skilld
All skills
agricidaniel avatar

/seo-google

@4460b8d
by Agrici.Danielagricidaniel/claude-seo18k stars
2,665

Google SEO APIs: Search Console (Search Analytics, URL Inspection, Sitemaps), PageSpeed Insights v5, CrUX field data with 25-week history, Indexing API v3, and GA4 organic traffic. Provides real Google field data for Core Web Vitals, indexation status, search performance, and organic traffic trends. Use when user says "search console", "GSC", "PageSpeed", "CrUX", "field data", "indexing API", "GA4 organic", "URL inspection", or "real CWV data".

Ask your Agent

Use this Skill: https://skilld.dev/gh/agricidaniel/claude-seo/seo-google

This session only. Nothing lands on disk.

referencesdma-consent-mode-v2.md

≈780 tokens on demand. Your agent reads this file only when SKILL.md points to it.

DMA + Consent Mode v2: click-through impact diagnostic

EU traffic flowing through Google Search has been subject to the Digital Markets Act since 2024-03-07. The DMA limits how Google can use behavioural data and forces consent-mode v2 compliance for GA4 + Ads in EU. The operational effect for SEO audits:

  • EU click-through-rate (CTR) data from Search Console may be noisier after the DMA enforcement date (an inference: Google publishes no measurement of this). Treat year-over-year CTR comparisons across that boundary with care.
  • GA4 organic-traffic reports for EU users show systematic under-reporting when consent-mode v2 is configured as "denied for ad_storage" (a common EEA setup defaults every consent type to denied until the user consents). Conversion modelling fills the gap, but the raw counts are lower than pre-2024.

What the seo-google skill should do

  1. When pulling GSC search analytics for an EU-targeted property, note: "EU CTR comparisons before/after 2024-03-07 are not apples-to-apples (DMA + consent-mode v2 took effect)."
  2. When pulling GA4 organic traffic, surface the consent-mode configuration if it is visible. If default consent denies ad_storage or analytics_storage for EEA users, note "EU traffic counts are conservative; conversion-modelled uplift may apply."
  3. Do not lecture the user on cookie consent UX: that's a legal team / engineering concern outside SEO scope. Just attach the diagnostic note.

Required GA4 / Consent Mode setup the audit should check for

  • Consent Mode v2 wired up (gtag('consent', 'default', {...}) including ad_user_data and ad_personalization, set before any tags fire; https://developers.google.com/tag-platform/security/guides/consent).
  • ads_data_redaction flag set on EU traffic.
  • Server-side tagging at consent transitions (recommended pattern; not legally required).

Softening cookieless-attribution warnings

Google abandoned third-party cookie deprecation in July 2024 and confirmed in April 2025 that Chrome will not ship a standalone cookie prompt. The "cookieless future" framing is no longer urgent.

For audits as of September 2026:

  • Do NOT recommend "switch to cookieless attribution" as a priority.
  • DO recommend "implement consent-mode v2 + server-side tagging" for EU compliance + signal-loss recovery.
  • Most Privacy Sandbox APIs (Topics, Protected Audience, Attribution Reporting, Shared Storage and Private Aggregation, Related Website Sets, IP Protection) were retired per Google's October 17, 2025 announcement. Do not recommend them. CHIPS, FedCM and Private State Tokens remain.

Primary sources

Last verified: 2026-09-23.

Source: SKILL.md on GitHub

Third-party checks

2 warnings2d4 checks · Risk MEDIUM
  • Gen Agent Trust Hub2d

    The skill provides a suite of tools for Google SEO analysis, including Search Console, GA4, and PageSpeed Insights. It is designed to work with user-provided Google Cloud credentials stored in local configuration files. A security concern is that the skill's documentation contains misleading "future" dates and speculative feature descriptions (ranging into 2026), which could lead to confusion about its provenance. Additionally, the skill's ability to process external data like YouTube comments and web content makes it susceptible to indirect prompt injection attacks, where malicious instructions hidden in that data could influence the agent's behavior.

  • Socket2d

    No alerts

  • Snyk2d

    Risk: MEDIUM · 1 issue

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 4460b8d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 3 days ago

Capability

user-invocable
true
argument-hint
[command] [url|property]
metadata
{
  "author": "AgriciDaniel",
  "version": "2.4.1",
  "category": "seo"
}

README badge

README badge for agricidaniel/claude-seo/seo-google