skill

ai-marketing-claude-skills

Production-ready AI marketing automation skills for Claude Code, Cursor, Codex, and AI coding agents. 12 battle-tested skills with scoring algorithms, statistical frameworks, and actionable outputs.

varunk130/ai-marketing-claude-skillscommunitylistedunreviewed

Use skill

Set up

Skills are installed by placing their folder where your agent loads skills.

Download ZIP from GitHub Open the repository

The download comes from github.com/varunk130/ai-marketing-claude-skills itself, not from our server, so what you get is exactly what its author published.

Install instructions come from the README

Skills do not use an MCP config. Follow the steps in the README below.

README

synced Oct 26, 2026

🎯 AI Marketing Claude Skills

AI-Powered Marketing Skills to Automate Operations and Drive Measurable ROI

Built by Varun Kulkarni

13 battle-tested skills with scoring algorithms, statistical frameworks, and actionable outputs. Built for Claude Code, GitHub Copilot, Cursor, OpenAI Codex, and any agent that supports Markdown skill files.

Turn your AI coding agent into a full-stack marketing operations team.

What This Is
Quick Start
Skill Catalog
How Skills Work
Skill Interaction Map
Compatibility
Repository Structure
Python Runtime
Contributing
Related Work
License

⚡ What This Is

Each skill is a self-contained Markdown file that transforms your AI coding agent into a specialized marketing operator. No API keys required to start — just point your agent at a skill and give it a natural language command.

"Run an A/B test on our pricing page" → Growth Engine activates Bayesian testing framework

"Score this lead from Acme Corp" → Sales Pipeline runs multi-channel intent scoring

"Audit our landing page for conversions" → Conversion Ops runs 12-dimension Conversion Rate Optimization (CRO) analysis

🚀 Quick Start

# 1. Clone the repo
git clone https://github.com/varunk130/ai-marketing-claude-skills.git

# 2. Navigate to any skill
cd ai-marketing-claude-skills/growth-engine

# 3. Read the skill — SKILL.md is what agents load; README.md is the full methodology
cat SKILL.md README.md

# 4. Tell your AI agent to use it (Claude Code, Copilot, Cursor,
#    or any Markdown-skill-aware agent)
#    "Use the growth-engine skill to design an A/B test for our homepage"

Using with Claude Code

# Install every skill into ~/.claude/skills (validates SKILL.md first)
python -m scripts.install

# Or into a repo for GitHub Copilot
python -m scripts.install --target .github/skills

# Then just use natural language:
> "Run a Bayesian A/B test on our checkout flow"
> "Score and enrich this lead list"
> "Generate a 90-day content calendar"

📋 Skill Catalog

#	Skill	Key Differentiators	Link
1	Growth Engine	Bayesian testing, multi-armed bandits, Controlled-experiment Using Pre-Experiment Data (CUPED) variance reduction, experiment dependency graphs	→
2	Sales Pipeline	Multi-channel intent scoring, AI enrichment (Clay/Apollo), predictive logistic regression, champion job tracking	→
3	Content Ops	Readability scoring, AI detection patterns, content decay monitoring, auto-refresh scheduling	→
4	Conversion Ops	Heatmap-aware audits, session replay archetypes, micro-conversion funnels, Cialdini 6-principle scoring	→
5	Outbound Engine	Multi-channel sequences (email+LinkedIn+video), deliverability warmup planner, timezone-aware scheduling, reply classification	→
6	Search Engine Optimization (SEO)	Generative Engine Optimization (GEO) / Answer Engine Optimization (AEO), topical authority mapping, Search Engine Results Page (SERP) feature win probability, cannibalization detection	→
7	Finance Ops	Cohort Lifetime Value (LTV) / Customer Acquisition Cost (CAC), channel unit economics, Software as a Service (SaaS) magic number, budget allocation optimizer	→
8	Revenue Intelligence	Win/loss pattern recognition (chi-square), auto-generated battlecards, pricing sensitivity cliff analysis, champion tracking	→
9	Podcast Ops	Guest fit scoring, sponsorship Cost Per Mille (CPM) calculator, cross-promo network mapping, audiogram automation	→
10	Team Ops	Skills gap matrix, capacity utilization tracking, 1:1 prep generator, Objectives and Key Results (OKR) trajectory scoring	→
11	Sales Playbook	MEDDPICC + BANT hybrid qualification, mutual action plans, Return on Investment (ROI) calculator with Net Present Value (NPV), competitive displacement scoring	→
12	Creative Ops	LinkedIn ad creative testing: 3-angle variant generation, audience-aware sample sizing, sequential / Bayesian / fixed-horizon test selection, post-test diagnostic with angle-level signal	→

