Content
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill covering mutation testing across TypeScript/JavaScript and Python ecosystems with concrete, executable examples and configurations. Its main weaknesses are moderate verbosity (explanatory content Claude doesn't need, like mutation type definitions and score target tables) and a workflow section that lacks explicit validation/error-recovery checkpoints. The content would benefit from trimming generic knowledge and adding error handling guidance.
Suggestions
Remove or significantly trim the 'Core Concept', 'Common Mutation Types', and 'Mutation Score Targets' sections — Claude already understands these concepts and they consume tokens without adding actionable value.
Add explicit validation/error-recovery steps to the workflow, e.g., what to do when Stryker reports errors, how to handle Bun version incompatibility, or how to triage a large number of survived mutants.
Consider extracting the detailed Bun runner configuration and key behaviors into a separate reference file to improve progressive disclosure and keep the main skill leaner.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary content like the 'Core Concept' definitions (Claude knows what mutation testing is), the mutation types table (basic knowledge), and the score targets table which is generic guidance. The Bun runner section's 'Key Behaviors' explanation is somewhat verbose for Claude's level. | 2 / 3 |
Actionability | Provides fully executable installation commands, complete configuration files, runnable CLI commands, and concrete before/after code examples showing weak vs strong tests. Everything is copy-paste ready for both Stryker (Vitest and Bun runners) and mutmut. | 3 / 3 |
Workflow Clarity | The workflow section at the end provides a clear sequence (coverage → mutation testing → check report → fix → re-run), but lacks explicit validation checkpoints or error recovery steps. For instance, there's no guidance on what to do if Stryker fails, if the Bun version is too old, or how to interpret and act on specific report findings systematically. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, and references 'vitest-testing' and 'test-quality-analysis' skills at the end. However, at ~170 lines it includes substantial inline content (common mutation types, score targets, multiple improvement patterns) that could be split into reference files. No bundle files exist to offload detail. | 2 / 3 |
Total | 9 / 12 Passed |