21 skills · category

SEO & Growth skills for Claude Code

Skills for getting found and converting: technical SEO audits, JSON-LD structured data, keyword research and content briefs, programmatic SEO without thin pages, landing page copy, lifecycle email, conversion optimization, analytics tracking plans, competitor research, and product launches.

Download all 21 (.zip) Browse the list

Every seo & growth skill

Each card opens the full playbook, example prompts and install commands.

★ No. 424

AI Search Optimization

Get cited in AI answers without gaming anything

Claude separates what actually drives citations in AI Overviews, ChatGPT, Perplexity, Copilot, and Claude from the folklore. It checks robots.txt and server-rendered HTML per bot with a bundled probe, rewrites target pages into self-contained, sourced answer passages, cleans up how third-party sources describe the brand, and measures progress with a fixed prompt panel and AI referral traffic.

ai-search-optimization 191 lines · 2 files

No. 425

Analytics Tracking Plan

Every event traced to a decision and verified live

Claude builds tracking plans backwards from the decisions stakeholders need to make, then turns them into exact dataLayer and Measurement Protocol payloads. A bundled validator catches GA4 reserved names, length and parameter limits, inconsistent property types, and likely PII before anything ships, and every event is checked in DebugView against the plan and reconciled with backend counts.

analytics-tracking-plan 212 lines · 2 files

No. 426

App Store Optimization

More store impressions, more of them installing

Claude handles the App Store and Google Play as separate listings with different indexing rules. It chooses winnable terms from Play search-term data and Apple Ads popularity, fills every character-limited field without repeating words, storyboards the first three screenshots around the core outcome, sets rating prompts on the official APIs, and tests one listing variable at a time.

app-store-optimization 205 lines

No. 427

Cold Outreach

Fewer, truer cold emails that people answer

Claude plans outreach around a narrow ICP and a real trigger for each account, writes short plain-text emails with one small ask and an easy way to say no, and sets a follow-up cadence that ends. It sets up a separate warmed sending domain with conservative caps, checks CAN-SPAM, PECR, GDPR and CASL rules per recipient country, and measures positive replies instead of opens.

cold-outreach 226 lines · 2 files

No. 428

Competitor Analysis

Sourced rival research that ends in decisions

Claude scopes competitor research to the decision it serves, then gathers dated, sourced evidence on positioning, pricing for realistic customer profiles, review sentiment, content gaps, and paid messaging. It keeps observations apart from inferences, rates rivals fairly instead of ticking boxes in our favor, and ends with specific moves, battlecards, and a source list that stays auditable.

competitor-analysis 186 lines

No. 429

Content Refresh

Fix the pages that are actually decaying, and only those

Claude compares Search Console exports year over year with a bundled script, rules out seasonality and sitewide causes, then reads each page's queries and the live SERP to name why it slipped. Every page gets one action (refresh, rewrite, consolidate, prune, or leave), destructive steps wait for your confirmation, and results are judged against an untouched control group.

content-refresh 180 lines · 2 files

No. 430

Conversion Optimization

Research-led A/B tests sized before they start

Claude runs CRO as a research process, not a list of button tweaks. It quantifies funnel leaks by device, pairs each with qualitative evidence from replays and surveys, and writes falsifiable hypotheses ranked with ICE. A bundled stdlib calculator sizes tests, finds the detectable effect for your traffic, and flags sample ratio mismatch before anyone reads the results.

conversion-optimization 178 lines · 2 files

No. 431

Email Campaigns

Lifecycle emails triggered by behavior, judged by lift

Claude designs email programs around the activation event that predicts retention. Each email gets one job, a deep-linked CTA, and an exit the moment the user converts. It writes subjects and preheaders that say what is inside, checks one-click unsubscribe and spam-rate requirements, and measures with clicks and a holdout group, because Apple Mail Privacy Protection makes open rates useless.

email-campaigns 172 lines

No. 432

International SEO

The right language version, in every market

Claude plans multilingual and multiregional sites from demand data, chooses between subdirectories and ccTLDs, maps true page equivalents before writing a single tag, and implements hreflang with self-references, return links, x-default and self-canonicals. It refuses forced IP redirects and verifies clusters in rendered HTML and Search Console.

international-seo 163 lines

No. 433

Keyword Research

A ranked page plan instead of a 5,000-row export

Claude starts from what the business sells, mines Search Console for striking-distance and cannibalized queries, then expands seeds from tools, autocomplete, and communities. A bundled script clusters keywords by shared top-10 URLs so each page targets one cluster, and clusters are scored with business value weighted double, so high-intent terms outrank vanity volume.

keyword-research 163 lines · 2 files

No. 434

Landing Page Copy

Copy a competitor could not paste onto their page

Claude writes landing pages from voice-of-customer research instead of stock adjectives. It matches the hero to the visitor's awareness level and traffic source, fills a positioning statement before drafting any headline, answers the top objections where they arise, and refuses to invent testimonials or metrics. You get a section-by-section copy deck with headline and CTA variants ready to test.

landing-page-copy 189 lines

No. 435

Local SEO

Win the map pack without risking a suspension

Claude audits each Business Profile against Google's guidelines before touching rankings: real-world name, the most specific primary category, accurate hours, and a location page that matches the profile character for character. It then cleans up citations in impact order, sets up review requests that never gate or incentivize, and measures with a geo-grid instead of one rank check.

