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 table of contents with no substance. It promises E2E testing guidance for Playwright and Cypress but provides zero concrete code, commands, selectors, or examples. The instructions read like a project plan outline rather than actionable guidance, and the entire value is deferred to a single external resource file without any meaningful overview content.
Suggestions
Add concrete, executable code examples for at least one framework (e.g., a Playwright test with proper selectors, setup, and assertions) directly in the SKILL.md.
Replace the vague 4-step instructions with specific, actionable steps including commands (e.g., `npx playwright test --trace on`) and validation checkpoints (e.g., 'verify test passes locally before pushing to CI').
Include at least one complete example of a critical user journey test (e.g., login flow) with stable selector strategies demonstrated in code.
Describe what's in the implementation-playbook.md resource so Claude knows when and why to consult it, and consider adding a quick-start section that doesn't require navigating to another file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes some unnecessary sections like the 'Use this skill when' and 'Do not use this skill when' lists that are somewhat obvious and don't add much actionable value. The actual instructions are very thin. | 2 / 3 |
Actionability | The instructions are entirely abstract and vague — 'Identify critical user journeys,' 'Build stable selectors,' 'Implement tests with retries' — with zero concrete code, commands, examples, or specific guidance. Despite the description mentioning Playwright and Cypress, neither tool is referenced in the content with any executable detail. | 1 / 3 |
Workflow Clarity | The four numbered steps are high-level platitudes without any specifics, validation checkpoints, or error recovery guidance. There is no concrete sequence that Claude could follow to actually accomplish anything. | 1 / 3 |
Progressive Disclosure | There is a reference to `resources/implementation-playbook.md` for detailed patterns, which is good progressive disclosure structure. However, the SKILL.md itself provides almost no useful overview content — it's too thin to serve as a meaningful entry point, and there's only one reference with no description of what's inside. | 2 / 3 |
Total | 6 / 12 Passed |