Use an open-source SEO playbook with Search Console scripts and matched controls to test content changes
A public repo documents a content site's SEO system: scripts that split human from machine search queries, judge rewrites against untouched control pages, and guard against traffic drops.
Evidence: The author reports this. We have not checked it beyond reading the source.
The business problem
Content teams cannot tell whether title or content changes caused traffic changes, and AI-heavy publishing risks thin pages and silent regressions.
What was tried
Node scripts read Search Console data to separate human queries from AI-agent impressions, then compare rewritten pages against untouched control pages instead of raw before and after numbers. Further scripts check traffic drops, sitemap health and schema markup, and verify that each fact's quote appears on its source page. Configs hold quality gates, title rules and refresh rules, and a chapter covers running scheduled and CI jobs cheaply.
What was reported (positive)
The author reports 11.08M impressions and 44.8K clicks over 90 days on one site (7.7x impressions and 12x clicks versus the prior 90 days), title rewrites outgrowing controls by roughly 19 to 48 points, and snippet rewrites having no effect.
Limitations
All results come from one site and are self-reported, and the underlying data file was not read. The causal claims depend on the author's control design and chosen windows. Scripts need a Google Cloud setup and access to source files, so hosted site builders are limited to URL-based tools. No cost figures back the 'cheaply' claim. It is MIT-licensed and early (26 commits, 71 stars, no releases).
What you need
Node 20 or later, Search Console access through Google Cloud, and a site whose source files you can run scripts against.
Sources
- GitHub (TraceCohenTech/ai-seo-playbook) ↗ Code repository, publication date unknown
Source published: unknown. Last reviewed here: October 11, 2026. Spot a mistake? Tell us.
Tools in this workflow
- Google Search Console: Source of query and page dataTry Google Search Console
Related workflows
Send a Monday business metrics email from Stripe, Notion and Sheets with Claude writing the narrative in n8n
A shared n8n template pulls last week's Stripe revenue, Notion deal pipeline and a Sheets row of support numbers, has Claude write a three-paragraph summary, and emails and posts it to Slack.
Give Claude Code a website team of connectors: Search Console, DataForSEO, Screaming Frog and PostHog
A founder connects five MCP servers to Claude Code, each acting as an SEO analyst, market researcher, technical auditor or product analyst, with the prompts he uses, including a weekly rage-click report.
Get a Monday analytics report by having a Claude skill read scheduled Google Analytics and Search Console exports
A newsletter writer has Google Analytics and Search Console email six CSV reports each Monday, and a Claude skill compares the week to the last and saves a visual report and the raw data to a dated folder.
Decide what to write next by checking Search Console queries and competitors with an MCP-driven SEO research agent
A newsletter writer built a coding-agent workflow that starts from his own Search Console queries, checks demand and competitors through a keyword tool, and labels each idea as write, update, expand, test or ignore.