← ClaudeAtlas

buyer-lenslisted

Reviews a website, landing page, or product concept through the eyes of its real buyers and reports purchase intent. Builds attribute-conditioned buyer personas, runs a synthetic panel using the SSR method, maps workflow-coverage gaps and incumbent alternatives, and returns scored segments, verbatim objections, and prioritized fixes. Use whenever the user wants a landing page, website, pricing page, or product idea reviewed from the customer's perspective, asks "would people buy this", "validate my idea", "test this concept", "how will my target audience react", wants purchase-intent or pricing feedback, a synthetic panel, focus group, or market research on a startup or product concept, or asks you to act as their customers or buyers — even if they never mention personas, surveys, or purchase intent. NOT for signal inventory or instrumentation planning: if the user asks what buying or intent signals to track, collect, or instrument, use signal-lens instead.
ujjwalks/buyer-lens · ★ 1 · AI & Automation · score 64
Install: claude install-skill ujjwalks/buyer-lens
# buyer-lens Evaluate a product or page the way its buyers would, using the semantic similarity rating (SSR) method from Maier et al., arXiv:2510.08338. The paper's core findings drive every rule here: LLM panels reproduce human purchase-intent rankings only when respondents are conditioned on concrete buyer attributes and react in free text first — asking for a 1–5 rating directly collapses variance into uniform 4s and the results stop matching human panels. Work through the steps in order. Do not skip step 4 (the maps) or step 6 (the script) — they exist because models grade only what a page says and miscount distribution arithmetic. Wrong skill? This one simulates how buyers would *react* to something. If the request is instead about what to *observe* — which buying signals to track, what data each one needs, whether it can lawfully be collected — that is [signal-lens](https://github.com/ujjwalks/signal-lens). The same pricing page is an artifact here and an evidence surface there, so the verb decides: review/test/validate/"would they buy" is this skill; track/detect/collect/instrument is not. ## Step 0 — Intake If the request already names a website URL or describes the product, do not re-ask. Otherwise ask one question: what website or product should be reviewed (a URL is preferred — a live page shows what buyers actually see, including what's missing). Defaults, stated not asked: 2–4 buyer segments, 5 respondents per segment. ## Step 1 — Capture the concept Fetch