Content
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a hollow shell that defers all substantive content to an external file while providing no actionable guidance, no code examples, and no concrete testing patterns in the main body. The instructions are generic boilerplate that could apply to any domain and teach Claude nothing about Python testing. The skill fails its core purpose of providing executable, specific guidance for pytest-based testing.
Suggestions
Add at least 2-3 concrete, executable pytest code examples directly in SKILL.md covering common patterns (basic test, fixture usage, mocking with unittest.mock/pytest-mock)
Replace the generic instruction bullets with specific pytest workflows, e.g., 'Run tests with `pytest -v --tb=short`, use `@pytest.fixture` for setup/teardown, mock external calls with `monkeypatch` or `unittest.mock.patch`'
Add a quick-start section showing a minimal test file structure and how to run it, so the skill provides immediate value without requiring the external resource
Remove the generic 'Do not use this skill when' section and the vague instruction bullets ('Clarify goals, constraints') that waste tokens without adding testing-specific knowledge
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'Use this skill when' and 'Do not use this skill when' sections are somewhat padded and don't add actionable value. The instructions section is generic filler that Claude already knows ('Clarify goals, constraints, and required inputs'). However, it's not excessively verbose overall. | 2 / 3 |
Actionability | There is no concrete code, no executable examples, no specific commands, and no pytest-specific guidance. The instructions are entirely generic platitudes like 'Apply relevant best practices and validate outcomes' that could apply to any skill. No actual testing patterns are taught. | 1 / 3 |
Workflow Clarity | There is no clear workflow, no sequenced steps for writing tests or setting up test infrastructure, and no validation checkpoints. The four bullet points in Instructions are vague directives with no testing-specific process. | 1 / 3 |
Progressive Disclosure | There is a reference to `resources/implementation-playbook.md` which is one level deep and clearly signaled. However, the SKILL.md itself contains essentially zero useful overview content — it's just a pointer to another file with no quick-start or summary of key patterns, making the top-level document nearly empty of substance. | 2 / 3 |
Total | 6 / 12 Passed |