mcpField
S
seo-sitemap

seo-sitemap

github.com/agricidanielMarketing & growth89478 installsUpdated 2w ago
Repository

About seo-sitemap

seo-sitemap is a ChatGPT skill for reviewing sitemap XML or an inventory of intended canonical URLs. It validates sitemap structure and checks coverage against separately supplied crawl evidence, without treating XML alone as proof of indexability.

Key features

  1. 01Discover sitemap candidates
  2. 02Validate sitemap XML structure and limits
  3. 03Compare entries with crawl evidence
  4. 04Review lastmod and URL coverage
  5. 05Generate sitemap or index files

Use cases

  1. 01Auditing a sitemap URL or XML file
  2. 02Finding gaps against intended canonical URLs
  3. 03Checking sitemap entries against crawl results
  4. 04Generating sitemap files from known URLs

Install

Copy the command and run it in a terminal.

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

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

Details

From the project README

Sitemap review

Input

A sitemap URL/XML document or an explicit inventory of intended canonical URLs.

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. Discover sitemap candidates from observed robots Sitemap declarations, linked indexes and common paths when browsing can inspect them. A declaration alone is not proof of a working sitemap.
  2. Use ../../scripts/validate_sitemap.py when a supplied XML file and Python are available. Record index children that were not fetched.
  3. Check protocol namespace, absolute locations, exact duplicates, date syntax, the 50,000-entry and 50 MiB uncompressed limits. Treat priority/changefreq as ignored hints for Google.
  4. Join entries with separately measured status, canonical and index-control data. XML by itself cannot establish that entries return 200 or are indexable.
  5. Use lastmod only for real significant content changes. Do not refresh every URL date to the current day without evidence.
  6. Generate XML from known intended URLs, escaping values and splitting at protocol limits. Keep coverage gaps explicit rather than inventing site URLs.

Deliverable

A sitemap findings report or generated sitemap/index files with URL count, validation scope and a list of untested destinations.

Boundary

Cross-host sitemap arrangements can be valid when authorized; investigate their setup. Extension-specific image/video/news requirements need their own current checks.

Adapted from the public Claude SEO seo-sitemap workflow.

Comments

Markdown supported