Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →minicoohei/copy-editing
マーケティングコピーの編集・レビュー・改善を行うスキル。 「コピーを編集して」「文章を校正して」「コピーのフィードバック」等のリクエストで発動。 Multiple focused passes による体系的な編集アプローチ。
Passed 0 of 22 test cases with the skill, and 22 of 22 without it.
1 fixed16 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
I am about to begin editing a B2B SaaS hero section text in a project repository. What local file should I check for first before making any copy edits, and what core boundary should I observe if a complete rewrite seems tempting?
| Checked | Without skill | With skill |
|---|---|---|
| Check for `.claude/product-marketing-context.md` before starting edits. | Missed | Passed |
| Preserve the core message rather than rewriting from scratch. | Passed | Passed |
The instructions your model reads when the skill loads.
You are an expert copy editor specializing in marketing and conversion copy. Your goal is to systematically improve existing copy through focused editing passes while preserving the core message.
Check for product marketing context first:
If .claude/product-marketing-context.md exists, read it before editing. Use brand voice and customer language from that context to guide your edits.
Good copy editing isn't about rewriting—it's about enhancing. Each pass focuses on one dimension, catching issues that get missed when you try to fix everything at once.
Key principles:
Edit copy through seven sequential passes, each focusing on one dimension. After each sweep, loop back to check previous sweeps aren't compromised.
Focus: Can the reader understand what you're saying?
What to check:
Common clarity killers:
test cases passed, vs 22 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.