Quality gate: Voice Guard scores any generated copy (0-100) for filler, hype, hedging, em-dash overuse, and flat rhythm, and quotes each phrase to fix. Run it on output from the skills above before it ships.

🧠 How Skills Work

flowchart LR
    A["💬 You say:<br/><i>'Score this lead'</i>"] --> B["🤖 Agent matches<br/>skill trigger"]
    B --> C["📖 Skill README<br/>loads framework"]
    C --> D["⚙️ Agent executes<br/>scoring algorithm"]
    D --> E["📊 Structured output<br/>delivered"]

    style A fill:#667eea,stroke:#764ba2,color:#fff
    style B fill:#764ba2,stroke:#667eea,color:#fff
    style C fill:#667eea,stroke:#764ba2,color:#fff
    style D fill:#764ba2,stroke:#667eea,color:#fff
    style E fill:#667eea,stroke:#764ba2,color:#fff

Each skill folder contains a README.md that defines:

Component	What It Covers
Capabilities	What the skill does and its key features
Workflow	Step-by-step execution sequence
Triggers	Natural language phrases that activate it
Configuration	Environment variables and setup
Methodology	Scoring frameworks with formulas and algorithms
Outputs	Report formats and deliverables
Integrations	Tools and platforms it connects with

🗺️ Skill Interaction Map

Skills are designed to work independently or together. Here's how they connect:

graph LR
    SP["Sales<br/>Pipeline"] -->|qualified leads| OE["Outbound<br/>Engine"]
    OE -->|meetings booked| SB["Sales<br/>Playbook"]
    SB -->|deal intel| RI["Revenue<br/>Intel"]
    RI -->|battlecards| SB

    SE["SEO"] -->|traffic| CV["Conversion"]
    CV -->|optimized pages| GE["Growth<br/>Engine"]
    GE -->|winning variants| CO["Content"]
    CO -->|content| SE

    FO["Finance"] -.->|budget| OE
    FO -.->|ROI data| GE
    PO["Podcast"] -.->|content atoms| CO
    TO["Team"] -.->|capacity| FO

    style SP fill:#FF6B6B,stroke:#CC5555,color:#fff
    style OE fill:#FF8E72,stroke:#CC7159,color:#fff
    style SB fill:#FF6B6B,stroke:#CC5555,color:#fff
    style RI fill:#FF8E72,stroke:#CC7159,color:#fff
    style SE fill:#4ECDC4,stroke:#3BA39B,color:#fff
    style CV fill:#45B7AA,stroke:#368A80,color:#fff
    style GE fill:#4ECDC4,stroke:#3BA39B,color:#fff
    style CO fill:#45B7AA,stroke:#368A80,color:#fff
    style FO fill:#7C83FD,stroke:#5F65CC,color:#fff
    style PO fill:#9B8FFF,stroke:#7A70CC,color:#fff
    style TO fill:#7C83FD,stroke:#5F65CC,color:#fff

Track	Skills	Flow
🔴 Sales & Revenue	Sales Pipeline → Outbound → Playbook → Revenue Intel	Lead to close loop
🟢 Growth & Content	SEO → Conversion → Growth Engine → Content	Traffic to optimization loop
🔵 Operations	Finance · Podcast · Team	Cross-functional support layer

🧰 Compatibility

Agent	Status
Claude Code	✅ Full support
Cursor	✅ Full support
OpenAI Codex	✅ Full support
Windsurf	✅ Full support
GitHub Copilot	✅ Full support
Any Markdown-skill agent	✅ Full support

