Skip to content

Skill · SEO Audit & Optimization Team

SEO Drift Comparison

Manually compare a page's current SEO-critical elements against a prior snapshot to catch regressions after a deploy.

What it is

Manually compare a page's current SEO-critical elements against a prior snapshot to catch regressions after a deploy.

A skill is a written procedure an agent loads when a job calls for it. This one is a single file, SKILL.md, and the whole file is on this page.

File
SKILL.md
Length
22 lines · 1 min read
Category
Marketing
License
MIT
Author
Brainwrite
Words
267

Paste it into any agent’s instructions (CLAUDE.md, AGENTS.md or a custom GPT), or add the team to Brainwrite and it arrives switched on.

Use it

Use this skill in Brainwrite.

  1. 1

    Add the SEO Audit & Optimization Team

    Its agents carry this skill. You preview every agent and skill first; skills arrive switched on and routines paused.

    Install in Brainwrite →
  2. 2

    Brief your Chief of Staff

    “Use the SEO Drift Comparison skill for this: [describe the job]. Show me the plan first, and send, post or change nothing.”

  3. 3

    Approve what matters

    The agent follows the skill and brings the result back. Anything that sends, posts or changes data waits for your approval in Ask mode.

    How approvals work →

Use this when

SEO drift, did anything break, SEO regression, before and after, deployment check.

Process

This is a redesigned, lighter version of the original tool's automated baseline system: the source project stores snapshots in a local SQLite database across sessions, which Brainwrite's persona-only team format has no equivalent for. Instead, this playbook works from whatever the user gives it: a saved copy of the page's title/meta/canonical/headings/schema from before a deploy (pasted text, a prior audit report, or a screenshot), compared against a fresh fetch of the current page.

Compare these SEO-critical elements between the two snapshots: title tag, meta description, canonical URL, meta robots directives, H1/H2/H3 headings, JSON-LD schema (presence and type), Open Graph tags, and HTTP status code.

Classify every difference by severity: CRITICAL (a change likely to cause real traffic loss — canonical removed or changed unexpectedly, noindex added, schema removed, status code changed to an error) needs an immediate look; WARNING (a change that could matter — title or meta changed, heading structure changed) needs review within the week; INFO (a change that's probably intentional, like an updated headline) is awareness-only.

When a regression is found, route to the right specialist: schema changes to schema-markup, a Core Web Vitals regression to technical-seo-audit or core-web-vitals-data, a title/meta/heading change to content-quality-eeat, a canonical or noindex change to technical-seo-audit.

Report a diff table (element, before, after, severity) and a plain-language summary of what changed and what to check first. Be explicit that this compares whatever two snapshots the user supplies — it isn't continuous automated monitoring the way the original tool's SQLite-backed version was.

Put this skill to work.

Download Brainwrite, add the team that carries it, and tell your Chief of Staff what needs doing.

macOS today. Windows and Linux are coming soon.