Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
agricidaniel avatar

Seo Drift

  • 3k installs
  • 12.5k repo stars
  • Updated July 27, 2026
  • agricidaniel/claude-seo

seo-drift is an agent skill that captures SEO baselines, compares regressions with seventeen rules, and tracks change history per URL.

About

The seo-drift skill provides Git-for-SEO baseline, compare, and history workflows for on-page SEO element regressions. Commands capture baseline snapshots, compare current state to stored baselines, and show change history per URL in local SQLite at ~/.cache/claude-seo/drift/baselines.db. Captured elements include title, meta description, canonical, robots, H1 through H3 arrays, JSON-LD schema, Open Graph, Core Web Vitals, HTTP status, and SHA-256 html and schema hashes. Comparison engine applies seventeen rules across CRITICAL, WARNING, and INFO severities with thresholds and recommended actions in comparison-rules.md. Critical changes imply SEO-breaking regressions needing immediate response while warnings need investigation within a week. Pairs with render and parse scripts for live page extraction. Use when monitoring SEO drift, deployment checks, before and after comparisons, or did anything break SEO regression questions. The workflow follows the source SKILL.md contract with progressive reference loading, clear trigger phrases, and practical steps developers can apply directly in agent sessions.

  • Baseline, compare, and history commands per URL in local SQLite storage.
  • Captures title, canonical, headings, schema, OG, CWV, status, and content hashes.
  • Seventeen comparison rules across CRITICAL, WARNING, and INFO severities.
  • Git-for-SEO metaphor: baseline known-good then diff on deploy or schedule.
  • Stores data at ~/.cache/claude-seo/drift/baselines.db locally.

Seo Drift by the numbers

  • 3,035 all-time installs (skills.sh)
  • +405 installs in the week ending Jul 28, 2026 (Skillselion tracking)
  • Ranked #199 of 1,881 Marketing & SEO skills by installs in the Skillselion catalog
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
At a glance

seo-drift capabilities & compatibility

Capabilities
baseline capture of seo critical elements · seventeen rule comparison engine · severity classified drift reporting · per url history tracking · html and schema hash change detection
Use cases
seo · debugging
From the docs

What seo-drift says it does

SEO drift monitoring: capture baselines of SEO-critical elements, detect changes
SKILL.md
Git for your SEO. Capture baselines, detect regressions, track changes over time.
SKILL.md
npx skills add https://github.com/agricidaniel/claude-seo --skill seo-drift

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs3k
repo stars12.5k
Security audit2 / 3 scanners passed
Last updatedJuly 27, 2026
Repositoryagricidaniel/claude-seo

Did my deploy break title, canonical, schema, or Core Web Vitals compared to the last known-good baseline?

Monitor SEO drift by capturing baselines, comparing 17 severity rules, and tracking title, schema, canonical, and CWV regressions over time.

Who is it for?

Developers and SEO operators monitoring on-page SEO stability across releases and content edits.

Skip if: Skip for first-time page optimization without an existing baseline to compare against.

When should I use this skill?

Use when user says SEO drift, baseline, track changes, SEO regression, compare SEO, or deployment check.

What you get

Severity-classified drift report with CRITICAL, WARNING, and INFO changes versus stored baseline.

  • Drift severity report
  • Per-rule remediation actions

By the numbers

  • Defines 17 SEO drift comparison rules
  • Organizes rules across 3 severity levels

Files

SKILL.mdMarkdownGitHub ↗

SEO Drift Monitor (April 2026)

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

---

Commands

CommandPurpose
/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:

ElementFieldSource
Title tagtitleparse_html.py
Meta descriptionmeta_descriptionparse_html.py
Canonical URLcanonicalparse_html.py
Robots directivesmeta_robotsparse_html.py
H1 headingsh1 (array)parse_html.py
H2 headingsh2 (array)parse_html.py
H3 headingsh3 (array)parse_html.py
JSON-LD schemaschema (array)parse_html.py
Open Graph tagsopen_graph (dict)parse_html.py
Core Web Vitalscwv (dict)pagespeed_check.py
HTTP status codestatus_codefetch_page.py
HTML content hashhtml_hash (SHA-256)Computed
Schema content hashschema_hash (SHA-256)Computed

---

How Comparison Works

The comparison engine applies 17 rules across 3 severity levels. Load references/comparison-rules.md for the full rule set with thresholds, recommended actions, and cross-skill references.

