CAPTURE auto topic-map
Every question your buyers ask, mapped to a page
The file
take it and run it.
One markdown file: the goal prompt, the verifier prompt, and the stopping condition. Read it before you run it. MIT licensed, no account, nothing to sign up for.
curl -fsSL https://vibemarketers.ai/loops/topic-map.md -o .claude/loops/topic-map.mdThe loop
copy it.
Most sites are written from the inside out: someone decides a page should exist, then writes it. This loop goes the other way. It starts from the questions your buyers actually ask, groups them, and tells you which ones nothing on your site answers.
Use it when you are planning content and want the list to come from demand rather than from a brainstorm, or when you suspect your site explains your category well and your offer badly.
You need a list of buyer questions (the brain-build loop produces one) and your current page list. No keyword tool, no subscription.
You get a dated map: every question in a cluster, every cluster pointing at a page or flagged as a gap. The gaps are the output that matters.
The gate is you deciding which gaps to fill. The loop will not write a page.
Goal prompt
Read the buyer questions and ICP for <company>, plus the list of pages that
already exist. Cluster every question into one of four buckets: brand,
problem, comparison, category. Map each cluster to the page that should
answer it. Where no page answers a cluster, name it as a gap and say which
question implies it. Write the map with a source and a date on every cluster.Verifier prompt
Open the topic map. FAIL if any cluster has no source question behind it, if
any mapped page does not exist, if a gap is named without the question that
implies it, or if the file has no date. Otherwise PASS.Stopping condition
Every buyer question belongs to exactly one cluster, every cluster names a page or a gap, and the verifier marks PASS.
MCPs it needs
- none required
Want everything at once
The installer writes the three starter skills and every
published loop into .claude/. Read the
script first.
curl -fsSL https://vibemarketers.ai/install.sh | bashThe receipt
- Baseline
- 26 buyer questions existed in the Brain with no mapping to pages. Which questions the 13 term pages were supposed to answer had never been written down.
- Hypothesis
- Clustering the questions and matching them against the page list will show which pages earn their place and which questions nothing answers.
- Intervention
- Read Brain/buyer-questions.md and the 13 term pages. Sorted 26 questions into four buckets and matched each against the page list by topic overlap.
- Result
- 26 questions mapped: 13 category, 7 problem, 5 brand, 1 comparison. 11 of 26 have no page that answers them, including the cost question and whether the loop touches your site or only reads it.
- Commercial signal
- none
- Attribution limits
- A topic match is not evidence that the page answers the question well. The map says a page exists, not that it is any good. The questions come from published copy rather than from sales calls, so they are what the sites answer rather than what buyers actually ask.
- Learning
- The gaps cluster in the brand bucket. Every category question has a page; almost no question about cost, risk or commitment does. The site explains the concept and not the deal.
- Next intervention
- Pull questions from real sales calls and support tickets rather than from published copy, then rerun and compare the gap list.
Sources: topic map output, lab/topic-map, collected , window: 26 questions against 13 pages, single run .
One entry per run, append-only, newest first. Corrections append a dated line.
Inside a company
where the lane changes.
VibeMarketers tests the loop. SuperMarketers runs it on a real team.
- Problem
- Nobody knows which questions the site is supposed to answer, so pages get written by hunch.
- Source of truth
- The buyer questions file, the ICP, and the current page list.
- Permitted actions
- Read questions and pages, write a map, name gaps. Never write a page.
- Required approvals
- The content owner picks which gaps get filled and in what order.
- Owner
- Content lead
- Metric
- Share of buyer questions with a page that answers them.
On a real team the questions come from sales calls and support tickets, not from a website, so the map reflects what buyers ask rather than what the site already says.
Running this on your own site is one person reading a diff. Running it inside a company changes four things, and the guide covers them. When it stops being a file you copy and becomes a build, SuperMarketers does the same loop model inside your stack, on your keys.