agentleFS
CrakSEOCrakSEO/crakseo-search-console-mcp/skills/search-console/SKILL.md

search-console

Skill0 starsChanged 16 days agoMITView on GitHub

Report on the user's own Google Search Console (GSC) and Bing Webmaster Tools data, such as search analytics, keywords and search rankings, with CrakSEO's free Search Console MCP. Use when the user asks which queries or pages bring clicks, why a page is not indexed in Google, to list or resubmit sitemaps, or for Bing traffic, crawl issues and URL submission quota.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every tool on this server is free.

    line 14
  2. Very specific:

    Call list_search_console_properties first.

    line 18
  3. Distinctive:

    Use the exact property names it returns in the other tools.

    line 19
  4. Distinctive:

    Never promise that a page will be indexed or ranked.

    line 27
  5. Distinctive:

    Do not ask for or store passwords or API keys in chat.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Search Console and Bing Webmaster Tools

When to use

  • "Which Google search queries bring clicks to my website?"
  • "Why is my page not indexed in Google?"
  • "Check Bing traffic, crawl issues and my sitemap."

Every tool on this server is free. It only reads sites the user has verified and connected.

Steps

  1. Call list_search_console_properties first. If Google or Bing is not connected, give the user the links in its connect field and stop until they connect.
  2. Use the exact property names it returns in the other tools.
  3. Clicks, impressions, CTR and position: get_search_console_performance. Start with the last 28 days unless the user asks for another range.
  4. Indexing questions about one page: inspect_url_in_google. Explain the coverage state it returns, such as "Crawled - currently not indexed", and say what the user can change.
  5. Sitemaps: list_sitemaps reads; submit_sitemap writes. Ask the user to confirm before calling submit_sitemap.
  6. Bing: get_bing_webmaster_stats, get_bing_crawl_issues, get_bing_url_submission_quota.

Rules

  • Never promise that a page will be indexed or ranked. Google decides.
  • Report numbers as Search Console or Bing returns them; they are sampled and delayed by the provider.
  • Do not ask for or store passwords or API keys in chat. Authentication happens through the client's OAuth sign-in.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.