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 effectively communicates both the methodology (quantitative scoring, persona-based testing) and the assessment dimensions. The only minor weakness is potential overlap with other design-related skills due to the broad terms 'design' and 'component', though the evaluation/critique 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 focused on design implementation, visual design creation, or component development. It could benefit from clarifying it's for evaluation/critique rather than 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 phased workflow, concrete output formats, and good use of external references for detailed content. Its main weakness is moderate verbosity — some UX concepts are over-explained for Claude's knowledge level, and the inline examples in Phase 3 could be more concise. Overall it's a strong skill that provides clear, executable guidance for conducting thorough design evaluations.
Suggestions
Trim explanations of well-known UX concepts (peak-end rule, progressive disclosure, affordance) to just the checklist items — Claude already understands these concepts and only needs the specific evaluation criteria.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is structural (evaluation dimensions, scoring tables, persona examples). Some sections are verbose — e.g., the Emotional Journey and Information Architecture sections explain UX concepts Claude already knows (peak-end rule, progressive disclosure). The question templates in Phase 3 include excessive inline examples that could be tightened. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific scoring tables with numeric scales, exact output formats (Nielsen heuristic table with score bands), specific persona walkthrough formats with example outputs, tagged severity levels (P0-P3), and named commands to recommend. The persona red flag examples are copy-paste ready templates. | 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, Phase 3 questions must reference Phase 2 findings). Validation is built in via the mandatory preparation step and the cognitive load checklist with pass/fail thresholds. The conditional logic (skip Phase 3 if findings are straightforward) shows thoughtful error handling. | 3 / 3 |
Progressive Disclosure | The skill effectively uses progressive disclosure by referencing external files for detailed content (cognitive-load.md, heuristics-scoring.md, personas.md, frontend-design skill) while keeping the main skill focused on the workflow and evaluation structure. References are one level deep and clearly signaled with blockquote callouts. | 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
db1add7
- 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.