mcpbeat Sign in

Programmatic SEO Agent Skill

Builds large sets of search-targeted pages from a template and a dataset — the location, comparison, integration, and use-case pages that capture long-tail demand at scale. Use this when there is a repeating query pattern with real volume, when a dataset could answer many similar searches, or to judge whether a programmatic approach is viable before building it.

584 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
220
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/cbrock84/headcount --skill programmatic-seo

The instruction itself

5 sections, as written by the author

Programmatic SEO

Done well, one template covers thousands of real searches. Done badly, it is a mass of thin pages

that damages the whole domain.

Qualify before building

All four must hold:

  • A real query pattern with verified volume across many instances — not one popular term and a

long tail of zeroes.

  • Data you actually have, at quality, for most instances. Missing data produces empty pages,

and empty pages are the failure mode.

  • Genuine per-page value. If two pages differ only by a swapped noun, they are duplicates

however they are generated.

  • A reason to be better than what ranks now. Usually completeness, freshness, or data nobody

else has.

Fail any one and the answer is fewer, better pages.

Building

  • Design the best single page first, by hand, and confirm it is genuinely useful. Then find what

in it is variable. Templating before you know the good page scales a mediocre one.

  • Vary the substance, not just the strings. Each page needs data, comparisons, or context

specific to it.

  • Set a minimum data threshold. Below it, the page does not get generated. This single rule

prevents most programmatic disasters.

  • Internal linking is not optional — thousands of orphaned pages will not be crawled. Build hub

pages and cross-links into the template.

  • Roll out in batches. Publish a few hundred, wait for indexation and performance, then

continue. A full launch that goes wrong is hard to unwind.

Maintaining

Stale programmatic pages rot faster than editorial ones because there are so many. Set a refresh

cadence tied to the data source, and prune: pages with no impressions after two quarters should be

consolidated or removed. Volume is not the goal.

Never

  • Generate pages for instances with no data.
  • Spin text to create the appearance of uniqueness.
  • Launch without a plan for removing what does not work.

How to use it

Copy the folder

Take cbrock84/programmatic-seo from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.