lean-ux

Apply lean thinking to UX: hypothesis-driven design, collaborative sketching, and rapid experiments instead of heavy deliverables. Use when the user mentions "Lean UX", "design hypothesis", "outcome over output", "design studio method", "assumption mapping", "lightweight research", "too much design documentation", or "get the team designing together". Also trigger when reducing design-documentation overhead, getting cross-functional teams to co-design, or running fast usability experiments. Covers hypothesis statements, MVPs for UX, and cross-functional collaboration. For Build-Measure-Learn, see lean-startup. For usability audits, see ux-heuristics.

Quality

86%

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

78%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 well-structured, actionable, and exemplifies progressive disclosure with a clear overview pointing to six real reference files. The main improvement opportunity is tightening the repeated "Core concept"/"Why it works" explanatory blocks to lift conciseness toward fully lean.

Suggestions

Trim or merge the "Core concept" and "Why it works" paragraphs under each Framework step into a single concise line so each token earns its place, lifting conciseness toward score 5.

Add an explicit validate/retry checkpoint to the Scoring or Framework flow (e.g. "after diagnosing failed rows, re-score once fixes are applied") to give the workflow a clearer feedback loop.

For actionability, surface one copy-paste-ready artifact inline (e.g. a fillable hypothesis-statement block) so the most common action is executable without opening a reference.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence (no padding about what UX or a hypothesis is), but the repeated "Core concept" / "Why it works" prose under each framework step adds explanatory weight that could be trimmed, fitting score 4 rather than the fully lean score 5.	4 / 5
Actionability	Provides concrete, usable guidance — the standard hypothesis format ("We believe [outcome]..."), scoring bands, product-application tables with examples, and a diagnostic table — but some steps rely on instructional framing rather than copy-paste-ready artifacts, leaving minor gaps versus score 5.	4 / 5
Workflow Clarity	A clearly sequenced six-step Framework plus an eight-row Quick Diagnostic with explicit score bands and "If No / Action" guidance gives a clear sequence with most checkpoints present; it lacks explicit validate-then-retry feedback loops, but the skill is non-destructive so no cap applies, fitting score 4.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview with well-signaled, one-level-deep references (e.g. "See references/hypothesis-canvas.md ... the risk/uncertainty prioritization matrix") to six verified reference files, with content appropriately split and easy to navigate, matching the score-5 anchor.	5 / 5
	Total	17 / 20 Passed

Description

95%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 specific, trigger-rich, and complete, with explicit what/when guidance and disambiguation against neighboring skills. It is among the stronger example descriptions; the only minor gap is that the action list is not exhaustively comprehensive.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("hypothesis-driven design, collaborative sketching, and rapid experiments", "Covers hypothesis statements, MVPs for UX, and cross-functional collaboration") with only minor coverage gaps, fitting the score-4 anchor rather than the comprehensive score-5 list.	4 / 5
Completeness	Explicitly answers both what (the listed practices) and when via "Use when..." / "Also trigger when..." clauses with concrete trigger phrases, satisfying the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural-language triggers including synonyms and idioms users would actually say ("Lean UX", "outcome over output", "design studio method", "too much design documentation", "get the team designing together"), matching the score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	Clear Lean UX niche with distinct triggers and explicit disambiguation cross-references ("For Build-Measure-Learn, see lean-startup. For usability audits, see ux-heuristics"), minimizing conflict risk per the score-5 anchor.	5 / 5
	Total	19 / 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: lean-ux/SKILL.md
Commit: c172996

Reviewed: 3 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.