CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

71%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/usability-heuristics/SKILL.md
SKILL.md
Quality
Evals
Security

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 includes domain-specific terminology that practitioners would naturally use.

DimensionReasoningScore

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 (conducting heuristic evaluations, reviewing UI code for usability compliance, auditing existing interfaces) with an explicit 'Use when' clause.

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 combining Nielsen's heuristics, usability auditing, and structured issue logging. Unlikely to conflict with general UI or code review skills due to the specific methodology (Nielsen's 10 heuristics) and output format (severity ratings, heuristic mappings).

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.

This skill is extremely thorough and actionable, providing excellent concrete HTML examples and a well-defined output format for heuristic evaluations. However, it is massively over-length for a SKILL.md, essentially embedding an entire textbook chapter on Nielsen's heuristics that Claude already knows. The content would benefit enormously from splitting the detailed per-heuristic guidance into separate files and keeping only the audit methodology, checklist, and output format in the main skill.

Suggestions

Extract the 10 detailed heuristic sections (H1-H10) into a separate HEURISTICS_REFERENCE.md file, keeping only the Audit Checklist table and Issue Log Format in SKILL.md with a clear reference link.

Remove heuristic definitions and 'Key Takeaway' paragraphs — Claude knows Nielsen's heuristics. Keep only the code-specific 'What to look for' flags and examples that are project-specific (e.g., Stimulus controllers, Turbo patterns).

Add an explicit numbered audit workflow with checkpoints, e.g.: 1) Identify scope/files, 2) Run through checklist, 3) Document findings in log format, 4) Verify each finding has evidence + recommendation, 5) Generate priority summary.

Move the Cross-Cutting Concerns and Companion Skills sections into a brief inline note or separate file — the clustering advice is useful but adds significant length for guidance Claude can infer.

DimensionReasoningScore

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, review flags, and cross-references — most of which is textbook UX knowledge Claude possesses. The severity definitions, cross-cutting concerns section, and companion skills section add further bulk. This could be reduced to the audit checklist table, the issue log format, and brief code-pattern flags.

1 / 3

Actionability

Highly actionable with concrete, copy-paste-ready HTML code examples for every heuristic (both good and bad patterns), a specific structured output format (issue log with markdown templates), explicit review flags for each heuristic, and a clear audit checklist table. Claude would know exactly what to produce and what to look for.

3 / 3

Workflow Clarity

The audit workflow is implied but not explicitly sequenced with validation checkpoints. The overview says 'start with the Audit Checklist to identify which heuristics are most relevant, then refer to the detailed sections' and 'always produce findings in the Issue Log Format,' but there's no numbered step-by-step audit process with explicit checkpoints like 'verify all heuristics checked' or 'validate finding completeness before finalizing report.' The output format sections (summary table, finding format, audit completion) provide good structure for the deliverable but not for the process itself.

2 / 3

Progressive Disclosure

Monolithic wall of text with no bundle files to offload content to. All 10 heuristics with full examples, definitions, and review flags are inline in a single massive file. The skill references companion skills (laws-of-ux, bem-structure, optics-context) but doesn't split its own content. The detailed per-heuristic sections, cross-cutting concerns, and examples could easily be in separate referenced files, keeping SKILL.md as a lean overview with the checklist and output format.

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.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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

Repository
RoleModel/rolemodel-skills
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.