in chat or applied to the copy you point at.