Content
70%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 delivers a clear, well-sequenced TDD workflow with explicit validation checkpoints and largely executable code examples. Its weaknesses are verbosity from generic testing best-practice content Claude already knows, and a lack of progressive disclosure — everything is inlined in a single long file with no reference files.
Suggestions
Trim or remove the '最佳實務', '成功指標', and '常見測試錯誤避免' sections, which restate general testing knowledge Claude already has.
Move the detailed mock patterns (Supabase/Redis/OpenAI) and CI/CD config into separate reference files under references/ and link to them from the main body to enable progressive disclosure.
Fill in the placeholder test bodies ('// 測試實作', '// 實作在此') with concrete assertions so all code examples are fully executable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The actionable code examples and workflow steps are efficient, but generic sections ('最佳實務', '成功指標', '常見測試錯誤避免') restate testing knowledge Claude already has and could be trimmed. | 3 / 5 |
Actionability | Provides mostly executable, copy-paste-ready examples (Jest/Vitest, Playwright E2E, Supabase/Redis/OpenAI mocks, coverage config), though a few test bodies are placeholders ('// 測試實作', '// 實作在此'). | 4 / 5 |
Workflow Clarity | The 7-step TDD workflow is clearly sequenced with explicit validation checkpoints — Step 3 'tests should fail', Step 5 'tests now should pass', Step 7 'verify 80%+ coverage' — forming a complete feedback loop. | 5 / 5 |
Progressive Disclosure | Sections are well-organized with clear headers, but the ~410-line document is fully monolithic with no bundle files and no external references; content like mock patterns and CI config that could live in separate files is inlined. | 3 / 5 |
Total | 15 / 20 Passed |