Content
88%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.
The body is a strong, highly actionable profiling workflow with explicit validation gates and error-recovery loops. Its only real weakness is progressive disclosure: it is a monolithic single file with no accompanying reference bundle despite referencing external skills.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence (no explanations of what profiling or Instruments are), with only minor repetition — the consent gate is restated across the workflow and the error-handling table. | 4 / 5 |
Actionability | It gives fully executable, copy-paste-ready commands throughout — the intent-to-preset table maps user phrasing to exact `xcprof record` invocations, plus concrete `jq` discovery pipelines and analyze/compare commands covering the common cases. | 5 / 5 |
Workflow Clarity | A clear four-step sequence (target → record → analyze → report) with explicit validation checkpoints (`doctor` prereq, the support-matrix honesty gate) and feedback loops for error recovery (re-scope a hang window, re-record with the right preset, add `--dsym`). | 5 / 5 |
Progressive Disclosure | Well-organized sections with clearly signaled one-level-deep pointers to external skills in 'Related', but no bundle files exist and the single ~160-line file inlines detail (comparison workflow, error table, tips) that could be split into reference files. | 4 / 5 |
Total | 18 / 20 Passed |