I spend 30-45 minutes every morning on tasks that require zero thinking. Submitting new URLs to Google Search Console. Skimming competitor blogs for new posts. Checking whether my pages show up in AI Overviews. Pulling GA4 data to spot traffic drops.

Claude in Chrome turns all of that into scheduled shortcuts that run themselves. You save a prompt with a starting URL, set a schedule, and the extension handles the rest while you work on things that require your brain.

Below are the 6 shortcuts I run in production, with the exact prompts, starting URLs, and schedules. Copy them, swap in your own domains, and you have an SEO monitoring system running inside your browser.

New: CC for SEO is launching — pre-built Claude Code skills for technical audits, keyword clustering, and GSC/GA4 analysis. Join the waitlist.

What Claude in Chrome Does

Claude in Chrome is Anthropic’s browser extension. It reads pages, clicks buttons, fills forms, and navigates websites from a side panel. Three features matter for SEO:

Shortcuts save a prompt and starting URL as a reusable slash command. Type / and pick it from a list.

Scheduling runs any shortcut on a recurring cadence: daily, weekly, monthly. Claude executes at the set time and notifies you when finished.

Workflow recording lets you demonstrate a task while Claude watches, then saves it as a shortcut automatically.

The extension works with your existing browser sessions. If you’re logged into GSC, GA4, Semrush, or Ahrefs, Claude can interact with those dashboards. No credentials to configure separately.

The 6 Shortcuts

1. Auto-Submit New URLs to Google Search Console

Finds pages on your site that haven’t been submitted to GSC and submits them through URL Inspection.

Prompt:

Find all pages on https://www.yoursite.com/ that have not been submitted to Google Search Console and submit them. Ensure you are checking all locales. Start with English.

This catches new blog posts and programmatic URLs that sit undiscovered for days. Especially useful for sites with i18n where each locale generates a separate URL.

2. Weekly GSC Performance Snapshot

Pulls top queries, pages, and CTR data without exporting CSVs.

Prompt:

Extract the top 50 queries by clicks and top 30 pages by impressions for the last 7 days. Compare to the previous 7-day period. Flag any query that dropped more than 20% in clicks or any page that lost more than 30% impressions. Format as a table.

3. Index Coverage Error Monitor

GSC’s indexing report buries problems behind multiple clicks. This surfaces them daily.

Prompt:

Check the Pages indexing report. List all error types with their page counts. If any error type has more than 10 affected pages, list the first 5 example URLs. Flag any new error types that weren't present yesterday.

4. Competitor Blog Post Monitor

Track when competitors publish new content. Claude visits their blog, reads what’s new, and summarizes it.

Prompt:

Scan this blog page for any posts published in the last 7 days. For each new post, extract: title, URL, publish date, and a 2-sentence summary of the topic. If no new posts exist, say "No new posts."

Create one shortcut per competitor. Run 3-5 in parallel each morning for a daily competitive content briefing.

5. SERP Feature Tracker

Check whether your pages appear in featured snippets, People Also Ask, or AI Overviews for target keywords.

6. Google Business Profile Review Monitor

For local SEO: catch new reviews before your client sees them.

Prompt:

Check for new reviews posted in the last 24 hours. For each new review, extract: star rating, reviewer name, review text, and date. Flag any review with 1-2 stars as urgent. Summarize the overall sentiment of new reviews.

How to Set Up Your First Shortcut

Setup takes about two minutes per shortcut:

1. Open the Claude side panel in Chrome (click the extension icon or press the keyboard shortcut)

2. Run the workflow manually first. Type your prompt, let Claude navigate and complete the task, verify the results

3. Save as shortcut. Click “Convert to task” in the conversation header, or hover over your prompt and click the save icon

4. Set the Start from URL. Edit the shortcut and paste the URL where Claude should begin

5. Toggle scheduling on. Click the clock icon, pick frequency and time, choose your model

6. Test once. Let it run and check the output before trusting it on autopilot

You can also use workflow recording: click the record icon, demonstrate the task yourself while narrating what you’re doing, and Claude generates the shortcut from your actions.

Tips for Reliable Shortcuts

Be specific in prompts. “Check my rankings” is too vague. “Search Google for [keyword], note the organic position of yoursite.com, record whether an AI Overview appears” produces consistent results.

