ai-ux-enhancements
Automated UX review rules optimized for AI-driven design evaluations, addressing gaps in usability and user empowerment. Complementary to laws-of-ux skill, focusing on efficiency, control, cognitive workload, learnability, and personalization.
36
33%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ai-ux-enhancements/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies its domain and differentiates itself from a related skill, but it reads more like a summary of coverage areas than an actionable skill description. It critically lacks explicit trigger guidance ('Use when...') and concrete actions, making it difficult for Claude to know when to select this skill. The language leans toward abstract categorization rather than practical, user-facing trigger terms.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases, e.g., 'Use when the user asks for a UX review, usability audit, design critique, or wants to evaluate an interface for efficiency and learnability.'
Replace abstract framing with concrete actions, e.g., 'Evaluates UI designs for usability issues, flags cognitive overload risks, checks for user control and efficiency, and recommends improvements for learnability and personalization.'
Include common user-facing keywords and file/artifact types users might mention, such as 'wireframes', 'mockups', 'UI designs', 'design feedback', or 'heuristic evaluation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (UX review) and lists some focus areas (efficiency, control, cognitive workload, learnability, personalization), but doesn't describe concrete actions like 'evaluate', 'generate reports', or 'audit interfaces'. The language is more about what the skill covers than what it does. | 2 / 3 |
Completeness | Describes what the skill covers at a high level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. The description only implies context through its relationship to 'laws-of-ux skill', which is insufficient. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'UX review', 'usability', 'cognitive workload', 'learnability', and 'personalization', but misses common user phrases like 'user experience audit', 'UI review', 'design feedback', 'heuristic evaluation', or 'accessibility'. The term 'AI-driven design evaluations' is somewhat jargon-heavy. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of being 'complementary to laws-of-ux skill' helps differentiate it from that specific skill, and the focus areas (efficiency, control, cognitive workload, learnability, personalization) provide some niche definition. However, the broad term 'UX review' could still overlap with other design-related skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a well-structured and comprehensive set of UX review heuristics with clear categorization and concrete fail messages. However, it is significantly over-verbose for a skill file — the metadata preamble, background context, and explanatory framing waste tokens on information Claude doesn't need. The actionability is moderate: checks are described clearly but lack executable implementations, and the workflow for actually conducting a review is underspecified.
Suggestions
Remove the metadata block (Version, Date, Purpose paragraph) and Background & Scope section — Claude doesn't need this context. Start directly with the rules.
Add a concise step-by-step workflow at the top: e.g., '1. Run accessibility checks (Rules 9, 12) → 2. Analyze DOM structure (Rules 4, 6, 8) → 3. Review interaction patterns (Rules 1, 3) → 4. Compile findings into structured report'
Trim 'Automation ideas' to single-line tool references rather than multi-clause explanations (e.g., 'Tools: axe-core aria checks, DOM scan for aria-keyshortcuts' instead of full sentences).
Consider splitting the 12 rules into a separate reference file and keeping SKILL.md as a concise overview with the workflow and priority order, linking to the full rule definitions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is excessively verbose with unnecessary metadata (version, date, purpose paragraph), background explanations Claude doesn't need, and repeated framing about what the rules complement. The 'Background & Scope' section explains context Claude could infer. Many rules include 'Automation ideas' that are more educational than actionable for Claude's actual task. | 1 / 3 |
Actionability | Each rule provides a concrete check description, fail message examples, and automation ideas, which gives Claude reasonable guidance on what to look for. However, there is no executable code, no concrete command-line invocations, and the 'automation ideas' are suggestions rather than copy-paste-ready implementations. The guidance is specific but not fully executable. | 2 / 3 |
Workflow Clarity | The Implementation Guidance section provides a priority order and scoring suggestion, which gives some workflow structure. However, there's no clear step-by-step review process, no validation checkpoints, and no feedback loop for handling findings or re-checking after fixes. For a review skill involving systematic evaluation, the workflow is underspecified. | 2 / 3 |
Progressive Disclosure | The content is organized into clear thematic sections (Efficiency, Empowerment, Cognitive Workload, etc.) with numbered rules, which aids navigation. However, the entire skill is monolithic — all 12 rules with full detail are inline. Given the length (~150+ lines of substantive content), some rules or the automation tooling guidance could be split into referenced files. No bundle files exist to support this. | 2 / 3 |
Total | 7 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- RoleModel/rolemodel-skills
- Commit
72e8136
- 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.