Best Marketing Skills for Claude Code
Skills for SEO, paid ads, email programs, influencer campaigns, and launch management. All evaluated on six dimensions with public scorecards.
The best marketing skills for Claude Code, ranked by six-dimension evaluation: serp-markup-builder (9.4/10), technical-seo-checker (9.3/10), message-test-designer (9.2/10), on-page-seo-checker (9.2/10), ad-test-designer (9.1/10). Every score has published rationale. How we score →
Install the top 3 in one line
curl -fsSL https://skill123.me/install/serp-markup-builder.sh | bash
curl -fsSL https://skill123.me/install/technical-seo-checker.sh | bash
curl -fsSL https://skill123.me/install/message-test-designer.sh | bash
Verified evaluation, one-line install. Or tell your agent: install the marketing skill from skill123.me.
Use when the user asks to "optimize meta tags", "write title tags / meta descriptions", "add Open…
Excellent two-mode SERP markup skill: 129-line SKILL.md plus 827 lines of bundled references, per-mode done-when checks, validation steps, current deprecation notes and a JS-injected-schema caveat. Only the schema_lint pre-flight script and sibling-skill paths are not shipped.
Use when the user asks to "check technical SEO"; audits crawlability, indexing, Core Web Vitals, …
Comprehensive technical SEO reviewer: nine-step audit with thresholds, migration and LLM-crawler playbooks, eight bundled references, decision gates, and a dry-run-by-default index-push write channel. Connector scripts and sibling paths remain outside the zip.
Use when the user asks to "test our messaging before we scale it", "design a message-market-fit p…
Best-in-batch test-design skill: bundled stimulus-binding reference resolves locally, measurable hypothesis rule, hash-bound stimulus, precommitted stop/revise rule, and keyless significance recipe; sibling links still point outside the zip.
Use when the user asks to "audit on-page SEO" or "diagnose why a single page dropped"; scores tit…
Strong reviewer skill: 11-step audit workflow with per-element scores, keyword-inference fallback, decision gates, bulk mode playbook and four bundled references. Connector scripts and sibling-skill paths are not shipped, slightly hurting standalone robustness.
Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an increme…
Excellent experiment-design skill: falsifiable hypotheses, precommitted decision ownership, binding verification, and explicit statistical-method gates; only weakness is uns shipped suite-file links and helper script.
Design a controlled dynamic-pricing or repricing system for ecommerce products. Use when a seller…
Use when the user asks to "write the email", "draft subject lines", or "build email creative"; pr…
Mature generator: 11-step flow with mode selection, claim-ledger discipline, decision gates, quality bar, and versioned creative freezing; a few suite paths and the de-slop file are not shipped.
Use when the user asks to "build the email HTML", "make this email responsive", "fix dark-mode re…
Excellent email HTML build and QA skill with decision gates, a six-point quality bar, and two substantive bundled references; only weakness is dependence on unshipped repo files like resend.py and shared protocol docs.
Use when the user asks to "run a deliverability pre-flight before I send", "check my SPF/DKIM/DMA…
Thorough pre-send deliverability pre-flight with a detailed bundled checklist, explicit S1 flag states, and never-pass-by-default coverage rules; unshipped connector scripts and shared repo docs are the only gaps.
Use when the user asks to "optimize our landing page for influencer traffic", "fix our promo-code…
Solid landing-page optimization skill with a rigorous creator-reuse rights gate, eight concrete steps, and a large bundled templates reference; external repo dependencies (skill-contract, CONNECTORS, sibling skills) are not shipped.
Score comparison
How the top 10 compare across the six evaluation dimensions (0–10). Full written rationale for every score is on each skill's page.
| Skill | Overall | Trigger | Structure | Workflow | Content | Engineering | Security |
|---|---|---|---|---|---|---|---|
| serp-markup-builder | 9.4 | 9.5 | 10.0 | 9.6 | 9.0 | 8.0 | 9.5 |
| technical-seo-checker | 9.3 | 9.0 | 10.0 | 9.6 | 9.0 | 8.0 | 9.5 |
| message-test-designer | 9.2 | 9.5 | 8.7 | 9.2 | 9.0 | 8.0 | 10.0 |
| on-page-seo-checker | 9.2 | 8.5 | 10.0 | 9.6 | 9.0 | 8.0 | 9.5 |
| ad-test-designer | 9.1 | 9.5 | 8.7 | 9.6 | 9.0 | 7.0 | 9.5 |
| dynamic-pricing-ecommerce | 9.1 | 9.0 | 9.0 | 9.5 | 8.5 | 9.0 | 9.0 |
| email-creative-builder | 9.0 | 9.5 | 8.7 | 9.2 | 9.0 | 7.0 | 9.5 |
| email-render-builder | 9.0 | 9.5 | 8.7 | 9.6 | 9.0 | 6.0 | 9.5 |
| deliverability-qa | 9.0 | 9.5 | 8.7 | 9.6 | 9.0 | 6.0 | 9.5 |
| landing-optimizer | 9.0 | 9.5 | 8.7 | 9.6 | 9.0 | 6.0 | 9.5 |
FAQ
What is a Claude Code marketing skill?
A package that teaches your agent a marketing workflow — SEO audits, ad test design, email deliverability checks. Your agent uses it when the task matches.
Do these skills post to my accounts?
Only through explicit draft-and-approve flows. We scanned every script: the top-rated marketing skills gate publishing behind manual confirmation — nothing sends without your sign-off.
Which marketing skill should I try first?
The SEO checkers — serp-markup-builder (9.4) and technical-seo-checker (9.3) — are self-contained and need no external accounts.
Every skill here was scored on the same six-dimension rubric — the full scorecard with written rationale is on each skill's page. Browse the full Marketing skills collection (including skills outside the top 10), or see all Marketing skills.