Content
71%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.
A lean, well-structured conceptual skill that gives actionable TDD process guidance with concrete anti-pattern examples. Its main weakness is progressive disclosure: two referenced files (tests.md, mocking.md) are cited but missing from the bundle.
Suggestions
Add the referenced tests.md and mocking.md to the bundle (or inline the essential examples and remove the links) so all signaled references resolve.
Make the red-green verification checkpoint explicit (e.g., 'run the test and confirm it fails before writing implementation') to raise workflow clarity.
Tighten the 'What a good test is' paragraph by leading with the rule and trimming the explanatory rationale.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and assumes Claude's competence — it does not explain what a test or a refactor is — and every section earns its place; a few conceptual passages in 'What a good test is' could be tightened slightly, keeping it just below the lean-and-efficient anchor. | 4 / 5 |
Actionability | Gives concrete process guidance — 'write down seams and confirm with user before writing any test', 'One slice at a time', and a concrete tautological example (expect(add(a,b)).toBe(a+b)) — that is actionable without code; minor gaps in executable detail keep it at 4. | 4 / 5 |
Workflow Clarity | The 'Rules of the loop' section sequences the cycle (red before green, one slice at a time, refactoring deferred to review) with the seam-confirmation checkpoint explicit and red-before-green as an implicit failure check; not a 5 because explicit 'verify the test fails' verification steps are implicit rather than stated. | 4 / 5 |
Progressive Disclosure | Section structure is clean and references are clearly signaled inline, but the body links to [tests.md](tests.md) and [mocking.md](mocking.md) which are not present in the bundle (references/, scripts/, assets/ are absent), so the promised detail is unreachable — a navigation gap that caps this at 'some structure, references not fully resolvable'. | 3 / 5 |
Total | 15 / 20 Passed |