Skip to content
SkillModel-led2,082 tokens in use

seo-programmatic

Plan and audit SEO pages generated at scale from data, with quality gates against thin content, scaled content abuse and index bloat.

31,136 stars on the repository MIT LicenseAgriciDaniel/claude-seo · skills/seo-programmatic
/plugin marketplace add AgriciDaniel/claude-seo /plugin install claude-seo@agricidaniel-claude-seo
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing seo-programmatic costs

72tokens idle
2,082tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter15/15
  • Structure9/25
  • Examples3/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community72
  • Maturity32
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers