Hire an AI reference-based image ad builder

Everything it can hand back

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

• A selectable reference index and adaptation map.
• Editable compositions and approved-size exports where tools permit.
• A review deck, QA log and revision manifest.

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: You have a swipe library and want finished ads from selected layouts.

• brand.json. Your name, colours, fonts, logo, product photos, approved claims, blocked claims and current offer.
• Reference index and selection. Each reference with a stable ID, format, message device and risk, and who picked it, you or the AI.
• Adaptation map. For each reference, what to keep, swap or drop, plus any claim that cannot move to your brand.
• Ad briefs. One brief per ad with the buyer problem, one supported message, on-image words and layout zones.
• Editable ad files and exports. Ads with live text and logo layers, exported at 1080x1350 and 1080x1920 where your tools allow.
• Review deck, QA log and revision manifest. Each ad and size with a version, a check status and the corrections you asked for.

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 Jakob Nielsen would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Choose layouts. Index the references, keep user selections stable and capture per-ad direction.
• Rebuild with real assets. Translate layout devices into true brand claims and composite text separately from imagery.
• Inspect every size. Render, check, fix and show a versioned review deck before any publishing.

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 swipe-library-ad-production 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/swipe-library-ad-production/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

• Brand facts, live offers, approved claims, logo and fonts.
• Real photos of the exact product variant.
• Reference layouts you have permission to study, with any directions for each.

Functions and deliverables

• Reference-based image ad builder: Choose reference layouts, rebuild them with real product photos and live type, then review checked ads in multiple sizes.
  • A selectable reference index and adaptation map.
  • Editable compositions and approved-size exports where tools permit.
  • A review deck, QA log and revision manifest.
• 3D cutaway image ad maker: Share sourced product facts and approved claims. Get a cutaway image prompt, layout and ad copy, with image creation when tools allow.
  • The three tests, the chain with every link marked, and the one link to freeze
  • A parts key and honesty notes for your product
  • The layout, the words on the image checked for size and contrast, and an image prompt
  • Feed copy with a first line, headline and button
  • Any of the skill's five checks it couldn't meet, one line each
• Product photo ad prompt set writer: Turn one product photo into six ready-to-paste image ad prompts that share the same brand details, copy and layout rules.
  • A brand fingerprint to check before anything is made
  • Six ads with different jobs, each with a headline, a support line and one action
  • Six full prompts that each work on their own
  • A fix guide for wrong spelling, a changed product, drifting colour and crowded layouts
  • A MISSING list for any fact you left out
• Reference-style product photo maker: Make product photos that match a look you like. Attach your product and one reference photo. Get an image prompt and ranked pictures.
  • A five-part reading of the reference photo
  • A keep, swap or drop line for each part
  • The finished image prompt, ready to paste
  • If your chat can make images, the pictures ranked with a score out of 100, and a reject list
  • If it can't, any of the four checks the prompt still missed
• 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 have a swipe library and want finished ads from selected layouts.
• You need a review deck with revisions tracked by ad and size.

Limits to check before starting

• You have no reference ads, only your own: use the Brand ad remix designer.
• You want new image ads in the style your winners share: use Image ad style and concept planner.
• You want one ad built on an offer: use Meta offer image ad planner.
• You only want a product photo set: use the Reference-based product photoshoot planner.

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 complete pack and give its instructions to your AI.
• Provide the inputs listed here. Ask the AI to follow the method and return the stated outputs.
• Check the result against the supplied facts before using it.
• After the review deck is approved, hand the approved exports and the revision manifest to your publishing tool. Check each size before you publish.

Read it as data

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