ux-heuristics

Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "users are confused", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "is this easy to use". Also trigger when reviewing a design for usability issues, improving form-completion rates, or evaluating information architecture and navigation. Covers Krug's laws, Nielsen's 10 heuristics, severity ratings, dark-pattern recognition, and accessibility. For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology.

Quality

94%

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

85%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.

A well-structured, highly actionable skill body that uses progressive disclosure effectively, pushing detailed material into one-level-deep reference files while keeping concrete tables, copy patterns, and a scoring workflow inline. The main weakness is mild verbosity in re-explaining foundational heuristic concepts Claude already knows.

Suggestions

Trim the per-heuristic prose under Nielsen's 10 heuristics to the unique copy patterns and ethical-boundary notes; Claude already knows the heuristic definitions.

Add an explicit validate/iterate loop to the audit workflow (e.g., 're-run the Quick Diagnostic after applying fixes to confirm the score improved').

Consider moving the 15-row Common Mistakes table into a reference file to further lean out the main body, since it overlaps with the Nielsen heuristics coverage.

Dimension	Reasoning	Score
Conciseness	The body is dense and useful but runs ~230 lines with some explanation that leans on Claude's existing knowledge (e.g., re-explaining what each Nielsen heuristic means, 'Users don't read, they scan' framing) that could be trimmed while preserving the actionable tables.	4 / 5
Actionability	Highly actionable: concrete before/after copy patterns, severity-rating table, a 10-row Quick Diagnostic with specific 'If No / Action' columns, and a Common Mistakes table with concrete fixes — instruction-only but specific and executable throughout.	5 / 5
Workflow Clarity	The Scoring section gives a clear, sequenced audit workflow (audit -> rate severity -> score from Quick Diagnostic -> report score + fixes), and the Quick Diagnostic acts as a validation checkpoint, though there is no explicit validate->fix->re-check loop for the audit output.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview that delegates depth to seven well-signaled, one-level-deep reference files (krug-principles, nielsen-heuristics, audit-template, wcag-checklist, cultural-ux, heuristic-conflicts, dark-patterns), all verified to exist with no nested second-level references, making navigation easy.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

This is an exemplary description: it concisely states what the skill does and when to use it with a rich set of natural trigger phrases, and it actively disambiguates from neighboring skills. It uses correct third-person voice throughout and earns full marks on every dimension.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions and capabilities ('heuristic analysis', 'severity ratings', 'dark-pattern recognition', 'accessibility', 'evaluating information architecture and navigation'), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Clearly answers 'what' (evaluate and improve interface usability via heuristic analysis covering Krug, Nielsen, severity, dark patterns, accessibility) and 'when' with explicit 'Use when...' and 'Also trigger when...' clauses containing concrete trigger phrases.	5 / 5
Trigger Term Quality	Extensive natural trigger phrases users would actually say ('usability audit', 'users are confused', 'navigation problems', 'is this easy to use', 'form usability') plus framework names like 'Nielsen heuristics' and 'cognitive walkthrough'.	5 / 5
Distinctiveness Conflict Risk	The usability/heuristic niche is clearly scoped and distinct, and it explicitly disambiguates from adjacent skills ('For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology.'), minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: wondelai/skills
Path: ux-heuristics/SKILL.md
Commit: c172996

Reviewed: 14 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.