Content
62%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured TDD workflow skill with clear sequencing and good anti-pattern guidance. Its main weaknesses are the lack of concrete, executable code examples (no actual test/implementation shown) and some verbosity in the philosophy and anti-pattern sections that explain concepts Claude already knows. The references to supporting files are well-placed but unverifiable without bundle files.
Suggestions
Add a concrete, executable code example showing one full RED→GREEN→REFACTOR cycle (e.g., a simple function with a real test in a specific language/framework) to boost actionability.
Trim the philosophy section significantly—Claude understands testing principles. Focus on the project-specific conventions and the vertical-slice mandate, which are the genuinely novel instructions.
Provide the referenced bundle files (tests.md, mocking.md, etc.) or remove references to non-existent files to avoid confusion.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The philosophy section over-explains what good vs bad tests are—concepts Claude already understands well. The anti-pattern section is valuable but somewhat verbose in its explanation. The workflow and checklist sections are reasonably tight. | 2 / 3 |
Actionability | The workflow provides clear steps and checklists, but lacks concrete, executable code examples. The RED→GREEN diagrams are illustrative but abstract—no actual test code or implementation code is shown. A TDD skill would benefit greatly from a concrete example showing a real test→implementation cycle. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Planning → Tracer Bullet → Incremental Loop → Refactor) with explicit validation checkpoints (checklists per cycle, 'never refactor while RED', run tests after each refactor step). The vertical slice approach is well-articulated with a clear feedback loop. | 3 / 3 |
Progressive Disclosure | References to supporting files (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) are present and one-level deep, which is good. However, no bundle files were provided, so these references are unverifiable. The main file itself includes substantial philosophical content that could be split out, and the inline content is somewhat long for an overview. | 2 / 3 |
Total | 9 / 12 Passed |