Hire an AI generative art and image export workflow

Everything it can hand back

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

• An art page you can run, with controls and a seed
• Sharp stills of the piece at high resolution
• Smaller WebP or PNG files with the size saved

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 want original art for a site, a poster or a social post.

• step-01-generative-art-maker.md. The art page you can run in a browser, with a seed and controls.
• step-02-app-screenshot-maker.md. The sharp stills captured from the running art page, with clear names.
• step-03-image-compressor.md. The smaller WebP or PNG files, plus the size before and after.
• 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

• The page runs without errors, and the controls change the art.
• Running the page again with the same seed gives the same art, and each still matches a seed you can repeat.
• Stills are sharp, with no cut-off edges.
• Compressed files look the same as the originals, and the size saved is reported.
• 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.

Capabilities

• Build the art page. Names the style, writes what it expresses, codes a piece that runs in the browser and adds controls and a seed.
• Capture the stills. Opens the running page, captures the number of stills you ask for at high resolution and saves them with clear names.
• Shrink the files. Compresses the stills to WebP or PNG, keeps the originals and reports the size saved.

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 make-generative-art-and-export-sharp-small-images 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/make-generative-art-and-export-sharp-small-images/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 look, such as mood, colours and movement
• How many stills you need and what they are for
• A computer that can run the page and a screenshot tool (Playwright, free to install)

Functions and deliverables

• Generative art and image export workflow: Describe the art and intended use. Get an editable coded artwork, captured stills and compressed files where the required tools can run.
  • An art page you can run, with controls and a seed
  • Sharp stills of the piece at high resolution
  • Smaller WebP or PNG files with the size saved
• Generative art maker: Describe a mood and get generative art you can open in a browser, tweak with sliders and repeat with a seed. Made with p5.js code.
  • A short written art philosophy
  • An interactive HTML viewer
  • A p5.js sketch file
  • Seeds to repeat any result
  Source: Anthropic.
• App screenshot maker: Capture sharp, high-resolution screenshots of your running app for Product Hunt, social posts or your site. Give it your app address.
  • High-resolution PNG screenshots, each 2880x1800 pixels
  • Shots of the screens you choose, one file per screen
  • Files with numbered, readable names
  • A capture script you can run again after a redesign
  Source: sickn33.
• Image compressor: Compress images to smaller WebP or PNG files that look nearly identical at your chosen quality. Point it at one file or a folder.
  • Compressed WebP or PNG files
  • Original files kept if you choose
  • Size savings per image
  Source: Jim Liu.
• 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

Tasks you can use it for

• You want original art for a site, a poster or a social post.
• You want a result you can repeat and tweak later.
• You need stills of a piece, not the running page.

Limits to check before starting

• You want photos or pictures of people: use an image model, since this makes art drawn in code.
• You only need to shrink images you already have: use the Image compressor.
• You want a favicon from an existing picture: use the Favicon maker.

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 look in a few lines. Name colours and a mood.
• Open the page it makes and try a few seeds. Pick the ones you like.
• Say how many stills you need and where they will be used.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/make-generative-art-and-export-sharp-small-images 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.