Publisher: Corey Haines · Editorial profile by AI Tools Ratings · Review method
Not runtime tested; source-document review only. No security certification.
What task is this skill designed for?
Rewrite one landing-page section using verified product facts and customer language, with a clear call to action and no invented proof points.
What input and output should you expect?
Input: The existing draft or brief, approved product facts, target audience, primary action and any evidence supporting testimonials or quantitative claims.
Output: Expected, not independently tested: a page section or draft with an explicit argument, audience fit and proposed CTA. Conversion improvement requires a separate measurement or experiment.
What does it need to run?
An agent that can read the skill format and access the approved marketing context. No ad account, publishing permission or analytics integration is necessary for a local draft.
The author repository publishes Agent Skills-format instructions. Client-specific installation and tool dependencies must be checked; no Codex, Claude Code or Cursor runtime compatibility is independently verified here.
How should you approach installation?
- Read the pinned source and license, then assemble approved product facts.
- Load the skill in an agent-supported environment and begin with a single local section.
- Review factual accuracy and voice before approving publication or an experiment.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Reads product and customer context and writes copy. Customer quotes, logos and performance claims need permission and evidence before public use. Drafting is separate from publishing to a live page.
What does the skill cost?
The repository provides the skill under MIT. Agent usage, customer research and experimentation services have separate costs.
What are its limits and alternatives?
Persuasive wording cannot validate an unsupported product promise. Do not repeat quantitative examples from the source as if they were results for your business. Voice quality and conversion outcomes need review by the actual audience.
Use a copy-editing workflow when the structure and argument are already settled. Choose copywriting when the section needs a clearer offer, audience framing or action path.
What could you ask in a small trial?
Try this with a small sample:
Edit only this hero section for the stated audience. Preserve the founder’s vocabulary, use only the attached verified facts, and give two CTA options. Identify any claim that lacks supporting evidence.
How would you verify the result?
- Trace every numeric or comparative claim to approved evidence.
- Check that a reader can identify the product, audience and next action.
- Test the published version against a defined baseline before claiming a conversion lift.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
MIT — identified in LICENSE at the reviewed commit. Third-party assets and dependencies may have separate terms. License evidence
Version details and review scope
Source: coreyhaines31/marketingskills/skills/copywriting
Reviewed commit: e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b
SKILL.md SHA-256: 13c580c2432a4499e9dfdcf5d553df7aa6589e90cf5bd869fb4fbde5caf9f567
Source-document review. Source text and stated dependencies were inspected for this profile. Referenced code was not comprehensively audited, no runtime test was performed, and source files are not mirrored here.