Content
86%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 an exemplary lean, instruction-only skill: every pattern is a specific, non-obvious discipline with concrete examples and paired anti-patterns, and validation is baked into the guidance itself. The only meaningful gap is the absence of a worked assertion example showing good vs. bad practice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~30-line body is lean with zero padding: no basic-concept explanations, and every line ("A passing status-only test is not evidence that the intended artifact or contract is correct") adds non-obvious value; nothing to trim for the 4-anchor. | 5 / 5 |
Actionability | Concrete, executable directives ("Mutation-test critical gates by changing the real source or emitted artifact and proving the assertion turns red", "Exercise every caller path") plus two concrete example scenarios; it falls short of 5 only because no worked example shows an actual good-vs-bad assertion. For an instruction-only skill, the absence of code itself is not penalized. | 4 / 5 |
Workflow Clarity | Validation is the skill's core subject (mutation-test gates, red/green feedback, reproduce working-tree failures locally), and sections are clearly organized; however the Patterns form a parallel checklist rather than an unambiguous single action or sequenced workflow, so the simple-skill 5 exception does not fully apply. No destructive/batch cap applies. | 4 / 5 |
Progressive Disclosure | The skill is under 50 lines, needs no external references (none exist in the bundle), and is organized into clear Context/Patterns/Examples/Anti-Patterns sections — exactly the case the guideline scores 5. | 5 / 5 |
Total | 18 / 20 Passed |