critique
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates specific UX evaluation capabilities and includes an explicit 'Use when' clause with natural trigger terms. The description is well-structured, uses third person voice, and covers both what the skill does and when to use it. The only minor weakness is potential overlap with other design-related skills due to the broad terms 'design' and 'component', though the evaluation-focused framing helps mitigate this.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: assessing visual hierarchy, information architecture, emotional resonance, cognitive load, quantitative scoring, persona-based testing, and actionable feedback. These are well-defined UX evaluation activities. | 3 / 3 |
Completeness | Clearly answers both 'what' (evaluate design from a UX perspective with specific assessment dimensions and methods) and 'when' (explicit 'Use when' clause with trigger scenarios: review, critique, evaluate, or give feedback on a design or component). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'review', 'critique', 'evaluate', 'give feedback', 'design', 'component', 'UX'. These are terms users would naturally use when requesting design evaluation. | 3 / 3 |
Distinctiveness Conflict Risk | While the UX-specific terminology (visual hierarchy, cognitive load, persona-based testing) helps distinguish it, the broad terms 'design' and 'component' could overlap with skills for visual design creation, design systems, or UI component building. It could be more distinct by specifying it's for evaluation/critique only, not creation. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable design critique skill with clear phasing, concrete output formats, and good use of progressive disclosure through external references. The workflow is logically sequenced with appropriate conditional branching. Minor verbosity in some evaluation dimensions and the 'Remember' section could be trimmed, but overall the content density is justified by the complexity of the task.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is domain-specific evaluation criteria Claude wouldn't inherently know (AI slop detection, persona-based testing, specific scoring rubrics). However, some sections like 'Remember' bullet points at the end restate obvious feedback principles, and several evaluation dimensions could be more tightly written. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific scoring tables with exact formats, numbered phases with clear deliverables, severity tagging (P0-P3), persona walkthrough examples with specific failure language, and exact output structures like the Nielsen heuristics table. The examples of persona red flags are particularly actionable. | 3 / 3 |
Workflow Clarity | The four-phase workflow is clearly sequenced (Preparation → Critique → Present Findings → Ask User → Recommended Actions) with explicit dependencies between phases (Phase 4 depends on user answers from Phase 3). Validation is built in through the scoring system and the instruction to re-run critique after fixes. The conditional logic (skip questions if findings are straightforward) adds appropriate flexibility. | 3 / 3 |
Progressive Disclosure | The skill effectively references external files for detailed content (cognitive-load.md, heuristics-scoring.md, personas.md, frontend-design skill) while keeping the main file focused on the critique workflow. References are one level deep and clearly signaled with inline links and context about what to consult each reference for. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- pbakaus/impeccable
- Commit
3a4fc70
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.