Add verification steps. Include “Process all items” or “Check all 10 keywords” in your prompt. Claude in Chrome can stop mid-task on long lists without explicit scope instructions.

Match model to task. Haiku 4.5 handles simple data extraction (review monitoring, blog scanning). Sonnet 4.5 or Opus 4.6 for multi-step workflows requiring reasoning (comparing data, identifying anomalies). Pro plans only get Haiku 4.5. Max or Team plans unlock the more capable models.

Output to a persistent location. Claude in Chrome has no cross-session memory. Have your shortcuts paste results into a Google Doc or Sheet so you build a historical record.

Start small. Get 3-5 shortcuts running reliably before scaling to 15. Debug one broken workflow before adding the next.

What Shortcuts Don’t Replace

Claude in Chrome operates through the browser UI. It’s slower than API-based tools. A scheduled shortcut checking 10 keywords takes minutes, not seconds. For high-volume rank tracking (500+ keywords), you still need Semrush, Ahrefs, or a dedicated SERP API.

The extension can’t access financial services, work across browser sessions, or remember previous runs. It’s a workflow automation layer on top of existing tools.

Where it fits: the 15-30 minute manual tasks that aren’t worth building an API integration for but too tedious to repeat every day. Submitting URLs to GSC. Skimming competitor blogs. Spot-checking SERP features. These are the tasks that fall through the cracks when you’re busy.

Claude in Chrome vs. Claude Code

Plan Requirements

Claude in Chrome is available on all paid plans (Pro, Max, Team, Enterprise). Pro plans run Haiku 4.5 only, which handles simple shortcuts fine. Max and Team plans give you Sonnet 4.5 and Opus 4.6 for complex multi-step workflows.

Chrome needs to be open for scheduled shortcuts to execute. If Chrome is closed or your computer is asleep at the scheduled time, the task won’t run.

I’m Vytas Dargis, founder of CC for SEO and AI for Marketing Ops. Subscribe for weekly breakdowns of SEO workflows automated with Claude Code.

I use Claude Code to produce 2-3 long-form articles per week across multiple sites. AI handles research, structure, source verification, and first drafts. I handle voice, data, and editorial judgment. Readers don’t flag the output as AI. Detection tools don’t either.

This is the full breakdown. The config file, the banned phrase list, the skills and agents that handle research, and the line I draw between what AI does and what stays human.

I’ll also show you two real articles this system produced, with the data to back up why it works.

Why All AI Content Sounds Like the Same Person

AI writing blends together because models learn from the internet, and the internet is now full of AI writing. Each new model trains on the last model’s output. The voice gets flatter with every generation.

You can probably spot it by now. These patterns show up in roughly every other AI-generated article:

You can’t fix this with a better prompt. A single instruction can’t override patterns learned from billions of words. You need rules that apply to every output, every time, without you remembering to paste them.

The Config File That Makes the Difference

Claude Code reads a CLAUDE.md file at the root of every project. Think of it as a permanent instruction manual. It’s not a prompt you paste into a chat. It’s a file the tool reads automatically, every time, on every task.

You write your content rules once. Claude follows them on every article after that.

Here’s what the content section of my production CLAUDE.md looks like:

## Banned Language

- Em-dashes
- Filler: just, very, actually, basically
- Corporate: leverage, robust, scalable, streamline, delve
- Hedging: "It's worth noting", "You may want to consider"
- AI cliche structures:
  - "No X. No Y. Just Z."
  - "It's not just about X. It's about Y."
  - "game-changer" / "supercharge"
  - "Enter: [thing]"
  - "And here's the kicker"
  - "X changed everything"
  - Arrow formatting for lists
  - "The best part?" / "Want access?"
  - "If you're serious about X, [CTA]"
  - "To your success" sign-offs
  - "Not because of X. But because of Y."

## Writing Style

- Lead with data, not opinions. Every claim needs a source.
- No filler intros ("In today's digital landscape..."). Start with the point.
- 2-3 sentences per paragraph maximum.
- No sentences over 30 words.
- Active voice by default.
- Target Flesch-Kincaid grade 8-10.

The trick is being specific, not vague. “Write in a natural tone” does nothing. “Never use the phrase ‘It’s worth noting’” is a rule Claude Code actually follows.

