Score the slop

Name the problem precisely across four dimensions.

First time here? Paste the Context Pack first so the AI understands your project - open it from the header above.

Prompt Capsule

Run a brutal slop audit on this app and score each dimension 1-10 with evidence. DESIGN: default fonts, generic gradients, emoji-as-icons, identical card grids, no visual identity. COPY: lorem ipsum, robotic microcopy, 'Welcome to your dashboard' filler, inconsistent tone. FUNCTION: dead buttons, fake success states, data that resets, missing states. DETAILS: default favicon/title, console errors, no focus states, broken mobile. List every finding with location. No mercy - the score guides the fix order.

Paste into EmergentFull Build: complete implementation prompt with explicit requirements

Quick is short. Full Build is recommended for most steps. Strict forces real logic when the AI keeps faking output.

Actual change check

Expected after this step

A scored four-dimension audit with located findings.

Should NOT happen

An existing feature broke
A button only logs to console
Data disappears after refresh
Errors fail silently with no visible state

This is what should exist before you continue. If reality does not match, do not move on.

Your notes for this step

Track what changed, failed, or needs follow-up. Notes export with the flow.

Pass the Verify Gate to complete this step

Verify before continuing

Do not move on until every check is true. The complete button stays locked until then.

All four dimensions scored with evidenceFindings include locationsFunction-slop is separately identified

Do not continue if…

! Polishing visuals while buttons stay dead
! Replacing generic with differently-generic
! Missing the details: favicons, titles, console errors, focus states
! Claiming 'premium feel' without changing tokens

If the AI messes this up

Use this when:

- it only made visual forms or placeholder UI
- buttons do nothing or only log to console
- data is not persisted - state disappears on refresh
- something that worked before is now broken

Use this when the AI fakes progress or breaks the feature. It forces a real fix.

The audit is soft and vague. Re-run it hostile: click everything, read every string, check the favicon and console - list findings someone could act on.