Skip to content
SkillModel-led1,390 tokens in use

cro

Analyzes a landing, pricing or lead form page across seven conversion factors and returns quick wins, high-impact changes, test ideas and copy alternatives.

61,711 stars on the repository MIT Licensecoreyhaines31/marketingskills · skills/cro
npx skills add coreyhaines31/marketingskills --skill cro
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing cro costs

85tokens idle
1,390tokens in use
5,459tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure19/25
  • Examples3/15
  • Output7/15
  • Size13/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

cro helps an agent find why a page is not converting and what to change first. It identifies the page type, the main conversion goal and the traffic source, then reviews the page in order of impact: value proposition, headline, calls to action, visual hierarchy, trust signals, objections and friction.

Two references go deeper: one for lead, contact and demo forms, and one for experiment ideas by page type.

What You Get

  • A review of the page across seven factors ordered by impact
  • Quick wins to implement now and larger changes to prioritize
  • Test ideas written as hypotheses to A/B test
  • Two or three alternatives with a rationale for headlines and CTAs
  • Page-type guidance for homepage, landing, pricing, feature and blog pages

Common Use Cases

  • Reviewing a landing page URL shared for feedback
  • Deciding whether to remove a field from a lead form
  • Choosing what to change first on a pricing page
  • Planning experiments for a demo request page

What Makes It Unique

The analysis is ordered by impact, starting with whether a visitor understands the offer within five seconds. Form work is routed to a dedicated reference covering field decisions, layouts, errors and mobile, and the form guidance links to a revops playbook for handling lead enrichment without losing valid submissions.

Under The Hood

The SKILL.md and two references are loaded as context. It ships no scripts and runs no commands. The agent reads the product marketing context file in your project when present and works from the page, URL or screenshot you give it. If you share a URL it may fetch the page. Output is a written list of recommendations.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers