Hire an AI landing page draft and test planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A page plan with copy, layout rules and one clear button
• A ranked list of fixes with a score
• A test design with the claim, the numbers to watch, the sample size and the run time
• A ship, wait or stop call with the numbers behind it

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: You are about to launch a page and want it right.

• Page plan. The page order, copy for each section, design rules and one clear button.
• Page review. The page job, glance, skim and doubt notes, and a ranked list of fixes with a score.
• Test design. The claim, the main, side and guard numbers, sample size, run time, and the control and new version.
• Result. Setup and split checks, each rate with its range, the side numbers, and a ship, wait or stop call.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Jakob Nielsen would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Plan and write the page. Takes your offer, buyer and goal, sets the page order from headline to final call and writes the copy section by section.
• Review the page. Reads it at a glance, skimmed and with doubt, checks the phone view and ranks each fix by how much it hurts.
• Publish and pick one change (your step). You fix the quick wins, publish and choose the one change to prove. You also note your recent visits and conversions.
• Design the test. Writes the hypothesis, picks the main, side and guard numbers, and works out sample size and run time.
• Run the test (your step). You run it as planned and export the counts for the control and the new version.
• Read the result and make the call. Checks the setup and the visitor split, works out each rate with its range and gives a ship, wait or stop call.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id build-a-landing-page-fix-it-and-prove-the-top-change only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/build-a-landing-page-fix-it-and-prove-the-top-change/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your offer, price and buyer
• What counts as success on the page (a sale, a signup or a call)
• Your brand file (optional)
• Visits and conversions for the last few weeks, at the first pause
• The counts for each version, at the second pause

Tools and access

• Any good chat AI: Any current chat AI that reads screenshots can run the three reads. Give it phone screenshots, top to bottom.
• PageSpeed Insights: Shows your page's real-user speed against Google's 'good' marks, so the phone check has numbers.
• Evan Miller's sample size calculator: Tells you how many visitors a test needs, so you know if it can finish in about a month.

Functions and deliverables

• Landing page draft and test planner: Draft and review a landing page. Plan a test of one change, then use real results to make the next call.
  • A page plan with copy, layout rules and one clear button
  • A ranked list of fixes with a score
  • A test design with the claim, the numbers to watch, the sample size and the run time
  • A ship, wait or stop call with the numbers behind it
• Conversion landing page designer: Share your offer, audience, and proof for landing page copy, layout, and visual design rules.
  • Page structure and layout choice
  • Landing page copy
  • Typography and spacing rules
  • Hero section design
  • Build order
  Source: Elaya Design.
• Landing page conversion reviewer: Share your page and screenshots. Get conversion problems ranked by impact, with recommended fixes and a score.
  • The page's job, a one-line verdict, and whether the page matches its ad
  • What a buyer takes from a five-second glance and from a skim
  • A ranked findings table, each with a severity from 0 to 4 and where it sits
  • Up to five quick wins, up to three tests, and what the page can't tell you
  • A page score out of 100 worked out from the severities, now and after the quick wins
• Experiment designer: Turn a proposed change, conversion rate, and traffic figures into an A/B test plan.
  • Written hypothesis
  • Test design with one variable
  • Sample size and run time
  • Main and side metrics
  • Rules for reading the result
  Source: Corey Haines.
• A/B test results analyst: Share your A/B test data. Get a split check, results with confidence ranges and a ship call.
  • A traffic split check
  • Results with 95 percent ranges
  • Guard metric checks
  • A ship, stop or extend call
  • A written test report
  Source: Nimrod Fisher.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Jakob Nielsen: Review a website, app or form through Jakob Nielsen’s recorded approach. Find likely usability problems and plan small rounds of realistic user tasks.
  • Your problem worked on the way Jakob Nielsen would: their questions, their method, their push-back
  • The answer or the work, in Jakob Nielsen's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You are about to launch a page and want it right.
• You have a list of page fixes and no way to tell which ones work.
• You get enough visits to test (a few hundred a week or more).

Limits to check before starting

• You get under a few hundred visits a week: the test would take too long, so use the Landing page conversion reviewer on its own and fix the top items by hand.
• You only want a review of a page you already have: use the Landing page conversion reviewer.
• You want to read test counts you already have: use the A/B test results analyst.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• At the first pause, publish the page and pick one change to prove.
• At the second pause, let the test run its full time before you export the counts.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/build-a-landing-page-fix-it-and-prove-the-top-change for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.