playwright-testing

E2E testing with Playwright - Page Objects, cross-browser, CI/CD

Quality

37%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/playwright-testing/SKILL.md

Quality

Discovery

32%

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 reads more like a tag list than a proper skill description. While it identifies the domain (Playwright E2E testing) and some relevant concepts, it fails to describe concrete actions the skill performs and completely lacks a 'Use when...' clause to guide skill selection. It needs to be rewritten as a proper sentence-based description with explicit triggers.

Suggestions

Rewrite as complete sentences describing concrete actions, e.g., 'Writes and maintains end-to-end tests using Playwright, creates Page Object Model classes, configures cross-browser test matrices, and sets up CI/CD pipelines for test execution.'

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Playwright tests, end-to-end testing, browser automation, writing E2E specs, or integrating Playwright into CI/CD.'

Include common natural language variations users might say, such as 'end-to-end', 'browser automation', 'test automation', '.spec.ts', 'test fixtures', or 'Playwright config'.

Dimension	Reasoning	Score
Specificity	Names the domain (E2E testing with Playwright) and mentions some concepts (Page Objects, cross-browser, CI/CD), but these are more like topic tags than concrete actions. It doesn't describe what the skill actually does (e.g., 'writes test scripts', 'generates page object classes', 'configures browser matrices').	2 / 3
Completeness	There is no explicit 'Use when...' clause or equivalent trigger guidance, and the 'what' is only loosely implied through topic keywords rather than clearly stated actions. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it down to 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'Playwright', 'E2E testing', 'Page Objects', 'cross-browser', and 'CI/CD' that users might mention. However, it misses common variations like 'end-to-end', 'browser testing', 'test automation', 'integration tests', or file extensions like '.spec.ts'.	2 / 3
Distinctiveness Conflict Risk	Mentioning 'Playwright' specifically helps distinguish it from other testing frameworks, but the broad terms 'E2E testing', 'cross-browser', and 'CI/CD' could overlap with skills for Cypress, Selenium, or general CI/CD configuration skills.	2 / 3
	Total	7 / 12 Passed

Implementation

42%

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

The skill is highly actionable with excellent, executable code examples covering the full Playwright testing lifecycle. However, it is severely over-length — it reads like a comprehensive reference guide rather than a concise skill file, explaining many patterns Claude already knows how to implement. The content desperately needs progressive disclosure: splitting page objects, link checking, CI configs, and assertion references into separate files while keeping SKILL.md as a lean overview.

Suggestions

Reduce the main SKILL.md to ~100-150 lines covering setup, locator priority, basic test structure, and a quick reference — move page objects, link detection, CI/CD, mocking, and visual testing into separate referenced files (e.g., PAGES.md, LINK-CHECK.md, CI.md).

Remove code that Claude can generate from first principles (e.g., full BasePage/LoginPage/DashboardPage implementations, complete link crawler, image validator) and replace with brief patterns or one-liner examples showing the key insight.

Add an explicit workflow section with numbered steps and validation checkpoints, e.g., '1. Install → verify with `npx playwright --version` 2. Configure → run `npx playwright test` to verify setup 3. Write first test → run headed to verify'.

Cut the assertions reference section entirely — Claude knows Playwright's assertion API — or reduce to a 3-line 'prefer web-first assertions (auto-wait) over manual waits' note.

Dimension	Reasoning	Score
Conciseness	The skill is extremely long (~600+ lines) with extensive code blocks that are largely boilerplate Claude could generate on its own. The full playwright.config.ts, complete page object implementations, comprehensive link crawler, image validation tests, and CI/CD YAML are all things Claude already knows how to produce. The 'Dead Link Detection (REQUIRED)' section alone is ~120 lines of code that doesn't need to be spelled out in full. Much of this is reference documentation repackaged.	1 / 3
Actionability	Every section provides fully executable, copy-paste ready code examples — TypeScript test files, bash commands, YAML CI configs, and JSON package scripts. The code is complete and specific with realistic examples (Stripe iframe handling, faker factories, etc.).	3 / 3
Workflow Clarity	The setup flow (install → configure → write tests → run) is implicit rather than explicitly sequenced. The project structure section helps orient, but there are no explicit validation checkpoints (e.g., 'verify browsers installed successfully before proceeding'). The auth setup dependency chain is well-explained but the overall workflow lacks a clear step-by-step progression with verification gates.	2 / 3
Progressive Disclosure	This is a monolithic wall of content with no references to supporting files despite being well over 500 lines. The locator strategy reference, full page object implementations, complete link crawler code, CI/CD configs, and assertion reference tables should all be split into separate files. There are no bundle files to offload content to, and the skill doesn't attempt any layering — everything is inline.	1 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (962 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: alinaqi/claude-bootstrap
Commit: 65efb33

Reviewed: 6 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.