mcpbeat Sign in

SEO Drift Skill for Claude

Compare SEO snapshots, baselines or exports and explain observable changes. Use for SEO drift or before/after checks.

725 tokens
context cost
SKILL.md, read when the skill is used
2
files
plus reference files
0
copies elsewhere
how many repositories repackaged it
834
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/AgriciDaniel/chatgpt-seo --skill seo-drift

What comes with it

206 bytes besides the instruction
agents/openai.yaml

The instruction itself

7 sections, as written by the author

SEO change comparison

Input

Two named snapshots/exports or a request to capture a baseline of available evidence.

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:

  • control regression retesting.

Workflow

  • Capture or load only the stated material, with URL, date, source/tool and device/scope. Use available source HTML and the offline analyzer for repeatable static snapshots.
  • Use ../../scripts/compare_snapshots.py for two analyzer outputs when Python is available. It requires matching URLs unless an explicit migration comparison is intended.
  • Compare metadata, index controls, canonicals, hreflang, headings, images, links, structured-data fingerprints and content heuristics.
  • Validate suspected control regressions against the intended change. Small HTML formatting changes and raw hashes are not automatically SEO defects.
  • Keep traffic/ranking comparisons separately scoped to comparable dates and filters. Do not infer causation from a snapshot difference.
  • Provide a retest and recovery sequence if a regression is evidenced. If ongoing monitoring is requested, use a supported scheduler only within the user's explicit scope.

Deliverable

A before/after change report, control-risk review and concrete validation steps. For a baseline-only request save an artifact when supported.

Boundary

This package does not silently store history, start background jobs or schedule monitoring.

Adapted from the public Claude SEO seo-drift workflow.

How to use it

Copy the folder

Take agricidaniel/seo-drift from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.