---
name: critique
description: "Use when building, styling, optimizing, and auditing critique components, responsive layouts, design systems, and frontend state."
version: 6.0.0
last-updated: 2026-09-29
skills:
  - ui-ux-researcher
  - web-design-guidelines
  - baseline-ui
tools: Read, Grep, Glob, Bash, Edit, Write
scripts-binding:
  - .agent/scripts/checklist.js
  - .agent/scripts/verify_all.js
  - .agent/scripts/lint_runner.js
inputs:
  task: "string"
  target_file: "string"
outputs:
  result: "string"
  verification_status: "boolean"
trigger:
  - "critique"
---

# Critique — Structured UX & Design Quality Evaluation

## Mandatory Pre-Flight Context Inspection
Before reading, generating, or refactoring code in the `critique` domain, inspect these 5 critical parameters:
1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).


## Activation Boundaries
- **Activate when:** Use when building, styling, optimizing, and auditing critique components, responsive layouts, design systems, and frontend state.
- **DO NOT activate when:** The task falls outside the `critique` domain or is managed by a different dedicated specialist agent.


## 🔁 Multi-Pass Execution Protocol

| Pass | Phase | Core Action | Adaptive Depth |
|:---|:---|:---|:---|
| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |


---

## 🛠️ Technical Architecture & Reference Recipes

---

## The 6 UX Critique Heuristics

```
1. Clarity & Cognitive Load (0-10)
   - Is the primary task obvious within 3 seconds?
   - Is visual hierarchy clear with distinct primary, secondary, and tertiary elements?

2. Information Architecture & Pacing (0-10)
   - Is content logically grouped with appropriate negative space?
   - Is reading flow natural (top-left to bottom-right)?

3. Interaction Mechanics & Tactility (0-10)
   - Are interactive targets obvious and sized >= 44x44px for touch?
   - Is immediate feedback provided for hover, press, focus, and loading states?

4. Visual Elegance & Brand Craft (0-10)
   - Are color palettes harmonious and consistent?
   - Are typographic scales disciplined and optically balanced?

5. Accessibility & Inclusivity (0-10)
   - Does contrast meet WCAG AA standards (4.5:1 text, 3:1 UI controls)?
   - Is the screen fully navigable via keyboard with visible focus indicators?

6. Edge Case Resilience (0-10)
   - Are zero-item empty states, errors, loading skeletons, and truncated text handled?
```

---

## Critique Output Format (Required)

Always output the critique as a structured Markdown evaluation:

```markdown
# 🔍 UX Critique Report

### Overall Quality Score: 8.2 / 10

| Heuristic Domain         | Score | Critical Observation                                |
| ------------------------ | ----- | --------------------------------------------------- |
| Clarity & Cognitive Load | 8/10  | Hero CTA is clear, but subhead copy is verbose.     |
| Information Architecture | 9/10  | Excellent grouping and card rhythm.                 |
| Interaction Mechanics    | 7/10  | Missing `:active` press state on primary buttons.   |
| Visual Elegance & Craft  | 9/10  | Great typography scale and subtle border treatment. |
| Accessibility            | 8/10  | Text contrast passes; dropdown needs ARIA labels.   |
| Edge Case Resilience     | 8/10  | Empty state present; needs loading skeleton.        |

### Top 3 Actionable Fixes

1. **[High Priority]**: Add `:active` scale transform (`scale(0.97)`) to interactive buttons.
2. **[Medium Priority]**: Add `text-wrap: balance` to display headings to eliminate orphans.
3. **[Low Priority]**: Truncate secondary card description strings to 2 lines (`line-clamp-2`).
```

## 🚨 Edge-Case & Failure Mode Matrix

| Scenario | Risk | Production Mitigation |
|:---|:---|:---|
| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |


## 🤖 LLM-Specific Traps Table

| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
|:---|:---|:---|
| **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
| **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
| **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |


## 🏛️ Tribunal Verification & Guardrails

**Active Reviewers:** `frontend-reviewer` · `type-safety` · `ui-ux-auditor` · `complexity-reviewer`
**Slash Command:** `/review` or `/tribunal-full`

### 🔬 Evidence Standard (Tri-State Verification)
Every finding, audit statement, or completion claim must classify its factual certainty:
- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.

### ✅ Pre-Flight Self-Audit Checklist
```
✅ Are all component props strictly typed with zero implicit "any"?
✅ Are responsive breakpoints, fluid typography, and optical balance verified?
✅ Is accessibility (ARIA labels, keyboard navigation, contrast ratio >= 4.5:1) validated?
✅ Are re-renders minimized and state lifecycles cleanly separated?
✅ Did I verify all imported UI components and icon sets actually exist?
```

### 🛑 Verification-Before-Completion (VBC) Protocol
**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.