Content
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides strong, actionable examples with clear bad/good code comparisons that make test smells immediately recognizable. Its main weaknesses are the lack of a structured analysis workflow (how to systematically review test quality) and some redundancy between sections. The content would benefit from a clear step-by-step process for conducting a test quality review rather than being primarily a reference catalog.
Suggestions
Add a structured analysis workflow section at the top (e.g., 'Step 1: Run coverage and check thresholds → Step 2: Scan for overmocking → Step 3: Check assertion quality → Step 4: Identify flaky patterns') with explicit validation checkpoints.
Remove the 'Core Dimensions' bullet list which states concepts Claude already knows, and consolidate the 'Mocking Too Much' anti-pattern with the earlier 'Overmocking' section to eliminate redundancy.
Consider splitting the checklists into a separate reference file (e.g., CHECKLISTS.md) to keep the main skill focused on the analysis process.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of code examples, but some sections are slightly redundant (e.g., 'Mocking Too Much' in anti-patterns repeats the overmocking section). The 'Core Dimensions' list at the top is somewhat generic knowledge Claude already possesses. Could be tightened. | 2 / 3 |
Actionability | Provides fully executable code examples for every smell and anti-pattern with clear bad/good comparisons. Includes concrete CLI commands for coverage tools, specific threshold values, and copy-paste ready test patterns in both TypeScript and Python. | 3 / 3 |
Workflow Clarity | The skill provides checklists and categorized smells but lacks a clear sequential workflow for how to actually perform a test quality analysis. There's no explicit process like 'Step 1: Run coverage, Step 2: Scan for smells, Step 3: Check assertions' with validation checkpoints. For an analysis task, a structured review workflow with feedback loops would strengthen this. | 2 / 3 |
Progressive Disclosure | The 'See Also' section references related skills which is good, but the main content is a long monolithic document. Some sections (like the full code review checklist and best practices checklist) could be split into separate reference files. No bundle files exist to support progressive disclosure. | 2 / 3 |
Total | 9 / 12 Passed |