playwright-skill

Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, fixtures, POM, network mocking, auth flows, debugging, CI/CD (GitHub Actions, GitLab, CircleCI, Azure, Jenkins), framework recipes (React, Next.js, Vue, Angular), and migration guides from Cypress/Selenium. TypeScript and JavaScript.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/playwright/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The SKILL.md body is a well-organized, concise orientation hub with genuinely actionable Golden Rules, but its value depends on 50+ reference guides that are not present in the bundle, leaving the actionability and progressive disclosure only partially fulfilled.

Suggestions

Ship the referenced bundle files (core/, ci/, pom/, migration/, playwright-cli/) or remove the dead links so the index resolves to real content.

Include at least one complete, executable TypeScript/JavaScript example inline in SKILL.md so the entry point is self-sufficient for the most common task.

Add a short 'how to use this skill' workflow that sequences selecting a guide → applying the pattern → verifying with traces, so the navigation doubles as a process.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what Playwright is or basic testing concepts; the Golden Rules are terse opinionated one-liners and the rest is a navigational index, so every token earns its place.	3 / 3
Actionability	The Golden Rules give concrete directives ('getByRole() over CSS/XPath', 'expect(locator).toBeVisible()', 'Retries: 2 in CI', "Traces: 'on-first-retry'") but all complete executable code examples are delegated to the 50+ reference guides, which are not present, so the inline guidance is incomplete rather than copy-paste ready.	2 / 3
Workflow Clarity	Navigation is clearly organized into problem-category tables, but this is an index hub rather than a multi-step operational process, and there are no explicit validation checkpoints or feedback loops; the sequence is present but checkpoints are only implicit.	2 / 3
Progressive Disclosure	The structural design is excellent — a concise overview (Golden Rules) plus well-signaled one-level-deep references in categorized tables — but none of the referenced bundle files or directories (core/, ci/, pom/, migration/, playwright-cli/) actually exist, so the progressive disclosure is only partially realized with broken links.	2 / 3
	Total	9 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-triggered, and distinct description that names concrete capabilities and natural user terms. Its one weakness is the absence of an explicit 'Use when...' clause, leaving the activation conditions implied rather than stated.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when writing or debugging Playwright E2E/component/API tests, configuring Playwright CI, or migrating from Cypress/Selenium.'

Lead with the activation trigger before the capability list so the 'when' is as clear as the 'what'.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities across the Playwright surface — 'locators, fixtures, POM, network mocking, auth flows, debugging, CI/CD ... framework recipes ... migration guides from Cypress/Selenium' — matching the 'lists multiple specific concrete actions' anchor and exceeding the score-2 'some actions' bar.	3 / 3
Completeness	The 'what' is answered thoroughly, but there is no explicit 'Use when...' clause or equivalent trigger guidance — the 'when' is only implied — so per the rubric guideline this caps completeness at 2.	2 / 3
Trigger Term Quality	Uses natural terms a user would say — 'Playwright', 'E2E', 'API testing', 'component testing', 'visual', 'accessibility', 'CI/CD', 'React', 'Next.js', 'Vue', 'Angular', 'Cypress', 'Selenium' — giving broad coverage of how users actually phrase these needs; voice is correctly third person.	3 / 3
Distinctiveness Conflict Risk	Scoped specifically to Playwright with named framework recipes and Cypress/Selenium migration guides, giving it a clear niche that is unlikely to trigger for unrelated testing or generic coding skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 74 missing	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/playwright/SKILL.md
Commit: af7d491

Reviewed: about 8 hours ago

Table of Contents

Discovery Implementation Validation

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.