Big one this week: Anthropic just shipped “Record a Skill” inside Claude Cowork, a feature that lets Pro, Max, and Team users screen-record themselves doing a task once, then has Claude analyze that recording and turn it into a reusable, rerunnable skill.

If you’ve ever thought, “There has to be a faster way to do this every week,” this is the fastest path yet from tedious to automated. And for solo operators, it hands you a superpower that used to require a developer.

Here’s what else is packed into this edition…

Skills to Pay the Bills: Build a Customer Insight Extractor prompt that turns your reviews, DMs, support tickets, and sales call notes into a priority list of exactly what to fix, what to say, and what to sell next.

Top AI News: The top stories of the week you need to know about, in a snackable format.

Let’s get to work.

You already have the answers.

They are buried in your reviews, your DMs, your support tickets, your sales call notes, and that one Slack channel where customers occasionally rant.

The problem?

Nobody has time to read all of it, spot the patterns, and turn it into a plan.

This week’s prompt does that in one pass.

Paste it into ChatGPT, Claude, Perplexity, Gemini, or your AI tool of choice. Then dump your customer feedback into it.

You’ll get back a prioritized list of:

• what is costing you sales
• what your best customers actually love
• what language you should steal for marketing
• what gaps you need to fix
• what to change this week

Customer feedback is one of the most valuable assets in your business.

AI just makes it easier to actually use it.

You are the Customer Insight Extractor, a sharp customer research partner for small business owners who need to turn a messy pile of feedback into a clear action list.

Your job is to read whatever raw customer feedback I give you—reviews, DMs, support tickets, sales call notes, survey responses, forum posts, or chat logs—and pull out the patterns that actually change what I do next.

Work like a smart consultant, not a survey robot.

Push past surface-level themes.

Flag things that contradict each other.

Point out what my competitors probably do better based on what customers say they miss.

First, orient yourself.

Confirm:

• what business I run
• who my target customer is
• what I would love to learn from this feedback

If I am unsure, propose three angles I could analyze for.

Then ask me to paste the raw feedback.

Accept any format:

• a big block of text
• spreadsheet rows
• a screenshot summary
• reviews
• DMs
• support tickets
• survey responses
• sales call notes
• chat logs
• a mix of everything

Group findings into four categories:

1. Pain Points
What frustrates customers.

2. Delight Points
What wins customers over.

3. Language Gold
Exact phrases I should steal for marketing.

4. Gaps
What customers wish existed.

For each item, tell me:

• how often it showed up
• how emotionally charged it was
• whether it is likely to affect a purchase decision

Then give me a Top 3 To Fix This Week list, ranked by revenue impact versus effort, with a suggested first step for each.

Close with three Testable Messaging Ideas using the customer’s own words, ready to try in an ad, email subject line, or landing page headline.

Do not invent themes that are not in the feedback.

If the sample is too small to say something confidently, say so.

Do not summarize into blandness.

I want the sharp version… the one that would sting if a customer said it to my face.

Assume I am not a market researcher.

Explain terms and reasoning in plain language.

Section 1: Snapshot
Give me 3 bullet takeaways in one sentence each.

Section 2: The Four Buckets
Organize findings into Pain Points, Delight Points, Language Gold, and Gaps.

Section 3: Top 3 To Fix This Week
Rank the top fixes by revenue impact versus effort.

Section 4: Three Testable Messaging Ideas
Give me three customer-language ideas I can test in an ad, email subject line, or landing page headline.

To start, ask me for my business type, ideal customer, and one thing I am hoping this feedback will confirm or contradict.

Then ask one clarifying question at the end of your first reply.

Open ChatGPT, Claude, Perplexity, Gemini, or your preferred AI tool.

Copy the full prompt above.

Gather customer feedback from places like:

• Google reviews
• Facebook comments
• Instagram DMs
• support tickets
• sales call notes
• survey responses
• chatbot logs
• email replies
• customer service conversations
• Slack or community posts

Paste the prompt into your AI tool.

Then paste in the raw feedback.

Do not worry if it is messy.

Messy is fine.

The goal is not to create a perfect research report. The goal is to find the patterns that help you make better decisions this week.

Look closely at:

• repeated complaints
• repeated compliments
• exact customer phrases
• missing features or services
• reasons people hesitate to buy
• things people love but you are not marketing enough

Then pick one insight and act on it.

Fix the broken step.
Rewrite the unclear headline.
Add the missing FAQ.
Train the team on the recurring issue.
Turn the best customer phrase into your next ad.

Rerun this every 30 days with the newest batch of feedback.

Over time, you will spot what is shifting.

You will catch problems months before they show up in your sales numbers.

And you will stop guessing what customers want because they are already telling you.

You just needed a faster way to listen.

AI is moving from experiment… to essential.

Every major industry is integrating it.
Every major company is investing in it.

By late 2025, AI was already an $800B market — growing at a pace that could push it well beyond $1 trillion in the years ahead.

Cloud infrastructure is scaling fast.
AI-enabled devices are multiplying.
Automation is becoming standard.

But here’s the real question…

When trillions flow into this transformation — which stocks stand to benefit most?

Our new report reveals 10 AI stocks positioned across the backbone of this shift — from the companies powering the infrastructure… to those embedding intelligence into everyday systems.

If you want exposure to one of the defining growth trends of this decade, start here.

Download the Report Now

Anthropic announced that users on paid plans can now teach Claude Cowork a skill by recording a walkthrough of a task. Claude then analyzes the recording and turns it into a saved workflow it can rerun later. The “Record a Skill” option lives inside the Claude desktop app, alongside tools like adding files, browsing skills, connectors, and plugins. For a solo owner, this removes one of the biggest barriers to automation: writing detailed instructions. Now the demo is the instruction.

In other news…

Anthropic upgraded Claude’s voice mode so it can handle more useful work scenarios. Voice mode can now connect with apps like Gmail, Google Calendar, Google Docs, and Slack, making it more practical for scheduling, summarizing, drafting, and planning. Instead of just chatting, users can ask Claude to help turn conversations into actual work outputs. Worth testing before your next walk, commute, or meeting prep session.

Opus 5 has the same pricing as the previous generation: 5 bucks per million input tokens and 25 dollars per million output tokens. That is still expensive compared with models from Google Gemini and xAI’s Grok, but Anthropic is clearly trying to balance performance, safety, and efficiency as AI costs become a bigger issue. For small businesses, this is a reminder that choosing an AI model is not just about picking the smartest one. It is about matching the tool to the task, so you do not use a premium model for work a cheaper model can handle just fine.

Our next Clone Camp is taking place tomorrow.

If you’ve ever felt like you needed a clone of yourself, check out how I created mine.

Until next week,