indranilbanerjee/digital-marketing-pro/gsc-ai-performance

/digital-marketing-pro:gsc-ai-performance

Script location. If your host does not set ${CLAUDE_PLUGIN_ROOT}, the scripts are in this plugin's scripts/ folder, next to skills/. Run them with Python 3.10 or newer: python, or python3 where python is not found (macOS, many Linux systems).

Purpose

Google rolled out a new GSC AI Performance Report on 3 June 2026 (Search Engine Land announcement) covering both AI Overviews and AI Mode in a single combined surface. This skill helps you (a) baseline a brand's visibility in the new report, (b) understand the metric trade-offs, and (c) decide whether to use the new in-SC opt-out toggle.

What is genuinely new (3 June 2026)

Critical interpretation guidance: The report shows when your pages were SHOWN in AI Overviews / AI Mode, not when users clicked through to them.

Because click data is absent, all downstream attribution to AI traffic must come from your analytics, and GA4 has a blind spot for exactly this surface. Its AI Assistant channel excludes Google's AI Overviews and AI Mode; GA4 counts those visits as Organic Search (see the map below and /digital-marketing-pro:analytics-insights).

Honest measurement map — what exists and what does not (checked 2026-10-04)

State these limits in every deliverable. A blank cell is not a zero; it is a metric no first-party tool publishes.

Google's AI optimization guide points to this report as the way to measure generative AI visibility. It also warns that "No third-party tool has access to our internal ranking or AI systems."

When to use this skill

• Setting baseline AI visibility for a new brand (first 30-day capture of AI Overview + AI Mode impressions)
• Comparing brand AI visibility against aeo-audit synthetic results — the GSC report shows ACTUAL impressions vs aeo-audit's probe queries
• Deciding whether to use the Search generative AI control (Settings → Search generative AI) for a brand (regulated industry, brand-safety concern, or paywall/login content)
• Quarterly business review evidence — "AI search impressions grew X%" using authoritative Google data

Brand context (auto-applied)

1. Read ~/.claude-marketing/brands/_active-brand.json for the active slug, then load ~/.claude-marketing/brands/{slug}/profile.json
2. If no brand exists: ask "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults
3. Apply industry-specific guidance from skills/context-engine/industry-profiles.md (YMYL industries may want to exclude the site with the Search generative AI control until the E-E-A-T audit is clean)
4. Reference skills/context-engine/compliance-rules.md for jurisdiction-specific rules (EU markets — see skills/context-engine/eu-code-of-practice.md for Article 50 transparency context)

Numbered output convention

All outputs go to ${CLAUDE_PLUGIN_DATA}/{brand}/seo/gsc-ai-performance/{YYYY-MM-DD}/:

00-input.md                  brand domain, GSC access status, UK-cohort flag, date range
01-access-check.md           verification result; if no access, instructions for adding the user
02-export.csv                raw CSV export from GSC (preserved for reproducibility)
03-script-output.json        gsc-ai-performance.py parsed output (impressions, pages, countries, devices)
04-reconciliation.md         vs aeo-audit synthetic probe results — gap analysis
05-opt-out-decision.md       y/n on the Search generative AI control, with rationale
06-quality-scorecard.md      the gates below
PLAN.md                      single-page summary with tracking cadence

Quality scorecard

If the property still doesn't see the report after the worldwide rollout (31 Aug 2026), the gate framework still applies, but export_completeness will be fail. Record the reason; that is a finding, not a regression.

Chain handoffs

• Upstream: /digital-marketing-pro:brand-setup for property verification
• Downstream:
• /digital-marketing-pro:aeo-geo — optimization based on what's surfacing (or not)
• /digital-marketing-pro:seo-drift — month-over-month tracking using the exported CSVs
• /digital-marketing-pro:analytics-insights — GA4 AI Assistant channel attribution closes the click-side gap

Process