Critique the page against the visitor it actually got, not an imagined ideal one.
The tool that diagnoses your landing page against your actual traffic source and the specific question that visitor brought with them, instead of a generic best-practices checklist.
Most landing page critique is genre-blind: it applies the same checklist regardless of who's actually visiting or why. A cold-ad click and a warm newsletter click carry completely different context, and a page that serves one well can fail the other.
This tool ties the critique to your actual traffic source, maps the page against the questions that specific visitor is really asking, and names the one change most likely to move conversion for that channel.
Same page, tied to the traffic that actually hits it.
Same URL, same visitor, run two ways.
A B2B SaaS founder runs cold LinkedIn ads to a landing page converting at 1.2%, well below their 3-4% target.
You ask Claude to review the landing page. You get a solid generic checklist: clearer headline, add social proof, strengthen the call to action.
All reasonable, and none of it explains why a cold, skeptical LinkedIn visitor with low problem-awareness bounces off a headline that reads like it was written for someone who already knows they need this.
It maps the page against what a cold visitor is actually asking, in order:
- →The headline answers "what is this" with category language, not the specific problem
- →A pricing table appears before "is this for someone like me" gets answered at all
- →The demo CTA asks for calendar time before any trust has been built
The finished teardown names the single highest-leverage change, not ten fixes, given everything found: rewrite the headline around the specific pain, and replace the immediate demo ask with a lower-commitment first step.
The cold version gave you a generic checklist. This told you why this specific visitor bounces.
- ✦Founders with a known traffic source and a disappointing conversion rate
- ✦Marketers launching a new page who want a critique before it goes live
- ✦Anyone running one page across multiple channels with mixed results
- →landing-page-teardown.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →landing-page-teardown-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, Gemini, and the API
What it does with a real question.
Here is the landing page for our scheduling tool for physiotherapy clinics. The headline reads 'Work smarter, not harder', followed by a hero image of a smiling team, six feature icons, a pricing table, and a demo button at the bottom. Traffic comes mainly from Google searches for 'physio clinic booking software'. Conversion is 1.1%.
The headline is the main problem. Someone who typed "physio clinic booking software" into Google is a high-intent visitor who already knows the problem and is comparing options. They are asking one thing: is this built for a physio clinic like mine? "Work smarter, not harder" answers nothing. It could sit atop a payroll tool or a gym app, and the smiling-team hero image reinforces the vagueness. Within five seconds, that visitor cannot tell what you sell or who it's for, so they go back to the results page and click a competitor whose headline says "physio" and "booking."
The six feature icons likely compound this. Search traffic wants proof of fit: recurring treatment-plan bookings, no-show reminders, insurance or ACC billing, multi-practitioner calendars. Generic icons ("Easy," "Secure," "Flexible") don't answer the doubt this visitor actually has.
The page also asks for a demo only at the very bottom, after a pricing table. That is not the worst order for warm search traffic, but a demo is a real calendar commitment, and you haven't yet shown a single physio-specific proof point to justify it.
Next move: rewrite the headline to mirror the search itself, something like "Booking software built for physio clinics," with a subheadline naming one concrete outcome, such as fewer no-shows or full diaries without front-desk phone tag. Put that change live first. Then test a lower-commitment option, like a two-minute product tour, beside the demo button.
The full Tool runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Tool loaded, 2026-10-11. Checked automatically for length and for copied framework text.
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
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude applies a generic best-practices checklist, clearer headline, more proof, stronger CTA, regardless of who's actually visiting. This ties the critique to your specific traffic source, maps the page against that visitor's actual question sequence, and names the one change most likely to move conversion for that channel specifically.
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 Tool 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.
Landing Page Teardown is a conversion-diagnosis tool. Not a guarantee of a specific conversion rate, which depends on offer, price, and market fit as much as page structure.