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.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete code examples and review flags for all 10 heuristics, and the audit workflow is well sequenced. It is let down by verbosity (restating known heuristic definitions) and by keeping all detail inline in a single large file rather than offloading it to reference files.

Suggestions

Drop or condense the 'Definition' + 'Key Takeaway' pair for each heuristic into a single line; Claude already knows Nielsen's heuristics, so lead with the code-review application instead.

Move the per-heuristic GOOD/BAD examples and review flags into reference files (e.g. references/heuristics.md) and keep SKILL.md as overview + Audit Checklist + Issue Log Format, with clearly signaled one-level-deep links.

Add an explicit verification checkpoint to the audit workflow (e.g. cross-check each finding against the Audit Checklist and confirm every Critical/Major has a Location and Recommendation before finalizing the summary table).

Dimension	Reasoning	Score
Conciseness	The ~790-line body restates Nielsen's heuristic definitions and adds a redundant 'Key Takeaway' that rephrases each definition, explaining concepts Claude already knows; the code-review application is valuable but the per-heuristic framing could be tightened.	3 / 5
Actionability	Every heuristic ships concrete GOOD/BAD HTML snippets plus specific attributes to check (data-disable-with, aria-busy, data-turbo-confirm) and explicit review-flag checklists, giving copy-paste-ready audit guidance for common cases.	5 / 5
Workflow Clarity	A clear sequence is prescribed — start with the Audit Checklist, consult detailed sections, then emit the Issue Log Format (summary table, severity definitions, findings, priority recommendations) — though explicit validation/verification checkpoints are implicit rather than stated.	4 / 5
Progressive Disclosure	Internal sectioning is good (overview → quick-scan checklist → detailed per-heuristic sections), but the skill is a monolithic ~790-line file with no bundle/reference files, so the bulk of detailed examples is inlined rather than split one level deep.	3 / 5
	Total	15 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 is strong: it states concrete capabilities and outputs, gives an explicit 'Use when' trigger clause, and occupies a clear niche. The only minor gap is trigger-term synonym coverage in the description text itself.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and outputs — 'Audit UI implementations', 'Produces a structured issue log with severity ratings, heuristic mappings, and remediation guidance' — giving comprehensive coverage rather than a single generic verb.	5 / 5
Completeness	Explicitly answers both what (audit UI against Nielsen's 10 heuristics, produce a structured issue log) and when (heuristic evaluations, UI code review for usability compliance, auditing existing interfaces) with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when conducting heuristic evaluations, reviewing UI code for usability compliance, or auditing existing interfaces' clause supplies natural phrases a user would say, but omits common synonyms like 'usability audit' or 'ui audit' that appear only in metadata.	4 / 5
Distinctiveness Conflict Risk	The Nielsen heuristic-evaluation/audit niche has distinct triggers that clearly separate it from companion skills like laws-of-ux, minimizing wrong-skill activation.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: RoleModel/rolemodel-skills
Path: skills/usability-heuristics/SKILL.md
Commit: 6d600e9

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.