Agent skill · Data & Analytics

programmatic-seo

When the user wants to create SEO pages at scale using templates and data—including AI-assisted, grounded copy for per-URL differentiation (vs rigid mail-merge templates). Also use when the user mentions "programmatic SEO," "programmatic SEO pages," "template pages," "scale content," "location pages," "city pages," "comparison pages at scale," "X vs Y pages," "integration pages," "pages from data," "automated landing pages," or "programmatic landing pages." Uses a playbook matrix aligned to skills under skills/pages. For user-facing template galleries or marketplaces (browse → use), use templa

kostja94848★ · 1 repos on radarProfile →
cursorMIT
Install
npx skills add kostja94/marketing-skills --skill programmatic-seo --agent cursor

Same command for any agent — swap --agent for claude-code, codex, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 26 KB
Bundled scripts: none
Version: 1.4.1
Path: skills/seo/programmatic-seo/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 848

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Guides programmatic SEO by enabling a single template fed from a data source (database, API, or spreadsheet) to produce hundreds or thousands of unique pages. It emphasizes per-URL differentiation, using AI on top of a data spine to craft varied copy (intro, FAQs, tone, localization) while maintaining evidence blocks, data tiers, and QA processes.

How it works

Defines templates as reusable page structures and data as structured information (locations, products, prices, features). Describes an automation system that connects data to templates so pages can be generated dynamically or in bulk. An optional AI layer, applied to grounded inputs (row JSON + rules), produces varied copy per URL—guided by the data, not invented numbers. Requires a separate data layer to house facts, and a QA step where human review ensures fields are complete and citations are present. AI should ground outputs to verified numbers from the data pipeline, and not fabricate statistics.

When to use it

Use when scaling SEO pages with template-driven, data-backed content and when you need per-URL differentiation (e.g., localized, feature-focused, or comparison pages). It applies across tiers from product-generated to public data, with AI assisting generation across these tiers while relying on a verified data source.

What it can touch

Touches templates, data sources, and the AI layer to generate content. Requires passing structured inputs (JSON/CSV rows) into prompts and producing per-URL sections like intros, FAQs, and emphasis areas. The workflow relies on a data spine and an evidence block per page to ensure auditable outputs.

Caveats

Stresses the importance of provenance and freshness: log data sources, update frequencies (e.g., ratings every 90 days, prices every 30 days), and versioned templates. Advises against inventing numbers; use AI to rephrase or expand around verifiable data. Encourages human or automated QA before publish and discloses AI usage where appropriate.

From the SKILL.md

# SEO: Programmatic SEO Guides programmatic SEO—creating large numbers of SEO-optimized pages automatically using templates and structured data, rather than writing each page manually. **Classic “mail merge” pSEO** (one rigid template + swapped variables) often produced **low differentiation** and thin-feeling URLs. **With AI used responsibly on top of the same data spine**, you can scale **per-URL customization**—intent-aligned copy, section depth, FAQs, tone, localization—while still following **evidence blocks**, **data tiers**, and **QA** (see **Data strength hierarchy** and **AI-assisted generation** below). **When invoking**: On **first use**, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On **subsequent use** or when the user asks to skip, go directly to the main output. **Project context**: If `.claude/project-context.md` or `.cursor/project-context.md` exists, read product/ICP sections before proposing playbooks or page types. ## Definition **Programmatic SEO** = Building a single template and populating it with data from a database, API, or spreadsheet to generate hundreds or thousands of unique pages. Each

What's inside
Steps it walks through
  1. Definition
  2. Classic limits vs AI-enhanced differentiation
  3. Three-Part Framework
  4. Page Playbook Matrix (skills/pages)
  5. Choosing a Playbook
  6. Template Structure (Recommended)
  7. Data strength hierarchy (defensibility)
  8. Tier 2 — Product-derived (practical)
  9. Tier 3 — UGC / customer (practical)
  10. Tier 4 — Licensed / partner (practical)
  11. Tier 5 — Public / scraped (practical)
  12. AI-assisted generation (cross-tier)
  13. Operational requirements (all tiers)
  14. Ideal Use Cases
More from marketing-skills
All skills →
About this skill
What does the programmatic-seo skill do?

When the user wants to create SEO pages at scale using templates and data—including AI-assisted, grounded copy for per-URL differentiation (vs rigid mail-merge templates). Also use when the user mentions "programmatic SEO," "programmatic SEO pages," "template pages," "scale content," "location pages," "city pages," "comparison pages at scale," "X vs Y pages," "integration pages," "pages from data," "automated landing pages," or "programmatic landing pages." Uses a playbook matrix aligned to skills under skills/pages. For user-facing template galleries or marketplaces (browse → use), use templa

How do I install it?

Run `npx skills add kostja94/marketing-skills --skill programmatic-seo --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From kostja94/marketing-skills, a repository with 848 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going