Confirm successful installation by checking the skill directory location:
.cursor/skills/marketingskills-ai-agents
Restart Cursor to activate marketingskills-ai-agents. Access via /marketingskills-ai-agents in your agent's command palette.
โ
Security Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
coreyhaines31/marketingskills is a collection of markdown-based AI agent skills covering CRO, copywriting, SEO, analytics, paid ads, email, and growth engineering. Install them once and any compatible agent (Claude Code, Cursor, Codex, Windsurf) gains specialized marketing expertise and frameworks.
How Skills Work
Each skill is a markdown file that tells AI agents:
When to activate (trigger phrases)
What frameworks to apply (e.g. AIDA, PAS, Jobs-to-be-Done)
What to produce (copy, code, audits, strategies)
Which other skills to reference (cross-skill dependencies)
All skills read product-marketing-context first โ it's the shared foundation containing your product, audience, and positioning.
Installation
Option 1: CLI (Recommended)
# Install all 33 skills at oncenpx skills add coreyhaines31/marketingskills
# Install only specific skillsnpx skills add coreyhaines31/marketingskills --skill page-cro copywriting seo-audit
# See all available skills before installingnpx skills add coreyhaines31/marketingskills --list
Skills land in .agents/skills/ with a symlink to .claude/skills/ for Claude Code.
Improving post-signup activation and time-to-value
form-cro
Optimizing lead capture, contact, or non-signup forms
popup-cro
Creating or improving popups, modals, slide-ins
paywall-upgrade-cro
In-app paywalls, upgrade screens, feature gates
Copy & Content
Skill
Use When
copywriting
Writing homepage, landing page, or any marketing copy
copy-editing
Editing or improving existing copy
cold-email
Writing B2B cold outreach sequences
email-sequence
Building drip, lifecycle, or onboarding emails
social-content
LinkedIn, Twitter/X, Instagram content
Paid & Measurement
Skill
Use When
paid-ads
Google Ads, Meta, LinkedIn, Twitter campaigns
ad-creative
Generating ad headlines, descriptions, primary text
ab-test-setup
Planning and implementing A/B experiments
analytics-tracking
Setting up or auditing GA4, Segment, Mixpanel
Growth & Retention
Skill
Use When
referral-program
Building referral or affiliate programs
free-tool-strategy
Planning free tools for lead gen or SEO
churn-prevention
Cancellation flows, save offers, dunning
lead-magnets
Creating email capture lead magnets
Sales & GTM
Skill
Use When
revops
Lead lifecycle, CRM, marketing-to-sales handoff
sales-enablement
Pitch decks, one-pagers, objection handling
launch-strategy
Product launches, feature announcements
pricing-strategy
Pricing, packaging, monetization decisions
competitor-alternatives
Comparison and alternative pages
Strategy
Skill
Use When
marketing-ideas
Brainstorming marketing strategies and tactics
marketing-psychology
Applying behavioral science to marketing
Usage Examples
Example 1: Audit and improve a landing page
"Audit my landing page at src/pages/index.tsx and suggest CRO improvements"
The agent reads product-marketing-context, activates page-cro, then:
Reviews the page structure, headline, CTA placement
Applies frameworks (AIDA, above-the-fold analysis, social proof audit)
Outputs a prioritized list of changes with implementation code
Example 2: Write a homepage from scratch
"Write homepage copy for my SaaS product using the copywriting skill"
Output includes hero headline variants, subheadline, feature sections, social proof blocks, and CTAs โ all grounded in your product-marketing-context.
Example 3: Set up A/B testing
"Help me set up an A/B test for my pricing page CTA button"
The agent activates ab-test-setup and generates:
// Example output: Google Optimize / custom A/B test scaffoldconst experiments ={pricing_cta_test:{id:'pricing-cta-v1',variants:[{id:'control',cta:'Start Free Trial'},{id:'variant_a',cta:'Get Started Free'},{id:'variant_b',cta:'Try It Free โ No Card Required'}],metric:'signup_click',minimumDetectableEffect:0.05,confidenceLevel:0.95}};// Split traffic deterministically by user IDfunctiongetVariant(userId, experimentId){const hash =simpleHash(`${userId}-${experimentId}`);const variantIndex = hash % experiments[experimentId].variants.length;return experiments[experimentId].variants[variantIndex];}
Example 4: Generate programmatic SEO pages
"Create a programmatic SEO page template for '[tool] alternatives' pages"
The agent activates programmatic-seo + competitor-alternatives and scaffolds:
// Next.js dynamic route: /pages/[competitor]-alternatives.jsexportasyncfunctiongetStaticPaths(){const competitors =awaitfetchCompetitors();// your data sourcereturn{paths: competitors.map(c=>({params:{competitor: c.slug}})),fallback:'blocking'};}exportasyncfunctiongetStaticProps({ params }){const data =awaitgetCompetitorData(params.competitor);return{props:{competitor: data },revalidate:86400};}
Example 5: Build an email sequence
"Write a 5-email onboarding sequence for new trial users"
โบClaude Desktop or compatible AI client with skill support
โบClear understanding of task or problem to solve
โบWillingness to iterate and refine outputs
Time Estimate
15-45 minutes depending on use case complexity
Steps
1Install skill using provided installation command
2Test with simple use case relevant to your work
3Evaluate output quality and relevance
4Iterate on prompts to improve results
5Integrate into regular workflow if valuable
Common Pitfalls
โ Expecting perfect results without iteration
โ Not providing enough context in prompts
โ Using skill for tasks outside its intended scope
โ Accepting outputs without review and validation
Best Practices
โ Do
+Start with clear, specific prompts
+Provide relevant context and constraints
+Review and refine all outputs before using
+Iterate to improve output quality
+Document successful prompt patterns
โ Don't
โDon't use without understanding skill limitations
โDon't skip validation of outputs
โDon't share sensitive information in prompts
โDon't expect skill to replace human judgment
๐ก Pro Tips
โ Be specific about desired format and style
โ Ask for multiple options to choose from
โ Request explanations to understand reasoning
โ Combine AI efficiency with human expertise
When to Use This
โ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
โ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
Learning Path
1Familiarize yourself with skill capabilities and limitations
2Start with low-risk, non-critical tasks
3Progress to more complex and valuable use cases
4Build expertise through regular use and experimentation