seo-drift

Technical SEO

agricidaniel/claude-seoskills.sh ↗

Installs

4,012

deduplicated, at the last sync

Since we started

+2.8%

35 readings, about 2 hours apart. Not a live curve.

Our category

Technical SEO

ours

Last read

Sep 3, 2026

from the directory

Our brief

ours

This skill monitors SEO drift by capturing baselines of critical on-page elements for a given URL [2]. It detects changes (regressions) over time by comparing the current page state against a stored baseline [2]. This helps users track potential issues with SEO elements like title tags, canonical URLs, and schema structure [1], [2].

What it produces
  • JSON report containing triggered rules, old/new values, severity, and actions
  • HTML report (drift-report.html) after comparison
  • JSON array of baselines with timestamps and comparison summaries
What it needs
  • Target URL string
  • Optional --skip-cwv flag for CWV checks
Paid services

not detected

The evidence mentions an API key in relation to the skill's files, but it does not establish any requirement for paid services or credentials.

Registration

not detected

The evidence contains no information regarding user registration requirements.

Limits and human review

The skill cannot predict if a detected change will cause measurable traffic loss; it only flags potential issues [1]. Furthermore, the comparison command requires that a baseline must first be captured for the URL before any changes can be compared against [2].

Evidencestatic findingsskills/seo-drift/references/comparison-rules.md:1-54skills/seo-drift/SKILL.md:1-220
static findingsstatic_finding
[{"code":"api_key_mention","match":"API key","path":"SKILL.md"}]
skills/seo-drift/references/comparison-rules.md1–54 · excerpt truncated
# SEO Drift Comparison Rules

17 rules across 3 severity levels. Each rule compares a specific SEO element
between the stored baseline and the current page state.

---

## CRITICAL (Immediate Action Required)

These changes typically cause measurable traffic loss within days.

### Rule 1: Schema/JSON-LD Completely Removed
- **Compare**: Baseline `schema` array has items, current is empty
- **Threshold**: Any schema present before, none now
- **Action**: Restore structured data immediately. Eligible rich results (Product, Review, LocalBusiness, and similar supported types) can drop from SERPs quickly; retired types (FAQ, HowTo) should not be treated as rich-result losses.
- **Cross-ref**: `/seo schema <url>`

### Rule 2: Canonical URL Changed
- **Compare**: Baseline `canonical` vs current `canonical`
- **Threshold**: Different non-null values (after normalization)
- **Action**: Verify the new canonical is intentional. Incorrect canonicals redirect ranking signals to wrong page.
- **Cross-ref**: `/seo technical <url>`

### Rule 3: Canonical URL Removed
- **Compare**: Baseline `canonical` was set, current is `null`
- **Threshold**: Had value, now missing
- **Action**: Restore canonica
skills/seo-drift/SKILL.md1–220
---
name: seo-drift
description: >
  SEO drift monitoring: capture baselines of SEO-critical elements, detect changes,
  and track regressions over time. Git for SEO: baseline, diff, and track changes
  to your on-page SEO. Use when user says "SEO drift", "baseline", "track changes",
  "did anything break", "SEO regression", "compare SEO", "before and after",
  "monitor SEO changes", or "deployment check".
user-invocable: true
argument-hint: "baseline|compare|history <url>"
license: MIT
metadata:
  author: AgriciDaniel
  original_author: "Dan Colta (Pro Hub Challenge)"
  version: "2.2.5"
  category: seo
---

# SEO Drift Monitor (April 2026)

Git for your SEO. Capture baselines, detect regressions, track changes over time.

---

## Commands

| Command | Purpose |
|---------|---------|
| `/seo drift baseline <url>` | Capture current SEO state as a "known good" snapshot |
| `/seo drift compare <url>` | Compare current page state to stored baseline |
| `/seo drift history <url>` | Show change history and past comparisons |

---

## What It Captures

Every baseline records these SEO-critical elements:

| Element | Field | Source |
|---------|-------|--------|
| Title tag | `title` | `pa

Read 3 of 3 text files in the skill.

Checked September 2026 · GemmaWritten from the skill's published files. Check the source before relying on access or cost details.

Installfrom the directory

npx skills add https://github.com/agricidaniel/claude-seo

Installing happens there, not here. We are an index with an opinion, not a mirror.

What is inside itfrom the directory

references/comparison-rules.md
SKILL.md

2 files — names only. The directory does not report sizes.

What the auditors foundfrom the directory

A skill is instructions your agent will follow and scripts it may run, so who checked it matters as much as how many people installed it.

Gen Agent Trust HubThe seo-drift skill is a tool for monitoring changes in SEO-critical elements of web pages by capturing baselines and tracking regressions. It uses local Python scripts for data processing and a local SQLite database for storage. The skill includes security claims such as SSRF protection for external requests and the use of parameterized SQL queries to prevent injection attacks.May 11, 2026 · SAFEpass
SocketNo alertsMay 11, 2026pass
SnykRisk: MEDIUM · 1 issueMay 11, 2026 · MEDIUMwarn
ZeroLeaksScore: 93/100 · 2 sections analyzedApr 16, 2026 · NONEpass

Installs, reading by readingours

3.9k
4k
Aug 30, 202635 readings over 5 days, drawn as the last reading of each day.Sep 3, 2026

Axis starts at 3.9k, not zero — the range is 3.9k to 4k.

Asked out loudspoken, not typed

The same skill in the words people use speaking to an assistant rather than typing into a box. Each one carries the situation it came from, and each answer says only what the skill's own files support.

Setting up monitoringHow do I start tracking my SEO performance?

You need to run the baseline command first. This captures the current state of all critical elements, like titles and schema, as a 'known good' snapshot for that URL [2].

Post-deployment checkWhat if I just deployed changes? Did anything break?

You can run the compare command. It will check your current page state against the stored baseline and report any detected regressions, such as a missing title tag or canonical URL [2], [1].

Checking requirementsDo I need an API key to use this?

The evidence mentions 'API key' in relation to the skill's files, but it does not specify whether or when one is required for usage.

Filed alongside itours