Hire an AI product design and scope reviewer

Everything it can hand back

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

• A score out of 10 on each of the ten principles, with the reason for each
• A list of every part and its job, with the parts that serve no purpose marked
• A plan that sorts each feature into keep, cut or merge, with a reason
• The order a new user should meet what is left, and the size, colour and wording fixes to match

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

• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.
• Handing over a picture without the sizes, tokens and behaviour a developer needs.

What a good result looks like

An example, not your task: Your product, app or page has grown cluttered and new users don't know where to start.

• Purpose. One sentence on what the product is for and who uses it.
• Ten-principle scores. A score out of 10 and a reason for each principle, with a total out of 100.
• Parts list. Every part and its job, with the idle parts and the cuts that follow from them.
• Keep, cut and merge plan. Each feature sorted, with a reason, and the order a new user should meet them.
• Consistency fixes. Size, colour and wording changes so the parts that stay look and read as one.
• Hand-back summary. Each step's file 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.
• The purpose is one sentence and every score refers back to it.
• 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 Dieter Rams and Herb Lubalin would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Score against ten principles. Writes what the product is for, lists every part and its job, and scores it on ten principles. Marks the parts that serve no purpose.
• Plan the cuts. Takes the review and asks of each feature whether it helps the main job. Sorts them into keep, cut and merge, then sets the order a new user should see them.

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 ten-principles-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/ten-principles-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

• A description of the product, who uses it and what it is for
• A page or screenshot of it (optional)
• A list of its features, parts or settings (optional)
• Usage numbers or support questions for each feature (optional)

Helpful context (optional)

• Usage numbers for each feature
• Support questions about the product
• A screenshot of every main screen

Tools and access

• Any good chat AI: Takes screenshots and a feature list and works through both steps.
• Your analytics tool: Shows which features real users never touch, which backs up the cut list.
• Any good chat AI that reads images: It can judge what is in a screenshot or photo, not only your description.
• A notebook or spreadsheet: Keeping the part list and scores side by side shows progress between reviews.
• Any good chat AI: Weighing a list of features against one job is text work any strong chat AI does well.
• A spreadsheet: A part-by-part table with usage counts makes decisions easy to see.

Functions and deliverables

• Product design and scope reviewer: Share your product or page and its main job. Get a ten-principle review and a reasoned keep, cut or merge plan.
  • A score out of 10 on each of the ten principles, with the reason for each
  • A list of every part and its job, with the parts that serve no purpose marked
  • A plan that sorts each feature into keep, cut or merge, with a reason
  • The order a new user should meet what is left, and the size, colour and wording fixes to match
• Ten-principle product design reviewer: Share a product, page or service. Review each part’s purpose, score ten design principles and get reasoned cuts and fixes.
  • One-sentence purpose and a list of every part with its job
  • A verdict and reason for each of the ten principles
  • Parts that serve no purpose, with proposed cuts
  • A score out of 100, with how it was worked out
• Feature cutting planner: Plan which features to cut. Give it your feature list and the main job users want done. You get keep, cut or merge calls with reasons.
  • A keep, cut or merge decision for every part, with a reason
  • The order the remaining parts should take
  • A consistency check on size, colour and wording
  • A dated plan, with the order to make the changes
• Page keep-or-cut auditor: Find which pages to keep, update, merge, redirect or delete in your content audit. Give it your page list and data. You get a call and reason per page.
  • Each page marked keep, update, merge, redirect or delete
  • Reason for each call
  • Priority order of work
  • Redirect map for pages you remove
  Source: RampStack.
• 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
• Dieter Rams: Simplify a product, page or form using Dieter Rams’s recorded principles. Keep what serves the purpose and check that the design is honest.
  • Your problem worked on the way Dieter Rams would: their questions, their method, their push-back
  • The answer or the work, in Dieter Rams's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Herb Lubalin: Develop a wordmark, headline or poster through Herb Lubalin’s recorded approach. Make the letters carry one idea and check how well they read.
  • Your problem worked on the way Herb Lubalin would: their questions, their method, their push-back
  • The answer or the work, in Herb Lubalin'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

• Your product, app or page has grown cluttered and new users don't know where to start.
• You are planning a redesign and want to decide what goes before you decide what it looks like.
• Your team can't agree on which features to keep, and you want a shared standard to argue from.
• A settings menu or a form has gone past a screen long and nobody can say why each item is there.

Limits to check before starting

• You want to find where visitors get stuck on one page: use Page usability test planner.
• You sell many products and want to cut the line by what pays: use Product and team priority planner.
• The product has no features yet. Talk to customers first with Customer buying-journey interview planner.
• You want a new look or a visual redesign. This decides what to remove, not how it looks.

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".
• Describe the product and say what it is for. Add a page, screenshot or feature list if you have one.
• It works step by step and saves each result. Read the review before you read the cut list.
• Check the cuts with your team before you remove anything people rely on.

Read it as data

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