Severity Levels

LevelMeaningResponse Time
CRITICALSEO-breaking change, likely traffic lossImmediate
WARNINGPotential impact, needs investigationWithin 1 week
INFOAwareness only, may be intentionalReview at convenience

---

Storage

All data is stored locally in SQLite:

~/.cache/claude-seo/drift/baselines.db

Tables

  • baselines: Captured snapshots with all SEO elements
  • comparisons: Diff results with triggered rules and severities

URL normalization ensures consistent matching: lowercase scheme/host, strip default ports (80/443), sort query parameters, remove UTM parameters, strip trailing slashes.

---

Command: baseline

Captures the current state of a page and stores it.

Steps: 1. Validate URL (SSRF protection via google_auth.validate_url()) 2. Fetch page via scripts/fetch_page.py 3. Parse HTML via scripts/parse_html.py 4. Optionally fetch CWV via scripts/pagespeed_check.py (use --skip-cwv to skip) 5. Hash HTML body and schema content (SHA-256) 6. Store snapshot in SQLite

Execution:

python3 scripts/drift_baseline.py <url>
python3 scripts/drift_baseline.py <url> --skip-cwv

Output: JSON with baseline ID, timestamp, URL, and summary of captured elements.

---

Command: compare

Fetches the current page state and diffs it against the most recent baseline.

Steps: 1. Validate URL 2. Load most recent baseline from SQLite (or specific --baseline-id) 3. Fetch and parse current page state 4. Run all 17 comparison rules 5. Classify findings by severity 6. Store comparison result 7. Output JSON diff report

Execution:

python3 scripts/drift_compare.py <url>
python3 scripts/drift_compare.py <url> --baseline-id 5
python3 scripts/drift_compare.py <url> --skip-cwv

Output: JSON with all triggered rules, old/new values, severity, and actions.

After comparison, offer to generate an HTML report:

python3 scripts/drift_report.py <comparison_json_file> --output drift-report.html

---

Command: history

Shows all baselines and comparisons for a URL.

Execution:

python3 scripts/drift_history.py <url>
python3 scripts/drift_history.py <url> --limit 10

Output: JSON array of baselines (newest first) with timestamps and comparison summaries.

---

Cross-Skill Integration

When drift is detected, recommend the appropriate specialized skill:

FindingRecommendation
Schema removed or modifiedRun /seo schema <url> for full validation
CWV regressionRun /seo technical <url> for performance audit
Title or meta description changedRun /seo page <url> for content analysis
Canonical changed or removedRun /seo technical <url> for indexability check
Noindex addedRun /seo technical <url> for crawlability audit
H1/heading structure changedRun /seo content <url> for E-E-A-T review
OG tags removedRun /seo page <url> for social sharing analysis
Status code changed to errorRun /seo technical <url> for full diagnostics

---

Error Handling

ScenarioAction
URL unreachableReport error from fetch_page.py. Do not guess state. Suggest user verify URL.
No baseline exists for URLInform user and suggest running baseline first.
SSRF blocked (private IP)Report validate_url() rejection. Never bypass.
SQLite database missingAuto-create on first use. No error.
CWV fetch fails (no API key)Store null for CWV fields. Skip CWV rules during comparison.
Page returns 4xx/5xxStill capture as baseline (status code IS a tracked field).
Multiple baselines existUse most recent unless --baseline-id specified.

---

Security

  • All URL fetching goes through scripts/fetch_page.py which enforces SSRF protection

(blocks private IPs, loopback, reserved ranges, GCP metadata endpoints)

  • No curl, no subprocess HTTP calls -- only the project's validated fetch pipeline
  • All SQLite queries use parameterized placeholders (?), never string interpolation
  • TLS always verified -- no verify=False anywhere in the pipeline

---

Typical Workflows

Pre/Post Deployment Check

/seo drift baseline https://example.com     # Before deploy
# ... deploy happens ...
/seo drift compare https://example.com      # After deploy

Ongoing Monitoring

/seo drift baseline https://example.com     # Initial capture
# ... weeks later ...
/seo drift compare https://example.com      # Check for drift
/seo drift history https://example.com      # Review all changes

Investigating a Traffic Drop

/seo drift compare https://example.com      # What changed?
/seo drift history https://example.com      # When did it change?

Related skills

Forks & variants (1)

Seo Drift has 1 known copy in the catalog totaling 22 installs. They canonicalize to this original listing.

How it compares

Choose seo-drift for post-deploy regression checks against a known baseline; use initial SEO audit skills when establishing metadata strategy for the first time.

FAQ

Who is seo-drift for?

Developers and software engineers and SEO operators monitoring on-page SEO stability across releases and content edits.

When should I use seo-drift?

When user says SEO drift, baseline, track changes, SEO regression, compare SEO, or deployment check.

Is seo-drift safe to install?

Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.