/ README.md
README.md
1 # AI Marketing Skills 2 3 **Open-source Claude Code skills for marketing and sales teams.** Built by the team at [Single Brain](https://singlebrain.com/?utm_source=github&utm_medium=skill_repo&utm_campaign=ai_marketing_skills) — battle-tested on real pipelines generating millions in revenue. 4 5 These aren't prompts. They're complete workflows — scripts, scoring algorithms, expert panels, and automation pipelines you can plug into Claude Code (or any AI coding agent) and run today. 6 7 --- 8 9 ## 🗂️ Skills 10 11 | Category | What It Does | Key Skills | 12 |----------|-------------|------------| 13 | [**Growth Engine**](./growth-engine/) | Autonomous marketing experiments that run, measure, and optimize themselves | Experiment Engine, Pacing Alerts, Weekly Scorecard | 14 | [**Sales Pipeline**](./sales-pipeline/) | Turn anonymous website visitors into qualified pipeline | RB2B Router, Deal Resurrector, Trigger Prospector, ICP Learner | 15 | [**Content Ops**](./content-ops/) | Ship content that scores 90+ every time | Expert Panel, Quality Gate, Editorial Brain, Quote Miner | 16 | [**Outbound Engine**](./outbound-engine/) | ICP definition to emails in inbox — fully automated | Cold Outbound Optimizer, Lead Pipeline, Competitive Monitor | 17 | [**SEO Ops**](./seo-ops/) | Find the keywords your competitors missed | Content Attack Briefs, GSC Optimizer, Trend Scout | 18 | [**Finance Ops**](./finance-ops/) | Your AI CFO that finds hidden costs in 30 minutes | CFO Briefing, Cost Estimate, Scenario Modeler | 19 | [**Revenue Intelligence**](./revenue-intelligence/) | Prove content ROI and turn sales calls into strategy | Gong Insight Pipeline, Revenue Attribution, Client Report Generator | 20 | [**Conversion Ops**](./conversion-ops/) | Score any landing page and turn survey data into lead magnets | CRO Audit, Survey-to-Lead-Magnet Engine | 21 | [**Podcast Ops**](./podcast-ops/) | One episode → 20+ content pieces across every platform | Podcast-to-Everything Pipeline, Content Calendar | 22 | [**Team Ops**](./team-ops/) | Ruthless performance audits and meeting intelligence | Elon Algorithm, Meeting-to-Action Extractor | 23 | [**Sales Playbook**](./sales-playbook/) | Value-based pricing framework that turns $10K deals into $100K deals | Pre-Call Briefing, Tiered Packager, Call Analyzer, Pattern Library | 24 | [**Autoresearch**](./autoresearch/) | Karpathy-inspired optimization loops for conversion content — 50+ variants, expert scoring, evolved winners | Variant Generator, Expert Panel Scorer, Evolution Engine | 25 | [**Deck Generator**](./deck-generator/) | AI-generated slide decks with consistent visual styles in minutes | Image Generator, Google Slides Builder, Style Presets | 26 | [**YT Competitive Analysis**](./yt-competitive-analysis/) | Find outlier videos and packaging patterns across any YouTube channels | Outlier Detector, Title Pattern Extractor, Channel Benchmarker | 27 | [**X Long-Form + Humanizer**](./x-longform-post/) | Write X articles that sound human — with a 24-pattern AI slop detector | Post Writer, Humanizer Checklist, ASCII Diagram Builder | 28 29 --- 30 31 ## 🚀 Quick Start 32 33 Each skill category has its own README with setup instructions. The general pattern: 34 35 ```bash 36 # 1. Clone the repo 37 git clone https://github.com/ericosiu/ai-marketing-skills.git 38 cd ai-marketing-skills 39 40 # 2. Pick a category 41 cd growth-engine # or sales-pipeline, content-ops, etc. 42 43 # 3. Install dependencies 44 pip install -r requirements.txt 45 46 # 4. Set up environment variables 47 cp .env.example .env 48 # Edit .env with your API keys 49 50 # 5. Run 51 python experiment-engine.py create \ 52 --hypothesis "Thread posts get 2x engagement vs single posts" \ 53 --variable format \ 54 --variants '["thread", "single"]' \ 55 --metric impressions 56 ``` 57 58 --- 59 60 ## 🧠 How These Work with Claude Code 61 62 Every category includes a `SKILL.md` file. Drop it into your Claude Code project and the AI agent knows how to use the tools: 63 64 ``` 65 # In your project directory 66 cp ai-marketing-skills/growth-engine/SKILL.md .claude/skills/growth-engine.md 67 ``` 68 69 Then ask Claude Code: *"Run an experiment testing carousel vs. static posts on LinkedIn"* — it handles the rest. 70 71 --- 72 73 ## 📊 What Makes These Different 74 75 **These aren't toy demos.