A production-grade marketing operations toolkit for Claude Code: 12 skills, 5 specialist subagents, 4 Python scripts, and 6 templates that turn Claude into a full marketing team.
Runs natively in Claude Code. Everything is routed through one command — /market — with subcommands for audits, CRO, SEO, copy, emails, social, ads, funnels, launches, proposals, and reports.
| Command | Purpose |
|---|---|
/market audit <url> |
Full 6-dimension audit with 5 parallel subagents → MARKETING-AUDIT.md |
/market landing <url> |
Conversion rate optimization → LANDING-CRO.md |
/market seo <url> |
On-page + technical + AI search (GEO) audit → SEO-AUDIT.md |
/market brand <url> |
Voice, tone, archetype → BRAND-VOICE.md |
/market competitors <url> |
Competitive intelligence + Wayback history → COMPETITOR-ANALYSIS.md |
/market copy <page> |
Rewrite copy in brand voice |
/market emails <type> |
Welcome, nurture, launch, cold, abandon, re-engage sequences |
/market social <topic> |
Platform-native posts (X, LinkedIn, IG, TikTok, Shorts, Threads) |
/market ads <product> |
Meta, Google, LinkedIn, TikTok ad copy |
/market funnel <url> |
End-to-end funnel + GA4 event spec → FUNNEL-ANALYSIS.md |
/market launch <product> |
4-week launch orchestration → LAUNCH-PLAN.md |
/market proposal <client> |
Client SOW with pricing calculator → PROPOSAL.md |
/market report [--format pdf] <url> |
Consolidated client-ready report (Markdown or PDF) |
- market-content — content & messaging specialist
- market-conversion — CRO specialist
- market-technical — technical SEO specialist
- market-competitive — competitive intelligence
- market-strategy — brand, trust, and growth
analyze_page.py— HTML / SEO / schema / tracking extraction (stdlib only)competitor_scanner.py— multi-URL positioning scansocial_calendar.py— pillar-based content calendar generatorgenerate_pdf_report.py— client-ready PDF via reportlab
Welcome, nurture, and launch email sequences; content calendar; launch checklist; client proposal.
curl -fsSL https://raw.githubusercontent.com/rediumvex/ai-marketing-claude/main/install.sh | bashOr clone and run:
git clone https://github.com/rediumvex/ai-marketing-claude.git
cd ai-marketing-claude
./install.shThis copies the skills, agents, scripts, and templates into ~/.claude/ so Claude Code can discover them.
pip3 install reportlabOnly needed if you use /market report --format pdf.
# Full audit with all 5 specialists
/market audit https://example.com
# Just CRO
/market landing https://example.com/pricing
# Generate an email sequence in the detected brand voice
/market brand https://example.com # run this first
/market emails welcome # matches the voice from BRAND-VOICE.md
# Final client deliverable
/market report --format pdf https://example.com- Every skill is a Markdown file with YAML frontmatter that Claude Code reads to decide when to invoke it.
- The root
market/SKILL.mdis the router — it catches/marketcommands and hands off to the right specialist. - The audit skill launches 5 subagents in parallel. Each scores its dimension and returns specific findings with quoted evidence.
- All artifacts land in the current project root (
MARKETING-AUDIT.md,BRAND-VOICE.md, etc.) and downstream skills read them for context. - The PDF report compiles everything into a client deliverable.
Weighted 6-category composite (0–100):
- Content & Messaging — 25%
- Conversion Optimization — 20%
- SEO & Discoverability — 20%
- Competitive Positioning — 15%
- Brand & Trust — 10%
- Growth & Strategy — 10%
Grades: 90+ A, 80+ B, 70+ C, 60+ D, <60 F.
- Evidence over opinion. Every finding quotes actual page copy.
- Impact over activity. Fixes are ranked by
traffic × expected CR lift × ARPU. - Specific over generic. Every recommendation includes a concrete rewrite.
- Lean skills. Every skill fits under ~300 lines — no filler, no duplication.
- Stdlib first. Scripts run without dependencies except the optional PDF generator.
MIT. Use it, modify it, ship it.