Hire an AI design revision usability test planner

Everything it can hand back

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

• An issue list where each issue names where it is on the screen, which user task it hurts and how serious it is
• A revised design brief with a specific change for each agreed issue
• A split between what was seen on the screen and what is only a preference
• A usability test with tasks, neutral prompts and signs of success
• One next step

How it does the job well

• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Writing what users did when no user was watched.
• Making a change that has no issue behind it.
• Mixing a preference into the list as if it were seen on the screen.
• Writing test tasks that tell the person where to click.
• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.

What a good result looks like

An example, not your task: A teammate says this screen feels off and you need to turn that into changes you can ship.

• Issue list. Each issue with where it is, the task it hurts, how serious it is and whether it was seen or is a preference.
• Revised design brief. A specific change for each agreed issue, and the check that shows it worked.
• Test script. Tasks, neutral prompts and finished and stuck rules for watching a few people try the changes.
• Hand-back summary. Files saved, MISSING lines, checks not run and the one change to try first.

How the work is checked

• Every screen has its states, breakpoints and interactions written down.
• Colour pairs and type sizes pass the stated contrast checks.
• The handoff names components, tokens and open questions.
• 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 Don Norman and Jakob Nielsen would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Everyday usability reviewer. Reviews the screen for finding what to do, seeing what happened, fixing errors and matching controls. Labels the result as an expert-style review, not a test with real users. Hands step 2 the issue list with where each one is. Check before moving on, each issue points to a place on the screen.
• Design feedback giver. Turns the issues you agreed into specific changes. Keeps what it saw on the screen apart from what it would prefer. Hands step 3 the revised brief. Check before moving on, every change names the issue it fixes.
• Small usability test planner. Writes task-based checks for the changes, with neutral prompts and signs of success a watcher can see. Hands back the test script. Check before moving on, no task tells the person where to click.

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 turn-a-design-review-into-fixes 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/turn-a-design-review-into-fixes/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

• One screen or prototype, as a screenshot, a Figma link or a clear description
• The people who use it and the task they are trying to do
• Limits on what can change, such as no new pages or a fixed component library
• Existing feedback or comments on the design (optional)
• Your design rules or principles (optional)

Helpful context (optional)

• Approved examples of a good result.
• A named reviewer and their acceptance rules.

Tools and access

• A capable chat AI with file support: Read the full pack and supplied sources; connected actions need the corresponding authorized tools.
• 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

• Design revision usability test planner: Share a screen, its users, main task and limits. Get a reasoned issue list, a revision brief and a small usability-test plan.
  • An issue list where each issue names where it is on the screen, which user task it hurts and how serious it is
  • A revised design brief with a specific change for each agreed issue
  • A split between what was seen on the screen and what is only a preference
  • A usability test with tasks, neutral prompts and signs of success
  • One next step
• Everyday usability reviewer: Review a product or screen for unclear actions, weak feedback and recovery gaps. Get likely issues, practical changes and checks with users.
  • Score out of 10
  • List of confusing points with causes
  • Fixes for cues, limits and feedback
  • Error recovery suggestions
  Source: Wondel.ai.
• Design feedback reviewer: Share a design, audience and goal. Get specific usability notes, reading-order feedback, strengths and fixes ranked by importance.
  • First-impression read
  • Usability issues
  • Hierarchy and consistency notes
  • Fixes ranked by importance
  Source: Anthropic.
• 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
• Don Norman: Find why a product, form or service is hard to use through Don Norman’s public approach. Check cues, controls, feedback and recovery from mistakes.
  • Your problem worked on the way Don Norman would: their questions, their method, their push-back
  • The answer or the work, in Don Norman'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

• A teammate says this screen feels off and you need to turn that into changes you can ship.
• A new checkout, settings or dashboard screen is about to go to developers and you want one more pass.
• You have a design review with ten comments and need to know which three to fix first.
• You want to prove a design change helped, not only that it looks better.

Limits to check before starting

• You have real test results or customer complaints. Start from those with Customer complaint design researcher, or the Product ease of use checker for one repeated mistake.
• You only want a quick score for a screen. Use the Everyday usability reviewer on its own.
• You need to find what blocks a test before you run it. Use the Prototype usability test planner workflow.
• You review a new screen every week. Use the Screen usability reviewer.

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 workflow pack and add it to your AI, such as Claude, ChatGPT or Gemini. One that reads images works best.
• Attach the screen and say who uses it and what task they are trying to do. Add any limits on what can change.
• After step 1, read the issue list with your team. Delete issues you disagree with. The next step only uses the ones you keep.
• After step 2, check each change points back to an issue. Remove any change with no issue behind it.
• Run the test from step 3 with a few people before you call the fixes done.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/turn-a-design-review-into-fixes 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.