Publisher: Corey Haines · Editorial profile by AI Tools Ratings · Review method
Not runtime tested; source-document review only. Referenced scripts were not executed or comprehensively audited. No security certification.
What task is this skill designed for?
Audit a submission page for qualified completed submissions and propose one experiment.
What input and output should you expect?
Input: Approved page content, audience, traffic source, primary action and any actual funnel data with its observation window.
Output: Prioritized changes, test ideas and copy options; expected, not independently tested. The audit does not establish uplift.
What does it need to run?
An Agent Skills-capable client, product-marketing context and the task-specific form or experiment reference files.
Publisher README declares support for Agent Skills clients including Claude Code, Codex and Cursor. This is author-declared, not independently runtime tested.
How should you approach installation?
- Inspect the pinned source, license and task-specific reference files before installing anything.
- Follow the publisher README guidance for your actual client; no installation command or cross-client compatibility was independently tested here.
- Try the illustrative prompt with synthetic input in a separate folder, inspect the output against the checklist and approve external actions separately.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Reads page material and optionally approved analytics exports. Drafting needs neither live publishing access nor customer-level data.
What does the skill cost?
The inspected source license is MIT. Agent subscriptions, model usage, dependencies and external services have separate costs and terms. No paid runtime was tested.
What are its limits and alternatives?
Heuristics alone cannot explain abandonment. More CTA clicks may not produce more qualified submissions; avoid invented social proof or causal claims.
Use Copywriting to rewrite an agreed message. Use A/B Testing to specify measurement after choosing a hypothesis.
What could you ask in a small trial?
Try this with a small sample:
Audit this synthetic submission page. Separate observations from assumptions, prioritize three changes and propose a measurable test without claiming a conversion lift.
How would you verify the result?
- Tie changes to the stated action and audience.
- Label missing funnel evidence and causal assumptions.
- Include a downstream quality metric alongside CTA clicks.
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. Dependencies and third-party assets may have separate terms. License evidence
Version details and review scope
Source: coreyhaines31/marketingskills/skills/cro
Reviewed commit: e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b
SKILL.md SHA-256: 6e172cc38178c800ff41ceb097f36c6a1db8035fb88a1fee53043f8ec38a6f35
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.