1---
2tagline: "A design review with scoring, persona tests, and automated detection."
3---
4
5<div class="docs-viz-hero">
6 <div class="docs-viz-critique">
7 <div class="docs-viz-critique-head">
8 <div class="docs-viz-critique-verdict">
9 <span class="docs-viz-critique-verdict-label">AI slop verdict</span>
10 <span class="docs-viz-critique-verdict-value">FAIL</span>
11 </div>
12 <span class="docs-viz-report-target">gradient-text · ai-color-palette · nested-cards</span>
13 </div>
14 <div class="docs-viz-critique-cols">
15 <div>
16 <div class="docs-viz-critique-col-title">Heuristics (Nielsen)</div>
17 <div class="docs-viz-critique-heuristics">
18 <div class="docs-viz-critique-heur">
19 <span>Visibility of status</span>
20 <span class="docs-viz-critique-heur-score docs-viz-critique-heur-score--good">3</span>
21 </div>
22 <div class="docs-viz-critique-heur">
23 <span>Match with real world</span>
24 <span class="docs-viz-critique-heur-score docs-viz-critique-heur-score--ok">2</span>
25 </div>
26 <div class="docs-viz-critique-heur">
27 <span>Consistency & standards</span>
28 <span class="docs-viz-critique-heur-score docs-viz-critique-heur-score--ok">2</span>
29 </div>
30 <div class="docs-viz-critique-heur">
31 <span>Error prevention</span>
32 <span class="docs-viz-critique-heur-score docs-viz-critique-heur-score--good">3</span>
33 </div>
34 <div class="docs-viz-critique-heur">
35 <span>Recognition over recall</span>
36 <span class="docs-viz-critique-heur-score docs-viz-critique-heur-score--bad">1</span>
37 </div>
38 </div>
39 </div>
40 <div>
41 <div class="docs-viz-critique-col-title">Personas</div>
42 <div class="docs-viz-critique-personas">
43 <div class="docs-viz-critique-persona">
44 <div>
45 <span class="docs-viz-critique-persona-name">The evaluator</span>
46 <span class="docs-viz-critique-persona-note">Comparing us to two alternatives on a Tuesday evening.</span>
47 </div>
48 <span class="docs-viz-critique-persona-score">2 / 4</span>
49 </div>
50 <div class="docs-viz-critique-persona">
51 <div>
52 <span class="docs-viz-critique-persona-name">The returning user</span>
53 <span class="docs-viz-critique-persona-note">Knows the product, on mobile, in a hurry.</span>
54 </div>
55 <span class="docs-viz-critique-persona-score">3 / 4</span>
56 </div>
57 <div class="docs-viz-critique-persona">
58 <div>
59 <span class="docs-viz-critique-persona-name">The skeptic</span>
60 <span class="docs-viz-critique-persona-note">Has seen every SaaS landing and is bored.</span>
61 </div>
62 <span class="docs-viz-critique-persona-score">1 / 4</span>
63 </div>
64 </div>
65 </div>
66 </div>
67 </div>
68 <p class="docs-viz-caption">The two passes (LLM design review plus the deterministic detector) merge into one prioritized list. What's working, what to fix, and the provocative questions worth answering before shipping.</p>
69</div>
70
71## When to use it
72
73Reach for `/impeccable critique` when you want an honest second opinion on something you already built. Not "does it work" but "is it any good". The skill scores your interface against Nielsen's 10 heuristics, runs cognitive load checks, tests through persona lenses, and cross-references an automated detector for 25 concrete anti-patterns.
74
75Use it when a page is functionally done and you want to know if it reads as intentional or as AI slop.
76
77## How it works
78
79`/impeccable critique` runs two independent assessments in parallel so they do not bias each other.
80
81The first is an **LLM design review**: the model reads your source, visually inspects the live page if browser automation is available, and walks the impeccable skill's full DO/DON'T catalog. It scores Nielsen's heuristics, counts cognitive load failures, traces the emotional journey through the flow, and flags AI slop.
82
83The second is an **automated detector** (`npx impeccable detect`) that deterministically finds gradient text, purple palettes, side-tab borders, nested cards, line length problems, and the other visible fingerprints of generic AI output.
84
85The two reports merge into one prioritized list: what is working, the three to five things that need fixing, and the provocative questions worth answering before shipping.
86
87## Try it
88
89Point it at a page:
90
91```
92/impeccable critique the homepage hero
93```
94
95You get back a scored report. Typical shape:
96
97- **AI slop verdict**: pass / fail with the specific tells
98- **Heuristic scores**: 10 numbers, 0 to 4
99- **Cognitive load**: failure count out of 8
100- **Priority issues**: three to five items, each with what, why, and fix
101- **Questions to answer**: the ones the interface itself cannot decide for you
102
103From there, pair with `/impeccable polish` or `/impeccable distill` to act on the fixes.
104
105## Pitfalls
106
107- **Running it on incomplete work.** Critique is for finished pages. An empty state with three TODOs will score badly because it is not done, not because it is bad.
108- **Ignoring the questions at the end.** They are usually the fixes that change the design most.
109- **Treating the heuristic scores as a grade.** They are diagnostic, not evaluative. A 3/4 on a heuristic that matters less for your context is fine.