write-ui-tests

Creates UI tests for a GitHub issue and verifies they reproduce the bug. Iterates until tests actually fail (proving they catch the issue). Use when PR lacks tests or tests need to be created for an issue.

Quality

82%

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

81%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.

Highly actionable, well-sequenced content with strong validation and feedback loops. Its main weakness is redundancy — the core 'tests must fail' requirement is repeated across three sections, and supplementary sections could be split out to trim the body.

Suggestions

Consolidate the tests-must-fail guidance: state it once in the BLOCKING REQUIREMENT section and have Step 5 and Output reference it, removing the duplicated troubleshooting lists and the near-identical 'STOP and ask user' messages.

Move the iOS Device Selection section (jq UDID recipes) and possibly Common Patterns into a reference file (e.g., references/advanced.md), keeping the core workflow lean in SKILL.md.

Trim the 'Common mistakes' list in the BLOCKING REQUIREMENT section since the Step 5 table already covers the same failure modes and fixes.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — no concept explanations Claude already knows — but the tests-must-fail mandate is restated three times (BLOCKING REQUIREMENT, Step 5, Output) with overlapping troubleshooting lists and two near-duplicate 'STOP and ask user' messages.	3 / 5
Actionability	Fully executable throughout: copy-paste-ready C# HostApp and NUnit templates with marked placeholders, exact dotnet build commands, the verify-tests-fail pwsh invocation, and runnable jq snippets for iOS device selection.	5 / 5
Workflow Clarity	Five clearly sequenced steps with explicit validation checkpoints (compile check in Step 4, fail-verification script in Step 5), a feedback loop capped at 3 iterations with escalation to the user, and a pre-run checklist.	5 / 5
Progressive Disclosure	Well-organized sections with a clearly labeled References list pointing one level deep to authoritative sources (uitests.instructions.md, UITestCategories.cs, example tests); the Common Patterns and iOS Device Selection sections are peripheral material that could move to a reference file.	4 / 5
	Total	17 / 20 Passed

Description

83%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.

A strong description: concrete capabilities, explicit 'Use when' triggers, and a distinctive fail-verification angle. Gaps are limited — a few missing natural synonyms and no mention of the .NET MAUI context that would sharpen distinctiveness further.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Creates UI tests for a GitHub issue", "verifies they reproduce the bug", "Iterates until tests actually fail (proving they catch the issue)" — but stops short of comprehensive coverage of the workflow (e.g., no mention of the build/run or file-creation aspects).	4 / 5
Completeness	Explicitly answers both: what ("Creates UI tests... verifies they reproduce the bug. Iterates until tests actually fail") and when ("Use when PR lacks tests or tests need to be created for an issue") with concrete trigger conditions.	5 / 5
Trigger Term Quality	Natural phrases like "UI tests", "GitHub issue", "PR lacks tests" match what users would say, but common variations such as "test coverage", "reproduction test", or "write tests for this issue" are missing.	4 / 5
Distinctiveness Conflict Risk	The niche — creating reproduction UI tests tied to GitHub issues with fail-verification — is mostly distinct; only minor overlap risk with a generic test-writing skill.	4 / 5
	Total	17 / 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: dotnet/maui
Path: .github/skills/write-ui-tests/SKILL.md
Commit: 7a5a5d6

Reviewed: 7 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.