Content
85%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 and well-structured with a clear workflow and properly offloaded reference material. Its only weakness is mild verbosity from restating basic mutation-testing concepts and duplicating the step list as both a summary and detailed sections.
Suggestions
Trim the Overview's quoted definition of mutation testing and the 'killed vs lived' explanation; Claude already knows these concepts - keep only the speed-differentiation claim.
Collapse the 'How to use' 7-item summary into the detailed Step 1-7 sections (or vice versa) to remove the parallel restatement of the same sequence.
Move the inline 'fast (analyzes in minutes rather than days)' claim to a single location instead of repeating it across the description and body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with concrete code blocks, but the Overview quotes PIT explaining mutation testing and killed-vs-lived mutants (concepts Claude already knows) and the 'How to use' numbered list previews the Step 1-7 sections, creating redundancy. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready Maven XML, Gradle config, bash commands, and CI YAML with concrete values, satisfying the executable-code anchor. | 3 / 3 |
Workflow Clarity | A clear Step 1-7 sequence pairs with an explicit feedback loop - 'For each surviving mutant, add or strengthen a test until it is killed' - and a worked example showing survivor detection, fix, and re-run, matching the validation-checkpoint anchor. | 3 / 3 |
Progressive Disclosure | The SKILL.md body is an overview that offloads pitfalls to a real, clearly signaled one-level-deep reference (references/pitest-pitfalls.md, verified present), with content appropriately split and easy navigation. | 3 / 3 |
Total | 11 / 12 Passed |