mcpField
S
seo-programmatic

seo-programmatic

github.com/agricidanielMarketing & growth89473 installsUpdated 2w ago
Repository

About seo-programmatic

seo-programmatic is a ChatGPT skill for evaluating programmatic SEO datasets, templates, and URL groups. It turns data quality and page-value analysis into a pilot architecture, acceptance criteria, and a measured plan for expansion.

Key features

  1. 01Inspect dataset quality and licensing
  2. 02Assess distinct value across pages
  3. 03Plan URL and internal-link structure
  4. 04Review canonical and noindex choices
  5. 05Set review and expansion criteria

Use cases

  1. 01Evaluate a proposed URL family
  2. 02Design a small programmatic SEO pilot
  3. 03Review page data before scaling publication

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/agricidaniel/chatgpt-seo --skill seo-programmatic

After installing, type/seo-programmaticin Claude Code to confirm it loaded.

Details

From the project README

Programmatic SEO

Input

A dataset, template, representative pages or proposed URL family.

Evidence and runtime

If a skill-resource reader fails to open a linked supporting file, try the available file or execution tool using the installed plugin root returned by the host or resolved from this skill's location. Do not hardcode a home folder, version, or working directory. Distinguish a failed reader call from an absent file, and files actually attempted from files not attempted. Report a resource as unavailable only after the supported access paths have failed. If no file or execution access is available, continue within the evidence you can read and state that limit.

Read the operating contract when this workflow is selected. Use runtime and data paths when choosing a tool or handling missing data. Recheck relevant search facts and primary sources before date-sensitive claims. For a quantitative diagnostic, read scoring; unavailable categories stay unknown.

Supporting resources

Read only the resources needed for the selected part of this task:

Workflow

  1. Inspect the dataset's grain, keys, duplicates, missingness, freshness and licensing. Match each proposed page to a distinct useful task.
  2. Evaluate actual differentiating content, evidence and functionality beyond swapping a city, product or keyword. Sample both rich and sparse rows.
  3. Design stable unique URLs, useful hubs, related links, breadcrumbs and explicit handling of empty or low-value records.
  4. Review canonical/noindex decisions for true duplicates and faceted or paginated cases. Do not automatically noindex or canonicalize distinct useful pages.
  5. Define row-level content acceptance and a representative human review sample. For a small pilot, measure rendering, crawl behavior and indexing evidence before scaling.
  6. Check current scaled-content and site-reputation policies. Treat uniqueness percentages, batch sizes and word counts as internal review choices, not Google rules.

Deliverable

A data/template diagnosis, pilot architecture, row-level acceptance criteria, index-management plan and measurable expansion decision.

Boundary

Do not generate fake location presence, product facts or mass pages with no standalone value. A quality plan does not authorize publication.

Adapted from the public Claude SEO seo-programmatic workflow.

Comments

Markdown supported