** Each skill was built to run real business operations: 76 77 - **Growth Engine** uses bootstrap confidence intervals and Mann-Whitney U tests — real statistics, not vibes 78 - **Deal Resurrector** has three intelligence layers including "follow the champion" — tracking departed contacts to their new companies 79 - **ICP Learner** rewrites your ideal customer profile based on actual win/loss data — your targeting improves automatically 80 - **Expert Panel** recursively scores content with domain-specific expert personas until quality hits 90+ 81 - **RB2B Router** does intent scoring, seniority-based company dedup, and agency classification before routing to outbound sequences 82 83 --- 84 85 ## 📁 Repository Structure 86 87 ``` 88 ai-marketing-skills/ 89 ├── README.md ← You are here 90 ├── growth-engine/ ← Autonomous experiments 91 │ ├── SKILL.md 92 │ ├── experiment-engine.py 93 │ ├── pacing-alert.py 94 │ ├── autogrowth-weekly-scorecard.py 95 │ └── ... 96 ├── sales-pipeline/ ← Visitor → pipeline automation 97 │ ├── SKILL.md 98 │ ├── rb2b_instantly_router.py 99 │ ├── deal_resurrector.py 100 │ ├── trigger_prospector.py 101 │ ├── icp_learning_analyzer.py 102 │ └── ... 103 ├── content-ops/ ← Quality scoring & production 104 │ ├── SKILL.md 105 │ ├── scripts/ 106 │ ├── experts/ ← 9 expert panel definitions 107 │ ├── scoring-rubrics/ ← 5 scoring rubric templates 108 │ └── ... 109 ├── outbound-engine/ ← Cold outbound automation 110 │ ├── SKILL.md 111 │ ├── scripts/ 112 │ ├── references/ ← ICP template, copy rules 113 │ └── ... 114 ├── seo-ops/ ← SEO intelligence 115 │ ├── SKILL.md 116 │ ├── content_attack_brief.py 117 │ ├── gsc_client.py 118 │ ├── trend_scout.py 119 │ └── ... 120 ├── finance-ops/ ← Financial analysis 121 │ ├── SKILL.md 122 │ ├── scripts/ 123 │ ├── references/ ← Metrics, rates, ROI models 124 │ └── ... 125 ├── revenue-intelligence/ ← Sales call insights + attribution 126 │ ├── SKILL.md 127 │ ├── gong_insight_pipeline.py 128 │ ├── revenue_attribution.py 129 │ └── client_report_generator.py 130 ├── conversion-ops/ ← CRO + lead magnet generation 131 │ ├── SKILL.md 132 │ ├── cro_audit.py 133 │ └── survey_lead_magnet.py 134 ├── podcast-ops/ ← Podcast → content factory 135 │ ├── SKILL.md 136 │ └── podcast_pipeline.py 137 ├── team-ops/ ← Performance audits + meeting intel 138 │ ├── SKILL.md 139 │ ├── team_performance_audit.py 140 │ └── meeting_action_extractor.py 141 └── sales-playbook/ ← Value-based pricing framework 142 ├── SKILL.md 143 ├── value_pricing_briefing.py 144 ├── value_pricing_packager.py 145 ├── call_analyzer.py 146 └── pricing_pattern_library.py 147 ``` 148 149 --- 150 151 ## 🔒 Privacy & Security 152 153 Every skill is built with data privacy in mind: 154 155 - **PII Sanitizer** scans code and data for sensitive information before commits (`security/sanitizer.py`) 156 - **Pre-commit hook** blocks commits containing detected PII patterns 157 - **Configurable blocklists** for company names, person names, and custom patterns 158 - See [`security/README.md`](./security/README.md) for setup 159 160 ```bash 161 # Scan for sensitive data 162 python3 security/sanitizer.py --scan --dir . --recursive 163 164 # Install the pre-commit hook 165 cp security/pre-commit-hook.sh .git/hooks/pre-commit && chmod +x .git/hooks/pre-commit 166 ``` 167 168 --- 169 170 ## 📡 Telemetry (Opt-In) 171 172 Anonymous usage telemetry helps us understand which skills people actually use. Fully opt-in, privacy-first: 173 174 - **Local logging always** — see your own usage stats in `~/.ai-marketing-skills/analytics/` 175 - **Remote reporting optional** — only if you explicitly opt in on first run 176 - **Data collected:** skill name, duration, success/fail, version, OS. Nothing else. No code, no file paths, no repo content. 177 - **Version checks** — get notified when new skills are available 178 179 ```bash 180 # View your local usage stats 181 python3 telemetry/telemetry_report.py 182 183 # Check for updates 184 python3 telemetry/version_check.py 185 ``` 186 187 See [`telemetry/README.md`](./telemetry/README.md) for details. 188 189 --- 190 191 ## 🤝 Contributing 192 193 Found a bug? Have an improvement? PRs welcome. Read [`CONTRIBUTING.md`](./CONTRIBUTING.md) for guidelines. 194 195 1. Fork the repo 196 2. Create your feature branch (`git checkout -b feature/better-scoring`) 197 3. Run `python3 security/sanitizer.py --scan` before committing 198 4. Commit your changes 199 5. Push to the branch 200 6. Open a Pull Request 201 202 --- 203 204 ## 📄 License 205 206 MIT License. Use these however you want. 207 208 --- 209 210 *Star this repo if you find it useful. It helps others discover these tools.* 211 212 --- 213 214 <div align="center"> 215 216 **🧠 [Want these built and managed for you? →](https://singlebrain.com/?utm_source=github&utm_medium=skill_repo&utm_campaign=ai_marketing_skills)** 217 218 *This is how we build agents at [Single Brain](https://singlebrain.com/?utm_source=github&utm_medium=skill_repo&utm_campaign=ai_marketing_skills) for our clients.* 219 220 [Single Grain](https://www.singlegrain.com/?utm_source=github&utm_medium=skill_repo&utm_campaign=ai_marketing_skills) · our marketing agency 221 222 📬 **[Level up your marketing with 14,000+ marketers and founders →](https://levelingup.beehiiv.com/subscribe)** *(free)* 223 224 </div>