playwright-core

Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, assertions, fixtures, network mocking, auth flows, debugging, and framework recipes for React, Next.js, Vue, and Angular. TypeScript and JavaScript.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

78%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.

The body is a model progressive-disclosure overview: lean, well-organized, and routing users to one-level-deep reference guides. Its main limitation is that executable code examples live entirely in the referenced files, so the overview itself stays at 4 for actionability and conciseness rather than 5.

Dimension	Reasoning	Score
Conciseness	The Golden Rules are terse, concrete one-liners and the Guide Index is pure navigation with no padding about what Playwright is; only mild promotional flavor ("Opinionated, production-tested") and slight redundancy with the description keep it just under the 5 anchor.	4 / 5
Actionability	Concrete, copy-pasteable directives inline ("Never page.waitForTimeout() — use expect(locator).toBeVisible() or page.waitForURL()", "Retries: 2 in CI, 0 locally", "Traces: 'on-first-retry'") with specific API names and values, but no complete executable code blocks since those are deferred to reference files.	4 / 5
Workflow Clarity	Clear task-to-guide routing tables ("What you're doing" -> Guide) and an Architecture Decisions section guide selection; no multi-step validation workflow is present, but none is required for a non-destructive reference hub, so it sits at 4 rather than 5.	4 / 5
Progressive Disclosure	Exemplary one-level-deep structure: a lean SKILL.md overview (Golden Rules + categorized Guide Index) pointing to 46 well-signaled reference files with no nested-reference chains, matching the 5 anchor for clear overview with easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

70%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.

The description is specific, trigger-rich, and clearly niched to Playwright, but it omits an explicit "Use when..." trigger clause, which caps its completeness. Adding a use-when clause would raise the strongest remaining weakness.

Suggestions

Append an explicit trigger clause, e.g. "Use when writing or debugging Playwright tests (E2E, API, component, visual, a11y) or when the user mentions Playwright, browser automation, or flaky E2E tests."

Add the natural synonym "end-to-end" alongside "E2E" and a file-extension cue like ".spec.ts" to broaden trigger coverage.

Reframe one or two covered areas as concrete verb-actions (e.g. "write", "mock", "debug", "assert") to lift specificity toward the 5 anchor.

Dimension	Reasoning	Score
Specificity	Comprehensively enumerates concrete testing surfaces ("E2E, API, component, visual, accessibility, and security testing"; "locators, assertions, fixtures, network mocking, auth flows, debugging"), but they are framed as covered categories ("patterns for", "Covers") rather than verb-actions like extract/fill/merge, so it sits just below the 5 anchor.	4 / 5
Completeness	The "what" is clearly stated, but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Strong natural keywords users would say ("Playwright", "E2E", "API testing", "fixtures", "network mocking", "auth flows", framework names), but a few natural synonyms/extensions are missing (e.g. "end-to-end", ".spec.ts"), placing it just under comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	Anchored to a clear niche ("Playwright patterns") with distinct triggers and named frameworks, giving minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 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: 49 missing	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/playwright/core/SKILL.md
Commit: 4eaf4ff

Reviewed: 4 days 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.