When you ban 20+ specific patterns, the model has to find other ways to say things. Those alternatives sound less like AI because they don’t match the patterns readers have learned to spot.

The Rule That Stops AI From Making Things Up

AI fabricates statistics. Not on purpose, but because models generate things that sound true even when they aren’t. “73% of marketers say...” with no study, no URL, no source. Confident nonsense.

One CLAUDE.md rule fixes most of this:

## Source Verification Protocol

- Every external claim requires a source with URL and date
- Citation format: "81% of SEOs prioritize AI (Source, Month Year)"
- If a claim cannot be verified:
  1. Remove the claim, OR
  2. Reframe: "Many SEOs report...", OR
  3. Mark [NEEDS VERIFICATION] for manual research
- Never guess. Never fabricate statistics.

Here’s the difference in practice:

Without the rule:

Studies show that 73% of content marketers are now using AI tools to accelerate their workflow, making it more important than ever to stand out.

With the rule:

52% of new online articles are AI-generated as of mid-2025 (Futurism, 2025). On YouTube, 21-33% of recommended content qualifies as AI slop, generating $117 million in annual ad revenue across 278 synthetic content channels (Search Engine Journal, 2025).

The first version sounds confident but says nothing verifiable. The second has paper trails. Readers trust it because they can check it. AI answer engines cite it for the same reason.

How an Article Actually Gets Made

Let me walk through the real process. Not a theoretical workflow. The steps I follow every time.

Step 1: Research With a Content Brief

I start by running a /content-brief skill. This analyzes the top 10 Google results for my target keyword. It pulls their heading structures, word counts, and topic coverage. Then it builds a brief: what to write, how to structure it, and what gaps exist in the content that already ranks.

claude /content-brief "instagram dm automation"

Behind the scenes, Claude Code launches a deep-web-researcher subagent. This agent runs multiple web searches in parallel, cross-references what it finds, and returns structured data with URLs and publication dates. It’s doing in 2 minutes what would take me 45 minutes of tab-switching.

Step 2: Check for Cannibalization

Before writing, I verify the target keyword isn’t already covered on my site. The /cannibalization skill checks Google Search Console data and flags conflicts.

claude /cannibalization --gsc-data ./gsc-export.csv

This step has saved me from writing articles that would have competed with my own pages. Sounds obvious, but it’s the kind of check most people skip because it takes time. With a skill, it takes 30 seconds.

Step 3: Draft With All Constraints Active

The /copywriting skill generates the draft. Because the CLAUDE.md file is always active, the draft automatically follows the banned language list, the citation protocol, the paragraph limits, and the readability targets.

The draft comes out structured like this:

• Every H2 section opens with a 50-70 word “citation block” written in factual, third-person tone. AI search engines love pulling these as source material.

• Every stat has a source in parentheses.

• Paragraphs are 2-3 sentences. No exceptions.

• No filler intros. Sections start with the point.

Step 4: Fact-Check With a Dedicated Agent

After the draft is ready, I launch a fact-checker subagent. It takes every claim in the article that references external data and independently verifies it. If it can’t find the source, it gives me three options: remove the claim, reframe it (”Many marketers report...”), or mark it for manual research.

This runs in the background while I start the human editorial pass.

Step 5: The Human Pass (This Part Can’t Be Skipped)

This is where the article stops being a good AI draft and becomes something worth publishing.

I read every paragraph. I add:

• My own data. Screenshots from Google Search Console, Ahrefs dashboards, or terminal outputs from real Claude Code sessions. Nobody else has my data.

• Opinions that require judgment. “Are these numbers good? Here’s what I think and why.” AI can provide data. It can’t evaluate data.

• Things that went wrong. What didn’t work. What surprised me. What I’d do differently. This is the part readers remember.

• Voice. The way I phrase things. Short. Direct. Sometimes blunt. The CLAUDE.md constrains AI’s bad habits, but voice comes from the human.

Step 6: SEO and Schema Checks

After the human pass, I run two more skills:

/schema-gen creates Article and FAQ schema (JSON-LD structured data). Every article gets this. It helps both Google and AI search engines understand what the page covers.

/seo-audit crawls the page and checks title tag length, meta description, heading hierarchy, canonical URLs, and structured data validation. It’s the final gate.

