seo-programmatic covers pages built from CSV, JSON, API or database sources. It assesses the data source, plans the template engine and variable injection points, sets URL patterns, automates internal linking with hub and spoke structure and breadcrumbs, and defines canonical and sitemap rules.
Its quality gates raise a warning at 100 or more pages without review and a hard stop at 500 or more without justification, flag pages under 40 percent unique content or 300 words, and recommend progressive rollout in batches of 50 to 100 pages.
What You Get
- A programmatic SEO score with six category scores
- A list of issues by priority with data, template and URL fixes
- Uniqueness measurement rules that exclude headers, footers and navigation
- A rollout plan with human review samples and batch publishing
Common Use Cases
- Plan integration or glossary pages built from a database
- Audit city and service pages for city-swap duplication
- Decide which generated pages to noindex before a launch
- Set sitemap splitting and canonical rules for a large page set
What Makes It Unique
It turns scaled content abuse rules into thresholds the agent can apply: a swap test for location pages, a list of page types that are safe at scale and those that carry penalty risk, and a halt when the hard stop is reached. Metadata uniqueness is scored apart from body copy.
Under The Hood
The skill is written instructions with no scripts and no reference files. It tells the agent to inspect the data source, which can be a CSV, an API endpoint or a database, and to fetch live pages from a URL over the network when one is supplied. It writes no files itself beyond the report the user asks for. The frontmatter declares no access. Fetched pages and API responses are to be treated as untrusted data.