programmatic-seo

Trigger phrases

Phrases that activate this skill when typed to Claude Code:

• programmatic SEO
• pSEO
• template pages
• pages at scale
• data-driven pages

What it does

programmatic-seo is a Claude Code skill from Corey Haines’s marketing-skills repo. It turns Claude into a pSEO architect who designs templated page programs — directory pages, location pages, “[X] for [Y]” pages, integration pages — with enough unique data per page to avoid thin-content penalties and thoughtful internal-linking. The skill activates when you mention “programmatic SEO”, “pSEO”, “template pages”, or “generate 100 pages”.

The output of a session is a pSEO plan: data source identification, page-template structure (which sections are static vs data-driven vs uniquely written), URL pattern, internal-linking strategy, indexation control plan, and a quality-bar definition that prevents the spam-trap version of pSEO.

When to use it

Reach for it when:

• You have data (a directory, integrations, locations) that maps to long-tail search demand
• A competitor is winning a category with templated pages and you can do better with sharper data
• You want a content moat that doesn’t require writing 500 individual posts

When not to reach for it:

• You don’t actually have unique data per page — that’s just thin content
• Your domain authority is too low to support 1000 new URLs without crawl-budget issues

Install

The skill is distributed via Corey Haines’s marketing-skills repo. Install via the repo’s recommended path — copy the programmatic-seo SKILL.md into your project’s .claude/skills/programmatic-seo/ directory, or use the repo’s plugin install if you’ve set it up.

Once installed, the skill activates on the trigger phrases above. The first time it runs, it will check for .agents/product-marketing-context.md (or .claude/product-marketing-context.md) — populating that file with your product context first dramatically improves output quality across all of Haines’s marketing skills.

What a session looks like

A typical session has three phases:

1. Data + intent fit. What data do you have, what queries does it map to, what’s the searcher’s intent? The skill rejects ideas where the data is too generic to differentiate.
2. Template design. Section structure, ratio of templated vs unique content (the unique percentage is the make-or-break), URL pattern, schema markup per page type.
3. Quality + indexation. A quality bar each page must meet before it’s indexed (content depth, data uniqueness), staged rollout, and indexation controls (noindex for thin pages, sitemap chunking).

The discipline that makes it work: enough unique data per page that each one would justify being indexed individually. The skill’s pSEO is library-quality, not spam-quality.

Receipts

Honest reporting on what programmatic-seo produces and where it has limits:

Where it works well:

• The unique-content-percentage discipline is what separates real pSEO from doorway pages
• Staged-rollout with indexation controls catches thin pages before they hurt the domain
• Template structure with internal linking compounds — pages bring each other up

Where it backfires:

• pSEO is engineering-heavy; the skill scopes the plan but you still need to ship the build
• Without data verification the program can publish errors at scale; QA matters more than for one-off content

Pattern that works: ship 50 pages first, watch indexation and rankings for a month, then scale. Launching 5,000 pages on day one is how programs get the manual-action email.

Source and attribution

Originally written by Corey Haines. The canonical SKILL.md and any supporting files live in the programmatic-seo folder of his marketing-skills repository.

License: MIT. You can install, adapt, and redistribute the skill, with attribution preserved.

This page documents the skill from a practitioner’s perspective. For the formal spec and any updates, defer to the source repo.