gsc-seo-optimizer
GSC SEO Optimizer
Turn the user's own search evidence into a small, justified optimization batch. Default to read-only diagnosis. Execute changes only within the user's explicit authorization; existing approval for a concrete batch remains valid. An analysis request never authorizes publishing or spending.
Establish scope and data route
Confirm the exact GSC property (domain property or URL prefix), target market, Web/other search type, and requested period. Verify the property returned by a connector matches the requested site before using any numbers. Do not choose the first accessible property. Infer from the user's site and supplied context when unambiguous; ask if multiple properties or markets remain plausible.
For ranking analysis use the user's target market, not a universal US default. Global performance totals may be useful separately; label them and never mix scopes in comparisons. If no market can be established, label aggregate findings and defer market-specific ranking claims.
Use the least-friction route already available:
- Supplied exports: CSV or ZIP can be analyzed without credentials. Read references/data-access.md for the bundled local importer and export requirements.
- Existing Google API access: prefer it for reproducible filtering and comparison. The same reference documents the bundled read-only fetcher, authentication, and URL Inspection.
- Connected tools: inspect their actual capabilities and verify property, scope, freshness, authorization and any cost before use.
- Available browser: use the user's available authorized browser integration for UI-only evidence or missing API access. On login, account selection, 2FA, or permission screens, let the user complete the interaction. Never extract cookies, browser profile data, or passwords. If browser access is unavailable, request exports and continue with available evidence rather than blocking all analysis.
Do not install packages/connectors or start OAuth unless needed and within the user's request. The CSV importer uses Python's standard library. API dependencies are optional and separate.