Google Search Console Tool logo

Google Search Console Tool

Community
garrettjsmith
google-search-console-tool

When the user wants to know what queries drive traffic to their site, which pages are indexed, click-through rates, organic search performance, or technical indexing issues. Trigger on "Search Console," "GSC," "what keywords am I getting traffic for," "what queries," "impressions," "click-through rate," "indexing issues," "is my page indexed," or "organic performance."

Overview

Publishergarrettjsmith
Repositorylocalseoskills
Skill namegoogle-search-console-tool
Stars
140
Forks
27
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by garrettjsmith on GitHub. Read the source before you install it.

Installation

Install the Google Search Console Tool AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/garrettjsmith/localseoskills/tree/main/skills/google-search-console-tool
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git /tmp/localseoskills
mkdir -p .claude/skills
cp -r /tmp/localseoskills/skills/google-search-console-tool .claude/skills/google-search-console-tool
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Search Console Tool in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Google Search Console Tool on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Google Search Console Tool is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Google Search Console Tool

GSC has official and community MCP servers available. When connected, use it for ground-truth organic search performance data — this is the only tool that shows ACTUAL clicks and impressions from Google.

When to Use GSC vs Other Tools

You NeedUse GSCUse Instead
Actual clicks and impressions from Google✅ Only source of truth—
What queries drive traffic to which pages✅ Only source of truth—
Click-through rate per query/page✅ Only source of truth—
Average position per query✅ Ground truthSemrush/Ahrefs estimates
Is a specific page indexed?✅—
Core Web Vitals per page✅—
Crawl errors and issues✅Screaming Frog (more detailed)
Keyword search volume❌ No volume dataSemrush, DataForSEO
Competitor keyword data❌ Your site onlySemrush, Ahrefs
Backlink data❌ Very limitedAhrefs
Local pack rankings❌ Organic onlyLocal Falcon
Citation data❌BrightLocal

Critical Distinction

GSC shows organic search performance only — not map pack, not LSA, not ads. A business can get zero clicks in GSC but rank #1 in the local pack (because map pack clicks don't show in GSC as organic clicks). Always pair GSC data with Local Falcon map pack data for complete visibility.

Core Workflows

Location Page Performance

When: User wants to know how their location pages perform in organic search.

What to pull:

  1. Filter pages by URL containing "/locations/" or your location page pattern
  2. Get clicks, impressions, CTR, average position per page
  3. Get queries driving traffic to each location page

How to interpret:

  • High impressions, low clicks (low CTR): Title tag or meta description doesn't compel clicks — rewrite them
  • High position (>20), some impressions: You're on page 2-3, close to breaking through — optimize content
  • Location page with zero impressions: Page may not be indexed, or keywords don't trigger it
  • Impressions for queries you don't have a page for: Content gap — create a page for that query

CTR benchmarks by position (approximate):

PositionExpected CTR
125-35%
212-18%
38-12%
4-55-8%
6-102-5%
11-200.5-2%

If CTR is below expected for the position, the title/meta needs improvement.

Local Keyword Discovery

When: User wants to find keywords they're already getting impressions for but not optimizing.

What to pull:

  1. All queries with impressions, filtered to last 3 months
  2. Sort by impressions descending
  3. Look for queries containing city names, "near me," service terms

What to look for:

  • Queries with high impressions but position 8+: Optimization targets — these have demand
  • Queries with "near me" variations: Confirm GBP is optimized for these services
  • Queries you rank for that you didn't expect: New keyword opportunities
  • Queries with city names you don't have a page for: Location page gaps

Index Coverage

When: User asks "is my page indexed?" or location pages aren't getting traffic.

What to check:

  1. URL Inspection for specific pages — are they indexed?
  2. Index coverage report — any errors affecting location pages?
  3. Sitemap processing — is the sitemap submitted and processed?

Common issues for local:

  • Location pages not in sitemap → add them
  • Location pages marked "Discovered – currently not indexed" → thin content, Google didn't find them valuable enough
  • Location pages blocked by robots.txt → fix robots.txt
  • Location pages with "Duplicate, submitted URL not selected as canonical" → canonicalization issue between similar location pages

Core Web Vitals

When: User's pages are slow or CWV failing.

What to check:

  1. CWV report for location pages specifically
  2. Which pages fail LCP, FID/INP, CLS
  3. Mobile vs desktop performance

For local: Mobile CWV matters most — local searches are predominantly mobile. If mobile CWV fails, fix it before other optimization.

Content Gap Identification

When: Looking for new content opportunities from actual search data.

What to pull:

  1. Queries where you have impressions but no dedicated page
  2. Queries with high impressions but position 15+
  3. Compare queries to your existing page structure

Example: GSC shows 500 impressions/month for "emergency plumber Orchard Park" but you don't have a page specifically about emergency plumbing in Orchard Park → create one.

Key Metrics and What They Mean

MetricWhat It IsLocal SEO Context
ClicksActual clicks from Google to your siteThe number that matters — this is real traffic
ImpressionsTimes your page appeared in search resultsShows demand even if you're not getting clicks
CTRClicks ÷ ImpressionsLow CTR = title/meta issue. Compare to position benchmarks
Average PositionAverage ranking position for a queryRemember: this is organic only, not map pack

What to Do Next

What You FoundNext ActionSkill
Location pages with low CTRRewrite title tags and meta descriptionslocal-landing-pages
Queries without dedicated pagesCreate pages targeting those querieslocal-landing-pages
Location pages not indexedFix technical issues (thin content, canonical, sitemap)local-seo-audit, screaming-frog-tool
CWV failing on mobileFix page speed issueslocal-seo-audit
Good organic performance, want to see map pack tooRun Local Falcon scanslocal-falcon-tool
Competitor analysis neededGSC is your-site only — use Semrush for competitor datasemrush-tool
Need this in a client reportInclude GSC data in performance reportslocal-reporting

Default next step: GSC is the truth layer. Start every performance analysis with GSC data, then supplement with other tools. If GSC shows no impressions for a keyword, either the page doesn't exist, isn't indexed, or doesn't target the keyword properly.

Frequently asked questions

What does the Google Search Console Tool AI skill do?

When the user wants to know what queries drive traffic to their site, which pages are indexed, click-through rates, organic search performance, or technical indexing issues. Trigger on "Search Console," "GSC," "what keywords am I getting traffic for," "what queries," "impressions," "click-through rate," "indexing issues," "is my page indexed," or "organic performance."

Why use Google Search Console Tool on TypingMind?

Because you install it once and use it with any model. Google Search Console Tool is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Google Search Console Tool in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/garrettjsmith/localseoskills/tree/main/skills/google-search-console-tool. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Google Search Console Tool?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Google Search Console Tool?

As many as you like. As long as a model supports skills, you can use Google Search Console Tool with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Google Search Console Tool AI skill free?

Yes. It is published on GitHub by garrettjsmith under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