Content
61%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 well-organized, example-rich knowledge skill whose paired BAD/GOOD snippets and coverage commands are genuinely actionable. Its weaknesses are redundancy (repeated mocking guidance, textbook FIRST/AAA explanations) and the absence of a sequenced analysis workflow with validation checkpoints.
Suggestions
Add a short ordered workflow (e.g. 1. run coverage commands, 2. scan for each listed smell using the detection heuristics, 3. verify suspected flakiness by re-running, 4. report findings per dimension) so the analysis process is sequenced with checkpoints.
Merge the duplicated 'Mocking Too Much' section into the 'Overmocking' section and trim the FIRST and AAA checklists to one-line reminders, since Claude already knows these textbook concepts.
Move the extended smell catalog and coverage-tool details into a references/ file (e.g. SMELLS.md) linked from a concise overview in SKILL.md to improve both conciseness and progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Sections like the FIRST principles checklist and the AAA pattern restate concepts Claude already knows, and the "Mocking Too Much" section largely repeats the earlier "Overmocking" section's guidance. It is mostly efficient with concrete value in the code examples, matching the 3 anchor (some unnecessary explanation that could be tightened) rather than 4, where only minor trimming would be needed. | 3 / 5 |
Actionability | Runnable commands ("bun test --coverage --coverage.thresholds.lines=80", "uv run pytest --cov --cov-report=html"), paired BAD/GOOD code examples, and concrete detection heuristics ("More than 3-4 mocks") give mostly executable guidance. The code snippets are illustrative rather than complete (e.g. `calculateTotal` is undefined), which keeps it at 4 rather than 5. | 4 / 5 |
Workflow Clarity | The body offers dimensions, checklists, and tool commands but never sequences them into an analysis workflow (e.g. run coverage → scan for each smell → report findings), and there are no validation checkpoints confirming a smell before recommending a fix. This matches the 3 anchor (elements present but sequence/checkpoints implicit) rather than 4, which requires a clear ordered process; the destructive-operation cap is not triggered since this is a read-only analysis skill. | 3 / 5 |
Progressive Disclosure | No bundle files exist, and the ~185-line body is well-organized with clear section headers (smells, tools, checklists, anti-patterns) and one-level "See Also" pointers to related skills. It sits at 4 rather than 5 because the body exceeds the simple-skill threshold and some material (e.g. the extended smell catalog or coverage tooling details) could live in reference files, leaving minor organization gaps. | 4 / 5 |
Total | 14 / 20 Passed |