playwright-expert

Name: playwright-expert
Rating: 67 (1 reviews)
Author: jeffallan

tessl i github:jeffallan/claude-skills --skill playwright-expert

github.com/jeffallan/claude-skills

Use when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke for browser automation, E2E tests, Page Object Model, test flakiness, visual testing.

Review Score

67%

Validation Score

12/16

Implementation Score

42%

Activation Score

90%

SKILL.md

Review

Evals

Generated

13 days ago

Warnings & errors only

Criteria	Score
metadata_version	'metadata' field is not a dictionary
license_field	'license' field is missing
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata
body_examples	No examples detected (no code fences and no 'Example' wording)

Overall Assessment

This skill has excellent progressive disclosure structure with a well-organized reference table, but critically lacks actionable code examples. For a technical testing skill, the absence of any executable Playwright code (test examples, selector patterns, configuration snippets) significantly limits its utility. The content describes what to do rather than showing how to do it.

Suggestions

Add executable code examples for key patterns: a basic test file, a Page Object class, and a playwright.config.ts snippet
Replace vague workflow steps with concrete commands (e.g., 'npx playwright test --trace on' for debugging)
Remove the 'Role Definition' section - Claude doesn't need persona framing to execute the skill
Add a validation checkpoint in the workflow, such as 'Run `npx playwright test --ui` to verify tests pass locally before CI integration'

Dimension	Score	Reasoning
Conciseness	2/3	The skill includes some unnecessary framing ('Senior E2E testing specialist with 8+ years experience') and role-play setup that Claude doesn't need. The MUST DO/MUST NOT lists are efficient, but the 'Role Definition' and 'When to Use' sections add tokens without adding actionable value.
Actionability	1/3	The skill provides no executable code examples - only abstract guidance like 'Use POM pattern, proper selectors, auto-waiting' and 'Configure Playwright with proper settings.' There are no concrete code snippets, commands, or copy-paste ready examples despite being a technical testing skill.
Workflow Clarity	2/3	The 5-step core workflow is listed but lacks validation checkpoints or feedback loops. Steps like 'Debug - Fix flaky tests, use traces' are vague. No explicit verification steps between writing tests and CI integration, which is important for test reliability.
Progressive Disclosure	3/3	Excellent use of a reference table with clear topics, file paths, and 'Load When' guidance. References are one level deep and well-signaled. The structure appropriately keeps the main skill lean while pointing to detailed materials.

Overall Assessment

This is a strong skill description with excellent trigger term coverage and clear 'Use when' guidance. The main weakness is that the capabilities could be more specific - listing concrete actions like 'generate page objects', 'configure test fixtures', or 'implement retry strategies' would strengthen the specificity dimension.

Suggestions

Add more concrete actions to the description, such as 'generate page objects, configure test fixtures, implement retry strategies, set up visual regression tests'

Dimension	Score	Reasoning
Specificity	2/3	Names the domain (E2E tests, Playwright) and mentions some actions like 'writing', 'setting up', 'debugging', but doesn't list concrete specific actions like 'create page objects', 'configure test runners', or 'implement retry logic'.
Completeness	3/3	Clearly answers both what (writing E2E tests, setting up infrastructure, debugging flaky tests) and when (explicit 'Use when' and 'Invoke for' clauses with specific trigger scenarios).
Trigger Term Quality	3/3	Excellent coverage of natural terms users would say: 'Playwright', 'E2E tests', 'browser automation', 'Page Object Model', 'test flakiness', 'visual testing', 'flaky browser tests'. These are terms developers naturally use when seeking help with this domain.
Distinctiveness Conflict Risk	3/3	Very distinct niche with Playwright-specific terminology. Terms like 'Page Object Model', 'flaky browser tests', and 'visual testing' clearly distinguish this from generic testing or other automation skills.