Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automate Google Search Console tasks via Rube MCP (Composio): query search analytics, list sites, inspect URLs, submit sitemaps, monitor search performance. Always search tools first for current schemas.
.claude/skills/composiohq-google-search-console-automation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | 109% | 0% |
| case-22 | ✓→✗ | ▼ Worse | 76% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 115% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 110% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 47% | 0% |
Query search analytics, inspect URLs, manage sitemaps, and monitor search performance using Google Search Console via Rube MCP (Composio).
Toolkit docs: composio.dev/toolkits/google_search_console
RUBE_MANAGE_CONNECTIONS with toolkit google_search_consoleRUBE_SEARCH_TOOLS first to get current tool schemasGet Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
RUBE_SEARCH_TOOLS respondsRUBE_MANAGE_CONNECTIONS with toolkit google_search_consoleUse GOOGLE_SEARCH_CONSOLE_LIST_SITES to retrieve all sites the authenticated user owns or has access to.
Tool: GOOGLE_SEARCH_CONSOLE_LIST_SITES
Parameters: (none required)
Returns: List of site entries with siteUrl and permissionLevelUse GOOGLE_SEARCH_CONSOLE_SEARCH_ANALYTICS_QUERY to get search performance data including clicks, impressions, CTR, and position.
Tool: GOOGLE_SEARCH_CONSOLE_SEARCH_ANALYTICS_QUERY
Parameters:
- site_url (required): Site URL (e.g., "https://www.example.com/" or "sc-domain:example.com")
- start_date (required): Start date in YYYY-MM-DD format
- end_date (required): End date in YYYY-MM-DD format
- dimensions: Group by ["query", "page", "country", "device", "date", "searchAppearance"]
- search_type: "web" (default), "image", "video", "news", "discover", "googleNews"
- dimension_filter_groups: Filters for dimensions (operator: equals, notEquals, contains, notContains, includingRegex, excludingRegex)
- row_limit: Max rows (1-25000, default 1000)
- start_row: Pagination offset (default 0)
- aggregation_type: "auto", "byPage", "byProperty", "byNewsShowcasePanel"
- data_state: "final" (default), "all", "hourly_all"Use GOOGLE_SEARCH_CONSOLE_INSPECT_URL to check the indexing status and issues for a specific URL.
Tool: GOOGLE_SEARCH_CONSOLE_INSPECT_URL
Parameters:
- inspection_url (required): Full URL to inspect (e.g., "https://www.example.com/page")
- site_url (required): Property URL (e.g., "https://www.example.com/")
- language_code: BCP-47 language (default: "en-US")Use GOOGLE_SEARCH_CONSOLE_LIST_SITEMAPS to retrieve all sitemaps submitted for a site.
Tool: GOOGLE_SEARCH_CONSOLE_LIST_SITEMAPS
Parameters:
- site_url (required): Site URL (e.g., "https://www.example.com/")
- sitemap_index: Specific sitemap index URL to list sitemaps fromUse GOOGLE_SEARCH_CONSOLE_SUBMIT_SITEMAP to register or resubmit a sitemap for indexing.
Tool: GOOGLE_SEARCH_CONSOLE_SUBMIT_SITEMAP
Parameters:
- site_url (required): Site URL or domain property (e.g., "sc-domain:example.com")
- feedpath (required): Full sitemap URL (e.g., "https://www.example.com/sitemap.xml")Use GOOGLE_SEARCH_CONSOLE_GET_SITEMAP to retrieve information about a specific submitted sitemap.
