playwright

Browser automation and E2E testing with Playwright. Auto-detects dev servers, writes clean test scripts. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use for cross-browser testing, visual regression, API testing, component testing in TypeScript/JavaScript and Python projects.

Quality

87%

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

Quality

Content

75%Weight 40%Scale 1-5

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

Highly actionable content with executable examples and a clear workflow anchored by server detection, supported by a real one-level-deep reference. It is held back by verbosity — redundant re-explanation of familiar Playwright concepts and repeated guidance across multiple sections.

Suggestions

Consolidate the duplicated workflow guidance spread across 'CRITICAL WORKFLOW', 'How It Works', 'Best Practices', and 'Tips' into a single source of truth to cut padding.

Move the inline selector/assertion/action reference snippets into references/API_REFERENCE.md and keep SKILL.md to the unique execution workflow plus a pointer, since Claude already knows the Playwright API.

Add an explicit validate-then-retry loop for the dev-server detection step (e.g., re-detect after starting a server) to harden the workflow's feedback checkpoint.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code, but it re-explains concepts Claude already knows (selector best practices, assertion syntax, common actions, POM) and duplicates workflow guidance across the 'CRITICAL WORKFLOW', 'How It Works', 'Best Practices', and 'Tips' sections, adding padding.	3 / 5
Actionability	Fully executable, copy-paste-ready scripts and commands covering the common cases (responsive screenshots, login flow, broken links, network mocking, auth state), each with a precise execution command via run.js.	5 / 5
Workflow Clarity	A clear numbered sequence with a strong validation-first checkpoint (detect servers FIRST, branch on 1/multiple/none) and troubleshooting feedback, but the multi-server detection step lacks an explicit verify-or-retry loop and batch/destructive validation is only lightly addressed.	4 / 5
Progressive Disclosure	Good structure with one-level-deep reference: SKILL.md body points to the real references/API_REFERENCE.md via an explicit 'When to Load References' trigger list, though the main body still inlines substantial API material (selectors, assertions, actions) that could live in the reference file.	4 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 strong description: specific, concrete, and rich in natural trigger terms, with explicit what-and-when coverage and a clear niche that minimizes conflict risk. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links' — giving comprehensive coverage of concrete browser-automation capabilities.	5 / 5
Completeness	Clearly answers 'what' (browser automation and E2E testing with listed actions) and 'when' with the explicit 'Use for cross-browser testing, visual regression, API testing, component testing...' trigger clause.	5 / 5
Trigger Term Quality	Comprehensive natural keywords including synonyms and task phrasings users would actually say ('cross-browser testing', 'visual regression', 'API testing', 'component testing', 'login flows', 'check links') alongside file/format context (TypeScript/JavaScript, Python).	5 / 5
Distinctiveness Conflict Risk	Anchored to a distinct niche (Playwright browser automation/E2E) with clear trigger phrases that would not conflict with adjacent skills like vitest-testing or api-testing, which it explicitly differentiates from via 'See Also'.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (508 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	14 / 16 Passed

Repository: secondsky/claude-skills
Path: plugins/playwright/skills/playwright/SKILL.md
Commit: ad16332

Reviewed: 1 day 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.