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

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

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 content with a clear, well-validated workflow and excellent executable examples. The main weakness is redundancy around the 'tests must fail' rationale, which inflates length without adding new information.

Suggestions

Consolidate the repeated 'tests must FAIL to catch the bug' explanation: state the rationale once in the blocking banner and reference it from Step 5 and Output rather than re-deriving it each time.

Merge the bulleted 'Common mistakes that lead to passing tests' (lines 26-31) with the later symptom/cause/fix table (lines 188-194) into a single troubleshooting table to remove duplication.

Move the iOS Device Selection jq snippets and Common Patterns into a separate reference file (e.g. references/advanced-patterns.md) and link to it one level deep, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and commands, but the 'tests must FAIL to catch the bug' rationale is repeated across the blocking banner, Step 5, and the Output section, and the 'common reasons tests pass' list appears both as bullets (lines 26-31) and again as a table (lines 188-194).	3 / 5
Actionability	Fully copy-paste-ready C# for the HostApp page and NUnit test, exact dotnet build commands with paths and flags, the exact pwsh verify-tests-fail.ps1 invocation, and jq UDID-lookup snippets covering the common cases.	5 / 5
Workflow Clarity	Five clearly sequenced steps with an emphatic validation checkpoint (Step 5 CRITICAL), an iterate-then-ask-user feedback loop, a symptom/cause/fix troubleshooting table, and a pre-run checklist.	5 / 5
Progressive Disclosure	No bundle files ship with the skill, but external repo references are clearly signaled in a References section and section headers organize the body well; the iOS Device Selection and Common Patterns blocks are inlined advanced content that could be split into one-level-deep reference files.	4 / 5
	Total	17 / 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.

A strong, specific description that clearly states capabilities and gives an explicit 'Use when' trigger. The only minor gap is keyword synonym coverage, which keeps trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Creates UI tests,' 'verifies they reproduce the bug,' and 'Iterates until tests actually fail' — giving comprehensive coverage rather than just a few actions with gaps.	5 / 5
Completeness	Explicitly answers both 'what' (create, verify, iterate) and 'when' via the concrete 'Use when PR lacks tests or tests need to be created for an issue' trigger clause.	5 / 5
Trigger Term Quality	Natural phrases like 'PR lacks tests,' 'tests need to be created for an issue,' and 'GitHub issue' are present, but it lacks common synonyms (e.g. 'bug report,' 'repro test') or file-type cues that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The niche — UI tests for a GitHub issue that must fail to prove they catch the bug — is clearly distinct with trigger phrases unlikely to fire for unrelated skills.	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: dotnet/maui
Path: .github/skills/write-ui-tests/SKILL.md
Commit: 90afade

Reviewed: ~17 hours 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.