Content
78%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A highly actionable, well-structured test-runner skill with excellent executable commands and a clear decision tree. Its main weaknesses are repetition that could be tightened and a lack of progressive disclosure — everything lives in one long SKILL.md with no reference files.
Suggestions
Extract the error quick-reference table and 'Common Failure Patterns' catalog into a references/ file (e.g. failures.md) and link to it from SKILL.md to improve progressive disclosure.
Factor the repeated booted-simulator UDID lookup into a single snippet or script (e.g. scripts/booted_udid.sh) and reuse it instead of inlining the command three times.
Add an explicit post-run validation checkpoint (e.g. 'parse the summary; if failed > 0, export attachments and analyze before reporting') to turn the current front-loaded checks into a full validate→fix→retry loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is code-first and lean, assuming Claude's competence without explaining XCUITest fundamentals, but the booted-simulator UDID command is repeated three times and several -scheme/-destination blocks could be DRYed. | 4 / 5 |
Actionability | Provides fully executable, copy-paste-ready xcodebuild and xcresulttool commands with real flags, plus an error quick-reference table and concrete failure diagnoses covering the common cases. | 5 / 5 |
Workflow Clarity | Mandatory first steps and a decision tree give a clear sequenced flow with front-loaded checkpoints, but validation is implicit after test runs rather than a strict validate→fix→retry feedback loop. | 4 / 5 |
Progressive Disclosure | Section headers organize the ~300-line body well, but all content — including the error quick-reference table and failure-pattern catalog that would suit separate reference files — is inlined with no bundle files or one-level-deep references. | 3 / 5 |
Total | 16 / 20 Passed |