local-seo 218 lines

No. 436

Pricing Strategy

Prices that scale with the value customers get

Claude starts from segments, unit costs, plan-level churn, and realized discounts instead of competitor price tags. It tests candidate value metrics, builds tiers with a named buyer each, checks gross margin for the heaviest users on AI or usage plans, backs price points with at least two willingness-to-pay methods, and pairs every change with a plan for existing customers.

pricing-strategy 212 lines

No. 437

Product Launch

Launch-day attention turned into activated users

Claude plans launches by tier so minor releases get a changelog line and major ones get the full treatment. It builds a dated timeline with owners, an asset checklist, Product Hunt and Show HN playbooks that stay within community rules, production readiness checks, and an hour-by-hour run sheet, then measures the launch cohort by activation and paid conversion instead of leaderboard rank.

product-launch 207 lines

No. 438

Programmatic SEO

Thousands of pages, each one worth indexing

Claude treats the dataset and the quality gate as the product, not the template. It validates that a page pattern matches real SERPs, measures per-page uniqueness instead of swapping variables into boilerplate, computes index, noindex, or skip per row at build time, and pilots a few hundred pages in their own sitemap segment before scaling, keeping clear of Google's scaled content abuse policy.

programmatic-seo 178 lines

No. 439

Referral Programs

Referral rewards you can afford and fraud can't farm

Claude sizes rewards from blended CAC and first-year margin, pays them only after a revenue event and a refund hold, and builds attribution with codes and server-side storage so referrals survive device switches and fresh app installs. It adds fraud controls for self-referrals, coupon sites, and cookie stuffing before launch, then tracks share rate, viral coefficient, cycle time, and referred-cohort retention.

referral-programs 197 lines

No. 440

Schema Markup

JSON-LD that earns rich results and matches the page

Claude stops pasting generic schema snippets and instead builds one connected JSON-LD graph per template from the same data that renders the page. It skips types Google no longer rewards, such as HowTo and most FAQPage use, escapes output safely in Next.js, and lints every template variant with a bundled script before you run the Rich Results Test.

schema-markup 212 lines · 3 files

No. 441

SEO Content Briefs

Briefs built from the SERP, not from keyword density

Claude reads the real top results before planning a page, records format consensus and SERP features like AI Overviews, and checks your site for cannibalization. The brief it hands over names one information-gain angle, an E-E-A-T evidence plan, a question-led outline, internal links in both directions, and metadata, so writers never need a keyword-count target.

seo-content-briefs 196 lines

No. 442

SEO Site Migration

Move domains or platforms and keep your traffic

Claude treats a migration as a redirect and parity project with a benchmark, not a launch checklist. It unions URLs from crawls, sitemaps, Search Console, analytics, backlinks, and logs, maps each to its true equivalent, tests the whole map with a bundled checker before and after launch, diffs templates on staging, and sets rollback triggers before launch day.

seo-site-migration 210 lines · 2 files

No. 443

Social Media Posts

Platform-native posts with hooks that pay off

Claude writes posts that fit each platform instead of pasting one blurb everywhere. It pulls a single takeaway from your source, drafts three hook options without engagement bait, structures threads so every post stands alone, respects character limits for X, LinkedIn, Threads, Bluesky, and Mastodon, and turns one blog post or talk into a scheduled set of standalone pieces.

social-media-posts 182 lines

★ No. 444

Technical SEO

Every page you want indexed, provably indexable

Turns Claude into a methodical technical SEO auditor. It maps every URL template to an intended index state, probes live responses with a bundled script, reads Search Console indexing reasons correctly, and fixes conflicting signals in impact order, from accidental noindex to redirect chains. It also sets AI-crawler rules deliberately instead of blocking bots by accident.

technical-seo 222 lines · 2 files

Choosing SEO & Growth skills

Install the skills that match requests you make every week; each costs about 100 tokens of standing context until it loads. If you are not sure where to begin, start with AI Search Optimization and Technical SEO. For background, read The Best Claude Code Skills in 2026, by Use Case, How to Install Claude Code Skills (5 Ways) and Personal vs Project Skills.

Install several

Install several at once

The installer accepts any number of skill names. Add --project to install into the current repository.

curl -fsSL https://claudeskills.page/install.sh | sh -s -- ai-search-optimization analytics-tracking-plan app-store-optimization cold-outreach competitor-analysis content-refresh conversion-optimization email-campaigns international-seo keyword-research landing-page-copy local-seo pricing-strategy product-launch programmatic-seo referral-programs schema-markup seo-content-briefs seo-site-migration social-media-posts technical-seo

SEO & Growth skills FAQ

How do I install every SEO & Growth skill at once?

Download the bundle at https://claudeskills.page/downloads/category/growth.zip and unzip it into ~/.claude/skills/ (or .claude/skills/ inside a repository). To pick a few, pass several names to the installer: curl -fsSL https://claudeskills.page/install.sh | sh -s -- ai-search-optimization analytics-tracking-plan app-store-optimization.

Will installing 21 skills slow Claude Code down?

No. Claude Code keeps only each skill's short description in context — roughly 100 tokens per skill — and loads the full instructions only when a request matches. Install the whole category if it fits your work; unused skills cost almost nothing.

Which SEO & Growth skill should I start with?

Start with AI Search Optimization, Technical SEO. They cover the most common requests in this category; add the rest as your work calls for them.