Step 7: Track AI Citations After Publishing

A week or two after publishing, I run /ai-visibility to check whether the article shows up in AI-generated answers across ChatGPT, Perplexity, Google AI Overviews, and Grok.

This step closes the loop. If the article isn’t getting cited, I can see what’s missing and adjust the content.

Two Real Articles This System Produced

Theory is nice. Results are better. Here are two articles made with this exact workflow.

Example 1: Instagram DM Automation Guide

Article: Instagram DM Automation: Setup in 10 Min

This is a comprehensive guide for CreatorFlow, an Instagram DM automation tool. It covers setup steps, pricing comparisons, tool breakdowns, and use cases.

What the workflow handled:

• /content-brief identified gaps in existing DM automation guides (most were outdated or focused on a single tool)

• The draft followed all CLAUDE.md constraints: no filler, sourced claims, short paragraphs, citation blocks under every H2

• /schema-gen added FAQ and Article schema

• Human pass added: real pricing data, tool-specific screenshots, the author’s take on which tool fits which use case

The CreatorFlow domain earned 224 ChatGPT citations across 61 pages within 90 days, and this article was one of the highest-performing pieces in the set.

Example 2: Content Strategy Case Study (With Real Numbers)

Article: How Claude Code Helped Us Get 1,000+ Waitlist Signups in 2 Months

This one shows the workflow’s results on a new domain (creatorflow.so). The numbers, for a brand-new site with zero backlinks:

The majority of waitlist signups came from AI search referrals, not traditional Google organic. ChatGPT and Perplexity cited the content, users asked follow-up questions about the tool, and those conversations converted to waitlist visits.

What made this work wasn’t the volume (though 40 articles in 12 weeks matters). It was the structure. Every article opened sections with citation-ready blocks. Every claim had a source. The CLAUDE.md rules prevented slop from creeping in, even at that publishing pace.

Without the workflow, that volume would have required either a team of writers or a pile of generic AI content nobody would cite. Claude Code let a solo founder produce structured, citation-ready articles at a pace that landed 224 ChatGPT mentions in 90 days on a domain nobody had heard of before.

What Stays Human (Non-Negotiable)

Some content should never be delegated, no matter how good the CLAUDE.md rules are:

Google calls this “Experience” in their E-E-A-T framework. It’s the hardest quality signal to fake because it requires proof that the author has done the thing they’re writing about.

The CreatorFlow case study is a good example. Anyone can write about content strategy. Only someone who built CreatorFlow can share its actual Ahrefs dashboard, GSC data, and waitlist numbers. That data is the article’s defensibility. No competitor can replicate it.

How to Start (25 Minutes)

If you want to try this, you need four things in your CLAUDE.md:

1. Banned language list (10 min). Copy the one from this article. Add or remove phrases to match your voice. 15-20 patterns minimum.

2. Source verification rule (5 min). The protocol I showed above. This single rule kills most hallucinated statistics.

3. Structural constraints (5 min). Max 2-3 sentences per paragraph. 30-word sentence cap. Active voice. Sections lead with facts.

4. Human-only boundaries (5 min). Write down what you always add yourself: your data, your opinions, your experience. This prevents you from gradually outsourcing the parts that make your content unique.

That’s a working setup. The banned list and source verification handle the 80% that matters most.

The Results So Far

Since putting this system into production:

• Brief-to-published time dropped from 6 hours to 90 minutes per article

• Every article carries 3-5 verified external sources with URLs

• 224 ChatGPT citations on a brand-new domain in 90 days

• The AI draft is good enough to publish as-is. The human pass adds value on top instead of fixing problems underneath

The system isn’t magic. Every article still gets a full human read. I still add data, commentary, and judgment by hand. The AI handles the parts that benefit from speed and consistency: structure, research scaffolding, source verification, schema markup. The human handles the parts that benefit from experience: voice, data, and the “does this pass the smell test” filter.

The internet doesn’t need more content. It needs more content that was worth writing. A well-configured CLAUDE.md is how you make AI help with that instead of adding to the noise.

I’m Vytas Dargis, founder of CC for SEO and AI for Marketing Ops. Subscribe for weekly breakdowns of SEO workflows automated with Claude Code.