Content
68%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 highly actionable pattern catalog with copy-paste-ready TypeScript/Jest examples covering factories, mocking, and interaction testing. Its weaknesses are padding — a philosophy section and best-practices list that restate concepts Claude already knows, plus a boilerplate When to Use sentence — and an TDD workflow whose verify-at-each-step checkpoints are only implicit.
Suggestions
Cut or compress the 'Testing Philosophy' and 'Best Practices' sections to only project-specific conventions; Claude already knows TDD red-green-refactor and 'test behavior, not implementation', so these ~30 lines are pure token cost.
Delete the filler 'When to Use' sentence ('This skill is applicable to execute the workflow or actions described in the overview.') — it adds no information.
Make the TDD cycle's checkpoints explicit, e.g., '1. Write the failing test, run `npm test <file>` to confirm red; 2. Implement minimal code, re-run to confirm green; 3. Refactor, re-run before committing.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The code sections are lean, but the body spends lines on concepts Claude already knows: the TDD bullets ('Write failing test FIRST / Implement minimal code to pass / Refactor after green'), 'Test behavior, not implementation', and 'Keep tests DRY', then duplicates them in a six-item 'Best Practices' list, plus a pure filler sentence in 'When to Use' ('This skill is applicable to execute the workflow or actions described in the overview.'). This fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') rather than anchor 2, because the padding is confined to a few sections while the majority of the document is tight, executable code — but it is more than 'minor instances', excluding anchor 4. | 3 / 5 |
Actionability | Nearly every section is copy-paste ready executable code: the custom render helper, getMockX factories with typed overrides, jest.mock with factory functions and requireMock access, GraphQL hook mocking with mockReturnValue, fireEvent/waitFor interaction patterns, and concrete npm commands. This matches anchor 5 ('fully executable; copy-paste ready code or commands; specific examples cover the common cases'); the empty it() bodies in the Test Structure section are an intentional skeleton template, not a gap. | 5 / 5 |
Workflow Clarity | The primary workflow (TDD red-green-refactor) is listed as a clear sequence, but the checkpoints are implicit — it never says to run the tests to confirm red before implementing or green before refactoring ('npm test' appears only in a standalone commands section). This fits anchor 3 ('steps listed but validation gaps; sequence present but checkpoints missing or implicit') rather than anchor 4, whose sequence embeds the verification step at each stage. No destructive/batch operations, so no cap applies. | 3 / 5 |
Progressive Disclosure | The body is well organized with clear section headers (Utilities, Factories, Mocking, Structure, Query/Interaction Patterns, Anti-Patterns) and no nested references. It fits anchor 4 ('good structure; most content is appropriately placed; minor organization gaps') — the ~265-line catalog could offload advanced material (e.g., GraphQL mocking patterns) into reference files to keep SKILL.md as a leaner overview, and the 'Integration with Other Skills' section points at other skills by name without paths. Not anchor 5 because there is no clear overview-to-detail split, and not anchor 3 because the structure that exists is genuinely well signaled and navigable. | 4 / 5 |
Total | 15 / 20 Passed |