mcpField
S
seo-google

seo-google

github.com/agricidanielMarketing & growth89475 installsUpdated 2w ago
Repository

About seo-google

seo-google is a ChatGPT skill for analyzing supplied Google search data and creating a source-scoped SEO action plan. It emphasizes metric definitions, comparable periods, segmentation, and separating field performance data from lab results; it does not provide Google OAuth access.

Key features

  1. 01Reviews supplied search-property exports
  2. 02Checks scope, filters, and reporting context
  3. 03Compares periods and segments page/query patterns
  4. 04Separates CrUX field data from lab results
  5. 05Creates validation steps for SEO findings

Use cases

  1. 01Analyze a supplied Google search report
  2. 02Investigate changes in clicks, impressions, or CTR
  3. 03Review performance evidence by device and date
  4. 04Plan checks for indexing or URL inspection

Install

Copy the command and run it in a terminal.

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

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

Details

From the project README

Google search data

Input

An explicit property export/tool result, dates, filters and report type.

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. Identify the property, row grain, time window, timezone, search type, device/country filters, aggregation and any provider truncation.
  2. Read data analysis for metric definitions and comparability checks. When a CSV and Python are available, run the offline GSC calculator. Report clicks, impressions and CTR with their denominators; aggregate position with impression weights when that matches the export. The helper's totals cover supplied rows only. Use --metadata with a user-supplied property/date/filter sidecar when context is known; it remains supplied scope, not independently verified account access.
  3. Compare equal-length periods and segment page/query/device patterns. Keep missing/private queries and reporting lag visible. A traffic drop's timing is not proof of an algorithm cause.
  4. For performance data, separate PageSpeed lab runs from CrUX field samples and page-level from origin-level results. Record device and dates.
  5. Translate supported patterns into specific page/technical hypotheses and the next check. Keep GSC clicks separate from GA4 sessions and conversions.
  6. For inspection or indexing requests, use actual returned status and current API scope. Draft steps rather than running write endpoints without explicit authorization.

Deliverable

A source-scoped metric readout, segment findings, calculation notes, priorities and a validation plan. Use the linked performance template for a substantial metric report and the index template for URL inspection or discovery evidence.

Boundary

This package has no Google OAuth integration. Never request a key/token in chat, invent account access, or use the Indexing API for ordinary articles.

Adapted from the public Claude SEO seo-google workflow.

Comments

Markdown supported