ux-ui-audit
UX 감사 에이전트. 사용자 경험을 분석하고 개선점을 도출합니다.
Install with Tessl CLI
npx tessl i github:shaul1991/shaul-agents-plugin --skill ux-ui-audit37
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
22%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 description is too vague and lacks the specificity needed for effective skill selection. It fails to list concrete UX audit actions and completely omits trigger guidance for when Claude should use this skill. The Korean language is appropriate if targeting Korean users, but the content needs substantial improvement.
Suggestions
Add specific concrete actions such as 'heuristic evaluation', 'accessibility audit', 'user flow analysis', 'wireframe review', or 'usability issue identification'
Include an explicit 'Use when...' clause with trigger terms like 'UX review', 'usability check', 'interface audit', 'user experience analysis', or 'design evaluation'
Add file types or contexts this skill handles, such as 'screenshots', 'prototypes', 'Figma files', or 'user journey maps'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like '분석하고 개선점을 도출합니다' (analyzes and derives improvements) without specifying concrete actions such as heuristic evaluation, usability testing analysis, or accessibility audits. | 1 / 3 |
Completeness | Only provides a weak 'what' (analyzes UX and derives improvements) with no explicit 'when' clause or trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'UX 감사' (UX audit) and '사용자 경험' (user experience), but misses common variations users might say such as 'usability', 'UI review', 'interface analysis', or 'user testing'. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'UX 감사 에이전트' provides some specificity to UX auditing, but '사용자 경험을 분석' is generic enough to potentially overlap with general design review or product analysis skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a role description rather than actionable guidance. It lists what a UX audit agent does but provides no concrete methods, heuristics, evaluation criteria, or workflow for actually conducting UX audits. Claude would not know how to perform these tasks based on this content alone.
Suggestions
Add specific heuristic evaluation frameworks (e.g., Nielsen's 10 heuristics) with concrete criteria and scoring methods
Include a step-by-step workflow for conducting a UX audit with validation checkpoints
Provide an example audit report structure or template showing expected output format
Add concrete examples of common usability issues to identify and how to document them
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is brief and doesn't over-explain concepts Claude knows, but it's so minimal that it lacks substance rather than being efficiently dense with useful information. | 2 / 3 |
Actionability | The skill provides only vague descriptions of tasks ('휴리스틱 평가', '사용성 문제 식별') without any concrete methods, frameworks, checklists, or executable guidance on how to actually perform a UX audit. | 1 / 3 |
Workflow Clarity | No workflow or sequence is provided. The skill lists tasks but doesn't explain how to perform them, in what order, or what validation steps to take when conducting an audit. | 1 / 3 |
Progressive Disclosure | The content is appropriately short and mentions an output location, but provides no references to detailed materials, frameworks, or examples that would help Claude perform the audit effectively. | 2 / 3 |
Total | 6 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- 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.