usability-heuristics
Audit UI implementations against Nielsen's 10 Usability Heuristics for User Interface Design. Produces a structured issue log with severity ratings, heuristic mappings, and remediation guidance. Use when conducting heuristic evaluations, reviewing UI code for usability compliance, or auditing existing interfaces.
82
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that clearly defines a specific methodology (Nielsen's 10 Usability Heuristics), concrete outputs (structured issue log with severity ratings, heuristic mappings, remediation guidance), and explicit trigger conditions. It uses proper third-person voice and occupies a well-defined niche that distinguishes it from general UI review or accessibility skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: auditing UI implementations against Nielsen's heuristics, producing a structured issue log with severity ratings, heuristic mappings, and remediation guidance. | 3 / 3 |
Completeness | Clearly answers both what (audit UI against Nielsen's heuristics, produce structured issue log with severity ratings and remediation guidance) and when (explicit 'Use when' clause covering heuristic evaluations, reviewing UI code for usability, or auditing interfaces). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'heuristic evaluation', 'usability', 'UI code', 'audit', 'Nielsen', 'usability compliance', 'interfaces'. These cover the domain well and match how practitioners talk about this work. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: specifically scoped to Nielsen's 10 Usability Heuristics and structured usability audits. Unlikely to conflict with general UI review, accessibility, or code review skills due to the specific methodology and output format mentioned. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent concrete examples, a well-defined audit workflow, and a clear structured output format. However, it is severely over-length — the detailed treatment of all 10 Nielsen heuristics (which Claude already knows) inflates the token cost enormously. The content would be far more effective as a concise SKILL.md with the audit methodology and output format, pointing to a separate reference file for the per-heuristic details.
Suggestions
Move the detailed per-heuristic sections (H1-H10 with examples) into a separate HEURISTICS_REFERENCE.md file, keeping only the audit checklist table, issue log format, and cross-cutting concerns in SKILL.md
Remove the 'Definition' and 'Key Takeaway' subsections from each heuristic — Claude already knows Nielsen's heuristics; focus only on the code-specific 'What to look for' and examples
Trim the good/bad code examples to one concise pair per heuristic rather than extended blocks with explanatory paragraphs
Remove the Keywords line and the explanatory Overview paragraph about what heuristic evaluation is — this is background knowledge Claude possesses
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~600+ lines. It explains Nielsen's heuristics in detail — concepts Claude already knows well. Each heuristic includes definition, key takeaway, what to look for, good/bad examples, review flags, and cross-references, resulting in massive redundancy. The definitions and key takeaways are textbook knowledge that doesn't need restating. | 1 / 3 |
Actionability | The skill provides fully concrete, executable HTML code examples for every heuristic — both good and bad patterns. The issue log format is copy-paste ready with specific markdown templates, severity definitions, and a structured finding format. The audit checklist maps each heuristic to specific code attributes to look for. | 3 / 3 |
Workflow Clarity | The audit workflow is clearly sequenced: start with the summary table, use the audit checklist to scan, produce findings in the structured format, and end with a prioritized recommendations section. The severity levels provide clear triage guidance, and the cross-cutting concerns section explains how to group related findings rather than duplicating them. | 3 / 3 |
Progressive Disclosure | The skill references companion skills (laws-of-ux, bem-structure, optics-context) appropriately, but the main file is monolithic — all 10 heuristics with full examples are inline rather than being split into a reference file. The audit checklist table and issue log format could serve as the SKILL.md content, with detailed heuristic guidance in a separate reference document. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (806 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 8 / 11 Passed | |
- Repository
- RoleModel/rolemodel-skills
- Commit
097ad6b
- 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.