Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable with a well-sequenced, validation-driven workflow, but it carries redundant fail-mandate restatements and inline reference-style sections (iOS device selection, common patterns) that keep it from fully lean.
Suggestions
Collapse the repeated 'tests must FAIL' guidance into a single authoritative block and reference it from Step 5 and the Output section instead of restating it.
Merge the 'Common mistakes that lead to passing tests' list and the 'Common reasons tests pass when they shouldn't' table into one diagnostics reference to remove duplication.
Move the iOS Device Selection jq recipes and the Common Patterns code samples into a bundled reference file, keeping SKILL.md as a lean overview that links to them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient and free of concept-padding, but the 'tests must FAIL' mandate is restated across the BLOCKING REQUIREMENT, Step 5, and Output sections, and the 'common reasons tests pass' guidance appears twice as both a list and a table — it could be tightened. | 2 / 3 |
Actionability | Provides fully executable C# examples for both the HostApp page and NUnit test, exact file paths, and copy-paste `dotnet build` and `pwsh …verify-tests-fail.ps1` commands, matching the score-3 anchor. | 3 / 3 |
Workflow Clarity | A clearly sequenced 5-step workflow with an explicit validation checkpoint (Step 5, 'CRITICAL'), a numbered failure/feedback loop, and a Pre-Run Checklist — exactly the score-3 pattern. | 3 / 3 |
Progressive Disclosure | References to repo files (.github/instructions/uitests.instructions.md, UITestCategories.cs) are one-level and well-signaled, but no bundle files exist and inline sections like iOS Device Selection and Common Patterns could be split into separate reference files. | 2 / 3 |
Total | 10 / 12 Passed |