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.
60
71%
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/usability-heuristics/SKILL.mdQuality
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 heuristics), concrete outputs (structured issue log with severity ratings, heuristic mappings, remediation guidance), and explicit trigger conditions. It uses proper third-person voice throughout and occupies a well-defined niche that would be easily distinguishable from other UI-related 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. These are detailed, concrete outputs. | 3 / 3 |
Completeness | Clearly answers both what ('Audit UI implementations against Nielsen's 10 Usability Heuristics... Produces a structured issue log with severity ratings, heuristic mappings, and remediation guidance') and when ('Use when conducting heuristic evaluations, reviewing UI code for usability compliance, or auditing existing interfaces'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'heuristic evaluation', 'usability', 'UI code', 'auditing', 'Nielsen's 10 Usability Heuristics', 'usability compliance', 'interfaces'. These cover the domain well with terms practitioners would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: Nielsen's heuristics-based UI auditing is a very specific methodology. The combination of 'Nielsen's 10 Usability Heuristics', 'heuristic evaluation', and 'severity ratings' makes this unlikely to conflict with general UI or code review skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%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 output formats, code examples, and review checklists, making it very usable for conducting heuristic evaluations. However, it is severely over-long and verbose, explaining heuristic definitions and concepts Claude already knows in extensive detail. The content would benefit enormously from splitting the detailed heuristic reference material into a separate file and keeping only the audit methodology, checklist, and output format in the main SKILL.md.
Suggestions
Move the detailed 10 heuristic sections (definitions, examples, review flags) into a separate HEURISTICS_REFERENCE.md file, keeping only the audit checklist table and brief heuristic summaries in SKILL.md.
Remove heuristic definitions and 'Key Takeaway' lines — Claude already knows Nielsen's heuristics. Focus only on code-specific review flags and the audit-specific patterns that add novel value.
Add an explicit step-by-step audit workflow at the top (e.g., 1. Identify scope/files, 2. Scan with checklist, 3. Document findings in issue log format, 4. Cross-check cross-cutting concerns, 5. Produce priority recommendations) with clear sequencing.
Trim the good/bad HTML examples to shorter, more focused snippets — many are 10-20 lines when 5-8 lines would convey the same point.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. Extensively explains Nielsen's heuristics, which Claude already knows well. Each heuristic includes full definitions, key takeaways, detailed 'what to look for' lists, lengthy good/bad HTML examples, and review flag lists — most of which Claude could generate from its training knowledge. The severity definitions, cross-cutting concerns, and companion skills sections add further bulk. This could be reduced to the audit checklist table, the issue log format, and brief notes on cross-references. | 1 / 3 |
Actionability | Highly actionable with a concrete issue log format (summary table, finding template with severity/location/evidence/recommendation fields), a detailed audit checklist table mapping checks to heuristics, specific HTML code examples for both good and bad patterns, and explicit review flags for each heuristic. The output format is copy-paste ready and the audit workflow is clearly defined. | 3 / 3 |
Workflow Clarity | The audit workflow is implicitly structured — start with the checklist, evaluate each heuristic, produce findings in the issue log format, end with priority recommendations. However, there's no explicit step-by-step audit process with validation checkpoints. The cross-cutting concerns section suggests grouping related findings but doesn't provide a clear sequenced workflow for conducting the audit itself. For an audit skill involving structured reporting, a clearer step-by-step process would be expected. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files to offload content. All 10 heuristics are fully detailed inline with lengthy examples, review flags, and cross-references. The detailed heuristic sections (which constitute the bulk of the document) could easily be split into a separate reference file, with the SKILL.md retaining only the audit checklist, issue log format, and cross-cutting concerns. References to companion skills exist but the skill's own content is not appropriately split. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (798 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
72e8136
Table of Contents
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.