Tool: GOOGLE_SEARCH_CONSOLE_GET_SITEMAP
Parameters:
- site_url (required): Site URL
- feedpath (required): Sitemap URL to retrieve details forGOOGLE_SEARCH_CONSOLE_SEARCH_ANALYTICS_QUERY with dimensions: ["date"] over a date range to track daily search performance trends.GOOGLE_SEARCH_CONSOLE_SEARCH_ANALYTICS_QUERY with dimensions: ["query"] to find the most clicked search terms.dimensions: ["page"] to identify top-performing pages, then dimensions: ["query", "page"] to see which queries drive traffic to each page.GOOGLE_SEARCH_CONSOLE_INSPECT_URL to check the indexing status of important pages.GOOGLE_SEARCH_CONSOLE_LIST_SITEMAPS to verify submitted sitemaps, then GOOGLE_SEARCH_CONSOLE_SUBMIT_SITEMAP to submit new or updated ones.dimensions: ["country", "device"] to understand geographic and device-type distribution of search traffic.dimension_filter_groups with contains or includingRegex operators to focus on specific keyword groups.https://www.example.com/). Domain properties use the sc-domain: prefix (e.g., sc-domain:example.com). Using the wrong format will return empty results or errors.data_state: "all" includes fresher data that may still change. hourly_all only works for dates within the last 3 days.start_row with the row_limit.inspection_url must be a page under the site_url property. Cross-property inspections will fail.GOOGLE_SEARCH_CONSOLE_SUBMIT_SITEMAP requires the sitemap file to be publicly accessible at the specified URL and properly formatted as XML.date (which sorts by date ascending).| Action | Tool | Key Parameters | |--------|------|----------------| | List sites | GOOGLE_SEARCH_CONSOLE_LIST_SITES | (none) | | Search analytics | GOOGLE_SEARCH_CONSOLE_SEARCH_ANALYTICS_QUERY | site_url, start_date, end_date, dimensions | | Inspect URL | GOOGLE_SEARCH_CONSOLE_INSPECT_URL | inspection_url, site_url | | List sitemaps | GOOGLE_SEARCH_CONSOLE_LIST_SITEMAPS | site_url | | Submit sitemap | GOOGLE_SEARCH_CONSOLE_SUBMIT_SITEMAP | site_url, feedpath | | Get sitemap info | GOOGLE_SEARCH_CONSOLE_GET_SITEMAP | site_url, feedpath |
Powered by Composio
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,762 | 5,516 | -29% | 1 | 1 | 0% | 1,589 | 2,349 | +48% | 0 | 0 | — |
case-02 | fail→fail | 6,402 | 4,098 | -36% | 1 | 1 | 0% | 1,218 | 2,192 | +80% | 0 | 0 | — |
case-03 | fail→fail | 9,616 | 4,897 | -49% | 1 | 1 | 0% | 1,955 | 2,272 | +16% | 0 | 0 | — |
case-04 | pass→pass | 6,078 | 2,641 | -57% | 1 | 1 | 0% | 1,130 | 2,433 | +115% | 0 | 0 | — |
case-05 | pass→pass | 5,929 | 3,073 | -48% | 1 | 1 | 0% | 1,173 | 2,458 | +110% | 0 | 0 | — |
case-06 | pass→pass | 9,373 | 4,897 | -48% | 1 | 1 | 0% | 1,997 | 2,941 | +47% | 0 | 0 | — |
case-07 | pass→pass | 5,791 | 3,605 | -38% | 1 | 1 | 0% | 1,074 | 2,584 | +141% | 0 | 0 | — |
case-08 | pass→pass | 6,126 | 5,370 | -12% | 1 | 1 | 0% | 1,294 | 2,621 | +103% | 0 | 0 | — |
case-09 | pass→pass | 5,475 | 1,717 | -69% | 1 | 1 | 0% | 1,034 | 2,218 | +115% | 0 | 0 | — |
case-10 | fail→fail | 3,495 | 2,468 | -29% | 1 | 1 | 0% | 695 | 2,420 | +248% | 0 | 0 | — |
case-11 | pass→pass | 12,732 | 6,273 | -51% | 1 | 1 | 0% | 2,337 | 3,143 | +34% | 0 | 0 | — |
case-12 | pass→pass | 6,793 | 2,905 | -57% | 1 | 1 | 0% | 1,163 | 2,396 | +106% | 0 | 0 | — |
case-13 | fail→fail | 7,474 | 2,287 | -69% | 1 | 1 | 0% | 1,311 | 2,316 | +77% | 0 | 0 | — |
case-14 | pass→pass | 4,674 | 3,140 | -33% | 1 | 1 | 0% | 826 | 2,499 | +203% | 0 | 0 | — |
case-15 | pass→pass | 5,364 | 3,204 | -40% | 1 | 1 | 0% | 1,095 | 2,523 | +130% | 0 | 0 | — |
case-16 | fail→fail | 7,088 | 3,305 | -53% | 1 | 1 | 0% | 1,204 | 2,528 | +110% | 0 | 0 | — |
case-17 | fail→pass | 5,966 | 3,263 | -45% | 1 | 1 | 0% | 1,177 | 2,463 | +109% | 0 | 0 | — |
case-18 | pass→pass | 4,571 | 2,187 | -52% | 1 | 1 | 0% | 842 | 2,309 | +174% | 0 | 0 | — |
case-19 | fail→fail | 5,876 | 1,352 | -77% | 1 | 1 | 0% | 1,038 | 2,099 | +102% | 0 | 0 | — |
case-20 | pass→pass | 10,997 | 6,125 | -44% | 1 | 1 | 0% | 1,926 | 3,047 | +58% | 0 | 0 | — |
case-21 | pass→pass | 8,854 | 5,612 | -37% | 1 | 1 | 0% | 1,756 | 2,913 | +66% | 0 | 0 | — |
case-22 | pass→fail | 7,501 | 6,745 | -10% | 1 | 1 | 0% | 1,355 | 2,383 | +76% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 18 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 18 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.