Content
80%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 concise, well-structured set of testing rules that assumes Claude's competence and gives specific actionable directives. Its main weakness is that it is a principles document rather than a sequenced workflow, so it lacks explicit validation checkpoints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a lean set of terse bullets under clear headers (e.g. 'Assert public behavior, not implementation detail', 'Use `it.each` for small behavior matrices') with no padding or explanation of concepts Claude already knows, matching the score-5 'every token earns its place' anchor. | 5 / 5 |
Actionability | Directives are concrete and specific (keep tests in '*.spec.ts[x]', prefer render-returned queries over 'screen', use direct style-property assertions instead of 'toHaveStyle'), but as an instruction-only rules skill it lacks copy-paste executable code, fitting score-4 'mostly executable guidance with minor gaps' rather than 5. | 4 / 5 |
Workflow Clarity | The content is organized into topical sections but presents principles rather than a sequenced multi-step workflow, and there are no validation checkpoints for the mildly destructive rule 'Delete skipped, commented, or placeholder tests', matching the score-3 anchor of structure present but checkpoints missing. | 3 / 5 |
Progressive Disclosure | The skill is under 50 lines, has no bundle files, and is organized into clear well-labeled sections (Testing Goal, Core Rules, Seam Selection, Fixtures And Assertions, Quick Reference), meeting the guideline that simple skills with no external references can score 5 on well-organized sections alone. | 5 / 5 |
Total | 17 / 20 Passed |