rebalance-ui-test-categories

Rebalances a UI-test umbrella category into additive method-level CI shards using historical Azure DevOps test durations.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.github/skills/rebalance-ui-test-categories/SKILL.md

Quality

Content

96%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 content is lean, highly actionable, and presents a well-sequenced workflow with explicit validation and failure checkpoints; progressive disclosure is good but relies on inline script references rather than explicit pointer files.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it states rules and parameters without explaining what NUnit, Azure DevOps, or CI sharding are; every line earns its place.	5 / 5
Actionability	It provides fully executable, copy-paste-ready PowerShell invocations with real flags (-Mode All, -TargetMinutes, -BuildId, -UnmeasuredTestPolicy) plus separate Gather/Plan/Apply command examples covering common cases.	5 / 5
Workflow Clarity	A clear sequence (All-in-one or Gather→Plan→Apply) is given with explicit validation checkpoints — the planner 'fails when active source tests have no historical sample', users must 'Review the JSON report's projectedShardMinutes...', and the apply step performs plan-to-source validation.	5 / 5
Progressive Disclosure	The body is a concise overview that points to a real bundled executable in scripts/Rebalance-UITestCategories.ps1 (confirmed present) with well-organized Rules and Commands sections; it stops short of 5 because references are inline command paths rather than an explicit 'See X.md for details' one-level-deep file structure.	4 / 5
	Total	19 / 20 Passed

Description

58%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 and clearly distinct within its niche, but it omits any 'when to use' trigger guidance, which caps completeness and leaves trigger-term quality mid-range.

Suggestions

Append an explicit 'Use when...' clause naming concrete trigger situations, e.g. 'Use when a maui-pr-uitests category needs splitting into duration-bounded CI shards.'

Add natural-language trigger synonyms users would actually say (e.g. 'split UI tests', 'balance test shards', 'UITestCategories rebalance') to broaden trigger-term coverage.

Mention the key NUnit attribute trigger (ShardedTestCategory / UITestCategories) so the description surfaces the terms users reference.

Dimension	Reasoning	Score
Specificity	"Rebalances a UI-test umbrella category into additive method-level CI shards using historical Azure DevOps test durations" names the domain plus concrete actions (rebalance, shard) and a specific mechanism; it falls short of 5 only because it lists one core action rather than multiple distinct ones.	4 / 5
Completeness	It gives a clear 'what' but contains no 'Use when...' or equivalent trigger guidance; per the rubric, a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant niche terms ("UI-test", "CI shards", "Azure DevOps test durations") are present but lean technical and omit common natural variations or synonyms a user might say, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The highly specific UI-test-sharding niche gives it a clear distinct identity with minimal overlap risk; it does not reach 5 because the description lacks explicit distinct trigger phrases.	4 / 5
	Total	14 / 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/rebalance-ui-test-categories/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.