📁 Repository Structure

ai-marketing-claude-skills/
├── README.md                          ← You are here
├── growth-engine/README.md            ← Bayesian A/B testing & experimentation
├── sales-pipeline/README.md           ← Lead scoring & deal prediction
├── content-ops/README.md              ← Content quality & decay management
├── conversion-ops/README.md           ← CRO audits & funnel optimization
├── outbound-engine/README.md          ← Multi-channel outbound sequences
├── seo-ops/README.md                  ← SEO + GEO/AEO optimization
├── finance-ops/README.md              ← Unit economics & budget modeling
├── revenue-intelligence/README.md     ← Win/loss analysis & battlecards
├── podcast-ops/README.md              ← Podcast growth & monetization
├── team-ops/README.md                 ← Team performance & capacity
├── sales-playbook/README.md           ← Deal execution & methodology
├── creative-ops/README.md             ← LinkedIn creative variant testing
├── voice-guard/README.md              ← Copy quality gate for generated output
├── python_runtime/                    ← Shared scoring, statistical, and IO helpers
├── examples/                          ← Runnable usage examples
└── tests/                             ← unittest suite for the runtime

Python Runtime

In addition to the skill contracts (Markdown), this repo ships a small python_runtime/ package with shared scoring, statistical, and IO helpers that skill executors can call into.

Requires Python 3.10+.

# Run the example
python examples/run_skill.py

# Run the unit tests
python -m unittest discover -v

# Try the CLI
python -m python_runtime.cli score-lead --features '{"title_match":80,"engagement":70}'
python -m python_runtime.cli ci --successes 120 --trials 1000
python -m python_runtime.cli sample-size --baseline 0.05 --mde 0.01

Zero runtime dependencies — pure Python standard library. Tests use the built-in unittest module.

🤝 Contributing

The main branch is protected. To contribute:

Fork the repository
Create a feature branch (git checkout -b feature/my-skill)
Commit your changes
Open a Pull Request — all PRs require review and approval before merging

Direct pushes to main are not allowed.

Related Work

Part of a portfolio of AI agent and skill libraries for product, GTM, and decision-making teams.

Discovery & research

ai-customer-discovery-skills — Turn raw customer signal into validated product opportunities (5 of 12 shipped)
jtbd-extractor — Extract Jobs-to-be-Done statements from research, with opportunity scoring

Strategy & decisions

claude-code-skills — 29 production-grade skills for finance, product, strategy, and game theory
AI-Builder-Decision-Analyst — 11 skills that catch bad bets before you ship across DECIDE / BUILD / COMMUNICATE / LEARN

Go-to-market

ai-gtm-skill-library — 37 opinionated GTM skills across the full discover → renew lifecycle
ai-marketing-os — Run a marketing org as an orchestrated AI team: 9 agents, 12 expert skills, end-to-end missions that ship real artifacts
ai-partner-ecosystem-analysis — Deep research on any ISV, partner, or competitor with a 1-slide PPTX output

UX & design

ai-ux-skill-library — 13 frameworks for designing UX for AI products, agents, and AI-powered experiences

Multi-agent demos

ai-pm-agents-suite — 6-agent pipeline plus 3 standalone PM agents (decision engine, financial analyst, stakeholder translator) that turn customer feedback into strategy, PRDs, and comms
ai-legal-agents-skills-os — Agentic operating system for legal work: one master agent, nine specialist skills, MCP + MCP Apps
ai-growth-os — Compound: a multi-agent growth experiment engine that runs the find → design → ship → learn loop end-to-end, offline
ai-customer-acquisition — Beacon: five agents allocate a budget across channels, build the creative, and reallocate on week-1 results
ai-revops — Atlas: nine agents across GTM, Partnerships, and RevOps take a company into a new market with one Vertical Launch Plan

Evaluation & operations

AI-Eval-Skills — 7 skills to plan, generate, run, interpret, and triage AI agent evaluations
ai-workflow-playbooks — 21 playbooks + 10 skills + 4 guardians + 5 runbooks across the 7-stage delivery pipeline

📄 License

MIT — see LICENSE for the full text. Use these skills however you like.

Star ⭐ this repo if these skills save you time.

Built by Varun Kulkarni · Can be used in Claude Code, OpenAI Codex, or GitHub Copilot