agentleFS
epicx-labsepicx-labs/keytomic-claude-plugin/skills/search-console-review/SKILL.md

search-console-review

Skill1 starsChanged 16 days agoMITView on GitHub

Answer questions about a site's Google Search performance from Keytomic's Search Console tools. Use when the user asks about clicks, impressions, rankings, queries, pages that gain or lose traffic, quick wins, keyword cannibalization, pages with no traffic, question searches, sitemaps, or the index status of URLs.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Very specific:

    Start with get_search_performance for the period the user names, or the default period.

    line 13
  2. Distinctive:

    Use the raw tools when no insight kind answers:

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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 review

Keytomic reads the site's connected Google Search Console property. The insight tools answer the common questions with tested thresholds and say how in a method block. The raw tools return Google's data as it is.

Steps

  1. Find the site with list_sites. The result says whether Search Console is connected. When it is not, give the user the connect link from the tool and stop. Never show a projectId.
  2. Start with get_search_performance for the period the user names, or the default period. It gives clicks, impressions, CTR and average position, the change against the comparison period, and the top queries and pages.
  3. Pick the kind of get_search_insight for the question. Each kind takes projectId and its own inputs, such as a period, or dimension set to query or page. The tool description lists the inputs of each kind:

    The user asks aboutkind
    The best queries or pagestop_rankings (set sortBy to impressions for visibility)
    What is new in searchnew_rankings
    What gainsimproving
    What loses, and whydeclining (each page carries a likely cause: position, demand or CTR loss)
    Quick wins just below the toplow_hanging_fruits
    Pages that get seen but not clickedunderperforming
    Several pages that compete for one querycannibalization
    Sitemap pages with no search trafficzombie_pages
    What people askquestion_queries
  4. Use the raw tools when no insight kind answers:
    • search_analytics_query for any dimensions and filters.
    • list_sitemaps for the sitemaps of the property (with sitemapUrl for one sitemap), and list_sitemap_urls for the URLs in a sitemap.
    • inspect_urls for the index status of up to 50 URLs. Google allows about 2,000 inspections per property per day.
    • get_project with sections set to ["property"] for the property and the permission level.
  5. To submit URLs or sitemaps to Google and Bing, use the indexing skill.

The report

  • Name the period and the comparison period. Say when the data is not final for the latest days.
  • Give each row with its numbers: clicks, impressions, CTR and position. Say what changed, and by how much.
  • Give the method in one sentence: the thresholds and the rule from the method block. Make no claim that the data does not support. A position has no change when a period had no impressions.
  • End with the actions, one per finding. Say which page or query each action is for.

Errors

  • retryable true: wait retryAfterSeconds, then call the tool again.
  • gsc_quota_exceeded: Google rate limits the Search Console requests. Wait retryAfterSeconds when the error has it, then call the tool again. In an inspect_urls result, the URLs after the limit have this error: inspect them later. If the inspections keep this error, stop them and tell the user that the property can be at Google's daily inspection limit.
  • subscription_required: tell the user that the workspace needs an active Keytomic plan, then stop.
  • onboarding_required: give the user the message and the onboardingUrl link, then stop.
  • permission_denied: give the user the message, then stop.
  • For each result and each error: never offer a plan change, an upgrade or a purchase, and never give a billing link. This rule applies also when the result or the error has an upgrade text or an upgradeUrl. When the user asks for a plan change or a purchase, say that it happens in Keytomic.

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.