Hire an AI page usability test planner

Everything it can hand back

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

• A list of usability problems on the page, with the costliest ones first
• Every choice a first-time visitor faces, rated for how much thought it takes, with a plain rewrite for the hard ones
• A one-morning test plan with who to ask, the tasks, a script to read aloud and a sheet for noting what you see

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: Visitors reach your page but don't do the thing it is for, and you can't see why.

• Usability heuristic reviewer result. Problems found against ten usability rules, ordered by what each costs the visitor, with a fix for each.
• Click choice clarity checker result. Each choice a visitor faces, rated obvious or needs thought, with a plain rewrite for the hard ones.
• Small usability test planner result. A one-morning test plan: who to ask, the tasks, a read-aloud script, a notes sheet and a fix list.
• 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

• Every problem names the rule it breaks and where on the page it happens.
• The choice ratings cover the whole path to the goal, not only the first screen.
• Each rewrite is plainer than the label it replaces, not just a synonym.
• The test has three or four tasks, each a real goal and not a quiz on the page.
• 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 Steve Krug and Jakob Nielsen would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Review against ten rules. Walks the page as a newcomer would and checks it against ten well-known usability rules. Problems are ordered by what they cost the visitor.
• Rate every choice. Takes the problems from the review and lists each choice on the way to the goal. Rates it as obvious or needing thought, and rewrites vague labels.
• Plan the morning test. Uses the problems and ratings to pick the few tasks that matter. Writes the script, how to find three people and a sheet for the worst problems you see.

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 page-usability-review 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/page-usability-review/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

• The page or screen to review (a link, a screenshot or the text)
• What a visitor should be able to do on it, such as buy, book or find a price
• A saved copy of the page, if the live one can't be opened (optional)
• A screenshot of your store or app (optional)
• Notes on the layout, such as which blocks sit where (optional)
• A short description of your typical visitor (optional)
• A morning, and three people to test with, for the last step

Helpful context (optional)

• A screenshot of each screen on the path to the goal
• Any support questions or complaints about the page
• Your best guess at where visitors give up

Tools and access

• Any good chat AI: Reads a screenshot of the page and works through all three steps.
• A screen recorder: Lets you record the test sessions and replay the moments where people paused.
• Any good chat AI that reads images: It needs to look at screenshots, so use an AI that accepts attachments.
• A screen recorder: Record yourself doing the task, to catch what a static screenshot hides.
• Any good chat AI that reads images: It needs to look at screenshots of menus and buttons.
• Your site search log: The words people type are the best source of plain labels.
• Any good chat AI: Planning tasks and writing the script is text work any strong chat AI does with this skill.
• A screen and voice recorder: Record each session from the first screen so you can replay the pauses.

Functions and deliverables

• Page usability test planner: Share a page and the task users need to finish. Get usability concerns, clearer click choices and a small participant-test plan.
  • A list of usability problems on the page, with the costliest ones first
  • Every choice a first-time visitor faces, rated for how much thought it takes, with a plain rewrite for the hard ones
  • A one-morning test plan with who to ask, the tasks, a script to read aloud and a sheet for noting what you see
• Website usability reviewer: Check a page or form against ten usability rules. Get a usability review with a score out of 100, each break found and fixes ranked by harm.
  • A score out of 100 with the deductions shown
  • Every break, with the rule it breaks and the screen or step
  • Fixes ranked by cost to the user
  • A list of what still needs a real test
• Button and link label reviewer: Check your menu and button labels for clarity. Get each choice rated, a score out of 100, and plain rewrites for weak labels.
  • Every choice listed and rated: clear or needs thought
  • A score out of 100 with the working
  • A plain rewrite for each weak label
  • Places to add short help, and where not to
• Small usability test planner: Plan a small usability test in one morning. Name what people should do. You get tasks, a read-aloud script and a fix list of the worst problems.
  • The three to five tasks to test, in order
  • Who to recruit and how, including one outsider
  • A read-aloud script and a note sheet
  • A fix list template, limited to the worst problems
• 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
• Steve Krug: Review a screen or plan a small usability test using Steve Krug’s recorded approach. Make the task clear and watch real people try it.
  • Your problem worked on the way Steve Krug would: their questions, their method, their push-back
  • The answer or the work, in Steve Krug's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• 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

• Visitors reach your page but don't do the thing it is for, and you can't see why.
• You are about to pay for a redesign and want to know which problems are real before you do.
• You have changed a page or screen and want a quick check with real people before it goes live.

Limits to check before starting

• Your page has no clear goal for visitors yet. Decide what a visitor should do first, then run this review.
• You want to know why an ad is not getting responses. Use the Ad response troubleshooter.
• You want to check a page against 30 sales checks or pricing questions. Ask a person who knows your market, or run a tool built for that job.

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".
• Give it the page and say what a visitor should be able to do on it.
• It works step by step and saves each result. Read the choice ratings before you plan the test, since they tell you which tasks to give people.
• Run the test with three people, then fix the worst problems first.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/page-usability-review 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.