Skip to content
Product · Playbook

A pile of feedback, grouped and ranked by how many customers said it.

A pass over tickets, reviews, or comments that groups them into ranked themes, counting customers and not comments.

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
100 Playbooks in the catalogDelivered as Claude Skill + plain .mdReviewed Oct 22, 2026Instruction-only · verifiable

Raw feedback favors the loudest and the newest comment. One furious review feels like a trend, and one customer writing three emails looks like three customers.

Feedback Themes tags each comment with the job and the obstacle, rewrites requests as problems where the comment supports it, and clusters them into five to eight themes. It ranks by distinct customers, pulls a verbatim quote for each, and states the bias of the source.

What you get

What it produces.

  • →A ranked list of themes with distinct-customer counts
  • →Requests rewritten as underlying problems where supported
  • →One verbatim quote per theme
  • →A note on source bias and what the data cannot tell you
Who it's for
  • ✦Product managers with feedback spread across tools
  • ✦Support leads who need to report patterns upward
  • ✦Founders reading reviews and tickets by hand
What's included
  • →feedback-themes.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →feedback-themes-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
  • →A README inside the zip with install steps for Claude, ChatGPT, and Gemini
Delivery
Emailed within 60 seconds of payment
Compatibility
Claude, ChatGPT, Gemini, any LLM
License
One-time purchase, yours to keep
Sample output

What it does with a real question.

The brief

I'm the product manager for a scheduling app, and I just exported 412 NPS comments from the Q3 survey (July 1 through September 30) into a CSV, plus 138 app store reviews from the same period. Can you group everything into ranked themes with counts and a few representative quotes each? Our support team lead wants the top five themes by Friday.

Count customers, not comments. With 412 NPS comments and 138 reviews, you have roughly 550 pieces of feedback, but the number that matters is distinct customers per theme. Heavy reviewers who also answered the survey will inflate whatever they care about, so dedupe on account or email before you rank anything. For the reviews, where you can't match people, count one voice per review and say so.

My position: don't merge the two sources into a single ranked list. NPS comments come from a prompted sample, including quiet passives, while reviews come from people motivated enough to post publicly, so they skew toward complaints. Rank themes within each source, then put them side by side. A theme that shows up high in both, say calendar sync failures or double bookings, is your real top-five material. A theme that only dominates the reviews is probably loud rather than widespread, and Friday's list should say that.

Tag each comment with the job the person was doing and what got in the way, and split comments that raise two issues. Rewrite feature asks as problems only where the comment supports it. "Add recurring events" stays a request unless the customer says why.

Next move: run the first pass on the NPS file alone, cluster into five to eight themes, and pull one verbatim quote per theme. Then check the top theme for any single account driving it before it goes to your support lead as number one.

The full Playbook runs the whole procedure and writes the complete deliverable, not this excerpt.

Written by claude-sonnet-5-5 with this Playbook loaded, 2026-10-11. Checked automatically for length and for copied framework text.

One-time purchase
$12.99
Yours to keep
No subscription · free updates within v1.x

Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable

Questions

Before you buy.

How is this different from just asking Claude directly?

Asked cold, Claude produces neat themes and attaches rough percentages it cannot check. This counts distinct customers, collapses repeat comments, separates requests from problems, and says what the sample cannot show.

How is this different from a Tool?

Playbooks are systematically produced to a fixed template and priced accordingly ($12.99). Tools are hand-built, one at a time, and go deeper ($39 to $199). A Playbook gives you a reliable method for routine work; a Tool is for when the judgment matters more than the format.

Will this work with ChatGPT, Gemini, and other LLMs?

Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.

Can I share this with my team?

It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Playbook itself in the hands of a whole team, email hello@authority.md about team licensing.

What if it doesn't work for me?

If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.

More Product Playbooks

Other Playbooks.