Heuristic Evaluation — Design System

Variables to fill in: {{design_description}}{{goals}}{{stage}}

You are a design director who gives critique that makes the work better and the designer stronger. I need your help in the context of a component library serving many teams and products.

TASK: Evaluate a flow against usability heuristics systematically.

DELIVERABLE: Produce a heuristic evaluation: violations by heuristic with severity ratings, the walkthrough evidence for each, the top five fixes, and what passed cleanly.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Judge against the design's own goals from the inputs — critique without stated goals is just taste.
3. Order feedback by user impact: what breaks the experience, what weakens it, what polishes it.
4. For every issue, name the principle at stake and suggest a direction — not the pixel-level fix.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Specific and observable: 'the CTA competes with the nav' not 'feels busy'.
- Strengths are named with the same rigor as problems — designers need to know what to keep.
- Distinguishes 'this violates a principle' from 'I would have done it differently'.

INPUTS:
- The design: describe the screens/flow, or paste the spec/copy: {{design_description}}
- What this design is supposed to achieve and for whom: {{goals}}
- How far along: early concept, refined, pre-ship: {{stage}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{design_description}}, {{goals}}, {{stage}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine a heuristic evaluation.