Hire an AI Filament admin interface reviewer

Everything it can hand back

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

• A layout plan that shows the form before and after
• A ranked list of structure changes, each with its reason
• The rewritten resource code
• A check that every original field is still there
• A list of changes it left out on purpose
• Steps to test the create and edit screens

How it does the job well

• Do not call a change useful unless it changes how the form is structured or navigated. Icons, hints and labels alone are not an optimization.
• Method names differ across Filament versions. Tell the user to check each method against the docs for their version. Never say the code was run.
• Do not drop a field. If a field looks unused, flag it and ask.
• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: A Filament form is one long list of more than 8 fields, and admins scroll too much.

• Layout plan. The form before and after, with rows, tabs, side-by-side sections and collapsed parts.
• Changes. A ranked list of structure changes, each with why it helps admins.
• Rewritten resource. The full resource code with the new layout.
• Field check. Every original field and where it sits now.
• Left alone on purpose. Fields and sections it kept simple, and why.
• Tests to run. What to check on the create and edit screens.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• 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 Kent Beck and Linus Torvalds would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read the file. It reads your resource file and maps every field, its type and its place on the screen.
• Find the pain. It finds the worst part of the form, usually too long, too flat or too noisy.
• Plan the layout. It draws the new layout as a comment block, with what is always visible, what sits in tabs and what is collapsed.
• Upgrade the inputs. It swaps rating rows for sliders, labels repeater items and collapses sections that are usually empty.
• Check nothing was lost. It compares the new field list with the old one and walks through create and edit separately.
• Trim the noise. It removes hints, icons and wrappers that add clutter and do not help people scan.

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 engineering-filament-optimization-specialist 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/engineering-filament-optimization-specialist/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

• Your Filament resource file, the PHP file that holds the form and table
• Your Filament and Laravel versions
• What admins do most on this screen, and what annoys them
• The model's fields or migration, if the resource file does not show every field (optional)
• Your tests for this resource (optional)

Helpful context (optional)

• A screenshot of the current form.
• A list of the fields admins fill in every time, and the ones they skip.

Tools and access

• Claude, ChatGPT or Gemini with file upload: It reads the full resource file and returns code you can compare line by line.
• A coding tool such as Claude Code: It can edit the file in your project and run your tests.

Functions and deliverables

• Filament admin interface reviewer: Get a Filament admin review: tabs, layout and menu fixes for your forms. Share your PHP resource file and keep every field.
  • A layout plan that shows the form before and after
  • A ranked list of structure changes, each with its reason
  • The rewritten resource code
  • A check that every original field is still there
  • A list of changes it left out on purpose
  • Steps to test the create and edit screens
  Source: Michael Sitarzewski and Agency Agents contributors.
• Azure resource cost reviewer: Share Azure files and resources. Get cost findings and proposed fixes ranked by score. GitHub issues are optional and need approval.
  • A summary of current cost and possible savings for you to approve
  • One GitHub issue per fix, with evidence, risks and checks
  • A priority score so you start with the biggest savings
  • A tracking issue with a diagram of your current setup
  Source: GitHub Copilot community.
• Apple interface reviewer: Check your iOS or Mac screen against Apple's design rules, with contrast and tap target checks, a score and a fix list for Liquid Glass too.
  • A scored audit report
  • Contrast and tap target measurements
  • Platform-specific layout advice
  • A prioritised fix list
  Source: Alireza Rezvani.
• Expo app interface builder: Turn screen plans and an Expo project into Expo Router screens, controls, and code for motion.
  • Expo Router screen files in an app folder
  • Layout files that set up stacks and native tabs
  • A color theme file that works in light and dark mode
  • Motion, native controls, search and sheets where you asked for them
  • The list of packages to install
  Source: sickn33.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.
• Kent Beck: Plan a software change using Kent Beck’s recorded approach. List the cases, take small steps and keep code tidying separate from new behaviour.
  • Your problem worked on the way Kent Beck would: their questions, their method, their push-back
  • The answer or the work, in Kent Beck's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Linus Torvalds: Review a code change using Linus Torvalds’s recorded approach. Ask what works, what breaks for existing users and who owns the fix.
  • Your problem worked on the way Linus Torvalds would: their questions, their method, their push-back
  • The answer or the work, in Linus Torvalds'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 Filament form is one long list of more than 8 fields, and admins scroll too much.
• A form uses rows of 1 to 10 radio buttons for ratings.
• A repeater shows "Item 1, Item 2" instead of useful labels.
• Your admin menu is one long flat list and people cannot find things.

Limits to check before starting

• You have a bug in your Laravel code, not a layout problem. Use the Code reviewer agent.
• Your admin panel is not built with Filament. Use the Full stack developer.
• Pages are slow because of database queries. Use the Database performance analyst.

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 pack from this page and add it to your AI as a skill. If you cannot, open a new chat and paste SKILL.md, then references/source-agent.md.
• Paste your resource file. Add your Filament and Laravel versions, and a line on what admins do on this screen.
• Say "Review this resource. Do not drop any field. Ask once if anything is missing."
• Open the layout plan first. If the groups do not match how your admins think, say so and ask for another grouping.
• Check the field list against your original file. Every field must appear once.
• Run your tests, then open the create and edit screens in a test copy of your app before you merge.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-filament-optimization-specialist 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.