Open-source Claude Code skills for marketing and sales teams. Built by the team at Single Brain — battle-tested on real pipelines generating millions in revenue.

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.

Each skill category has its own README with setup instructions. The general pattern:

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

# 2. Pick a category
cd growth-engine  # or sales-pipeline, content-ops, etc.

# 3. Install dependencies
pip install -r requirements.txt

# 4. Set up environment variables
cp .env.example .env
# Edit .env with your API keys

# 5. Run
python experiment-engine.py create \
  --hypothesis "Thread posts get 2x engagement vs single posts" \
  --variable format \
  --variants '["thread", "single"]' \
  --metric impressions

Every category includes a SKILL.md file. Copy the complete skill directory when it also contains scripts/, references/, agents/, or other bundled files. Copying only SKILL.md will leave those workflows incomplete.

# In your project directory
cp ai-marketing-skills/growth-engine/SKILL.md .claude/skills/growth-engine.md

For a bundled skill such as YouTube Packaging, install the full directory:

cp -R ai-marketing-skills/packaging-youtube-thumbnails \
  .claude/skills/packaging-youtube-thumbnails

Other agent harnesses should import the same complete directory and use its SKILL.md as the entry point. OpenAI-compatible harnesses can also read agents/openai.yaml for display metadata and the default prompt.

Then ask Claude Code: "Run an experiment testing carousel vs. static posts on LinkedIn" — it handles the rest.

These aren't toy demos. Each skill was built to run real business operations:

• Growth Engine uses bootstrap confidence intervals and Mann-Whitney U tests — real statistics, not vibes
• Deal Resurrector has three intelligence layers including "follow the champion" — tracking departed contacts to their new companies
• ICP Learner rewrites your ideal customer profile based on actual win/loss data — your targeting improves automatically
• Expert Panel recursively scores content with domain-specific expert personas until quality hits 90+
• RB2B Router does intent scoring, seniority-based company dedup, and agency classification before routing to outbound sequences

ai-marketing-skills/
├── README.md              ← You are here
├── growth-engine/         ← Autonomous experiments
│   ├── SKILL.md
│   ├── experiment-engine.py
│   ├── pacing-alert.py
│   ├── autogrowth-weekly-scorecard.py
│   └── ...
├── sales-pipeline/        ← Visitor → pipeline automation
│   ├── SKILL.md
│   ├── rb2b_instantly_router.py
│   ├── deal_resurrector.py
│   ├── trigger_prospector.py
│   ├── icp_learning_analyzer.py
│   └── ...
├── content-ops/           ← Quality scoring & production
│   ├── SKILL.md
│   ├── scripts/
│   ├── experts/           ← 9 expert panel definitions
│   ├── scoring-rubrics/   ← 5 scoring rubric templates
│   └── ...
├── personal-strategic-signal-intelligence/  ← Private signals → decision intelligence
│   ├── SKILL.md
│   └── README.md
├── outbound-engine/       ← Cold outbound automation
│   ├── SKILL.md
│   ├── scripts/
│   ├── references/        ← ICP template, copy rules
│   └── ...
├── seo-ops/               ← SEO intelligence
│   ├── SKILL.md
│   ├── content_attack_brief.py
│   ├── gsc_client.py
│   ├── trend_scout.py
│   └── ...
├── finance-ops/           ← Financial analysis
│   ├── SKILL.md
│   ├── scripts/
│   ├── references/        ← Metrics, rates, ROI models
│   └── ...
├── revenue-intelligence/  ← Sales call insights + attribution
│   ├── SKILL.md
│   ├── gong_insight_pipeline.py
│   ├── revenue_attribution.py
│   └── client_report_generator.py
├── conversion-ops/        ← CRO + lead magnet generation
│   ├── SKILL.md
│   ├── cro_audit.py
│   └── survey_lead_magnet.py
├── podcast-ops/           ← Podcast → content factory
│   ├── SKILL.md
│   └── podcast_pipeline.py
├── team-ops/              ← Performance audits + meeting intel
│   ├── SKILL.md
│   ├── team_performance_audit.py
│   └── meeting_action_extractor.py
└── sales-playbook/        ← Value-based pricing framework
    ├── SKILL.md
    ├── value_pricing_briefing.py
    ├── value_pricing_packager.py
    ├── call_analyzer.py
    └── pricing_pattern_library.py

Every skill is built with data privacy in mind:

• PII Sanitizer scans code and data for sensitive information before commits (security/sanitizer.py)
• Pre-commit hook blocks commits containing detected PII patterns
• Configurable blocklists for company names, person names, and custom patterns
• See security/README.md for setup

# Scan for sensitive data
python3 security/sanitizer.py --scan --dir . --recursive

# Install the pre-commit hook
cp security/pre-commit-hook.sh .git/hooks/pre-commit && chmod +x .git/hooks/pre-commit

Anonymous usage telemetry helps us understand which skills people actually use. Fully opt-in, privacy-first:

• Local logging always — see your own usage stats in ~/.ai-marketing-skills/analytics/
• Remote reporting optional — only if you explicitly opt in on first run
• Data collected: skill name, duration, success/fail, version, OS. Nothing else. No code, no file paths, no repo content.
• Version checks — get notified when new skills are available

# View your local usage stats
python3 telemetry/telemetry_report.py

# Check for updates
python3 telemetry/version_check.py

See telemetry/README.md for details.

Found a bug? Have an improvement? PRs welcome. Read CONTRIBUTING.md for guidelines.

1. Fork the repo
2. Create your feature branch (git checkout -b feature/better-scoring)
3. Run python3 security/sanitizer.py --scan before committing
4. Commit your changes
5. Push to the branch
6. Open a Pull Request

MIT License. Use these however you want.

Star this repo if you find it useful. It helps others discover these tools.