Content
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a comprehensive pytest tutorial/reference manual rather than a focused skill document. While the code examples are excellent and fully executable, the document is far too verbose, explaining many concepts Claude already knows (basic assertions, simple test structure, how to run pytest). The lack of progressive disclosure means everything is crammed into one massive file with no external references, making it an inefficient use of context window tokens.
Suggestions
Cut the document to ~100 lines focusing only on project-specific conventions (TDD workflow, coverage requirements, directory structure, DO/DON'T rules) and move reference material (assertions, mocking patterns, parametrization examples, configuration) to separate linked files like PATTERNS.md and CONFIG.md.
Remove sections that explain basic pytest knowledge Claude already has: the 'Basic Test Structure' section, the full assertions catalog, and the 'Running Tests' command list are all standard pytest documentation.
Add validation checkpoints to the TDD workflow, such as 'Run pytest --cov after GREEN step to verify coverage target is met' and 'If coverage drops below 80%, identify untested paths before proceeding to REFACTOR.'
Replace the quick reference table and verbose running tests section with a brief link to pytest documentation, keeping only project-specific configuration choices.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Explains basic pytest concepts Claude already knows (assertions, basic test structure, how to run pytest). The assertions section alone lists trivial patterns like `assert result == expected` and `assert item in collection`. The 'Basic Test Structure' section with `test_addition` testing `2 + 2 == 4` adds no value. Much of this is essentially a pytest tutorial/reference manual rather than a skill adding novel knowledge. | 1 / 3 |
Actionability | All code examples are concrete, executable, and copy-paste ready. Covers fixtures, mocking, parametrization, async testing, and configuration with complete, runnable examples. Commands for running tests are specific and correct. | 3 / 3 |
Workflow Clarity | The TDD cycle (red-green-refactor) is clearly sequenced, but there are no validation checkpoints or feedback loops. For example, there's no guidance on what to do when coverage drops below 80%, no verification step after writing tests, and no error recovery patterns for common testing failures. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. Everything from basic assertions to async testing to configuration is inlined in a single massive document. Content like the full assertions reference, pytest configuration options, and the running tests command reference should be split into separate files with clear navigation links. | 1 / 3 |
Total | 7 / 12 Passed |