playwright-expert
Use when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke to write test scripts, create page objects, configure test fixtures, set up reporters, add CI integration, implement API mocking, or perform visual regression testing. Trigger terms: Playwright, E2E test, end-to-end, browser testing, automation, UI testing, visual testing, Page Object Model, test flakiness.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does, when to use it, and includes comprehensive trigger terms. It lists specific concrete actions, provides explicit 'Use when' and 'Invoke to' clauses, and is distinctly scoped to Playwright E2E testing. The description uses proper third-person voice and avoids vague language.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: write test scripts, create page objects, configure test fixtures, set up reporters, add CI integration, implement API mocking, perform visual regression testing. | 3 / 3 |
Completeness | Clearly answers both 'what' (write test scripts, create page objects, configure fixtures, etc.) and 'when' (writing E2E tests with Playwright, setting up test infrastructure, debugging flaky browser tests) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Playwright', 'E2E test', 'end-to-end', 'browser testing', 'automation', 'UI testing', 'visual testing', 'Page Object Model', 'test flakiness'. These are terms users would naturally use when requesting help with Playwright testing. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Playwright and E2E browser testing specifically, with distinct triggers like 'Playwright', 'Page Object Model', 'visual regression testing', and 'test flakiness' that are unlikely to conflict with other testing or general coding skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid Playwright skill with excellent actionability — the code examples are complete, executable, and demonstrate best practices with clear correct/incorrect comparisons. The main weaknesses are the missing bundle files that the reference table points to, some filler content (Output Templates, Knowledge Reference sections), and a top-level workflow that lacks explicit validation checkpoints between steps.
Suggestions
Provide the five referenced markdown files (selectors-locators.md, page-object-model.md, etc.) as bundle files, or remove the reference table if they don't exist yet.
Remove the 'Knowledge Reference' keyword list and the vague 'Output Templates' section — they add no actionable value and waste tokens.
Add explicit validation checkpoints to the Core Workflow, e.g., after step 3: 'Run tests locally and verify all pass before proceeding to CI integration.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary elements like the 'Knowledge Reference' keyword list at the bottom which adds no value, and the introductory line restates the description. The MUST DO/MUST NOT lists are concise and useful, but the 'Output Templates' section is vague filler. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready TypeScript code examples including a complete Page Object Model class, test file with assertions, selector comparisons with correct/incorrect patterns, and concrete CLI commands for debugging flaky tests. | 3 / 3 |
Workflow Clarity | The core workflow is listed at a high level but lacks validation checkpoints. The debugging workflow for flaky tests is well-sequenced with a clear feedback loop (run → trace → fix → verify with repeat-each=10), but the overall test-writing workflow lacks explicit validation steps between stages. | 2 / 3 |
Progressive Disclosure | The reference table with 'Load When' guidance is a well-structured progressive disclosure pattern, but no bundle files were provided, meaning all five referenced files (selectors-locators.md, page-object-model.md, etc.) are missing. The skill inlines substantial code examples that could partially live in references, and the external documentation link points to a URL rather than bundled content. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jeffallan/claude-skills
- Commit
e8be415
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.