e2e-testing

End-to-end testing workflow with Playwright for browser automation, visual regression, cross-browser testing, and CI/CD integration.

Quality

39%

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/e2e-testing/SKILL.md

Quality

Content

17%Scale 1-5

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

This skill is a hollow orchestration document that delegates all actual content to external skills that aren't provided. It contains no executable code, no concrete Playwright examples, no configuration snippets, and no specific commands. The repetitive phase structure adds significant bulk without providing any actionable guidance that Claude couldn't generate from its own knowledge.

Suggestions

Add concrete, executable Playwright code examples for at least the core phases (setup, test implementation, visual regression) — e.g., a complete test file, playwright.config.ts, and visual comparison snippet.

Include specific commands for each step (e.g., 'npx playwright install', 'npx playwright test --project=chromium', 'npx playwright show-report') instead of vague action items.

Add validation checkpoints with concrete criteria — e.g., 'Run `npx playwright test --reporter=list` and verify all tests pass before proceeding to CI integration'.

Either provide the referenced bundle skills or collapse the 7 phases into 2-3 phases with inline, self-contained guidance that doesn't depend on external files.

Dimension	Reasoning	Score
Conciseness	The skill is heavily padded with repetitive structure across 7 phases that all follow the same template. It explains when to use the workflow with obvious bullet points ('Setting up E2E testing', 'Automating browser tests') that add no value. The 'Copy-Paste Prompts' sections are just one-line delegations to other skills, adding bulk without substance.	2 / 5
Actionability	There is zero executable code, no concrete commands, no configuration examples, and no specific Playwright API usage. Every phase simply lists vague action items ('Install Playwright', 'Write test scripts', 'Add assertions') and delegates to other skills via copy-paste prompts. Claude would not know what to actually do from this content alone.	1 / 5
Workflow Clarity	While there is a rough 7-phase sequence, the steps within each phase are vague action items with no specifics. There are no validation checkpoints between phases, no feedback loops for test failures, and no error recovery guidance. The quality gates checklist at the end is superficial with no criteria for what 'adequate' or 'stable' means.	2 / 5
Progressive Disclosure	The skill references many other skills (playwright-skill, e2e-testing-patterns, browser-automation, etc.) but none of these are provided in the bundle, making it impossible to verify they exist or contain useful content. The skill itself is essentially an empty shell that delegates everything to unverifiable external references, with no substantive content at the top level.	2 / 5
	Total	7 / 20 Passed

Description

61%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 identifies the domain and tool (Playwright) well and includes several relevant trigger terms, but it reads more like a feature list of categories than concrete actions. The biggest weakness is the absence of an explicit 'Use when...' clause, which is critical for Claude's skill selection. The specificity could be improved by listing concrete actions rather than broad capability areas.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases, e.g., 'Use when the user asks about writing e2e tests, Playwright configuration, test automation, or debugging browser tests.'

Replace category labels with concrete actions, e.g., 'Write and debug Playwright e2e tests, configure test runners, capture visual regression screenshots, set up cross-browser test matrices, and integrate test suites into CI/CD pipelines.'

Include common synonyms and file references like 'e2e tests', 'test automation', 'playwright.config.ts', 'headless browser' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (end-to-end testing with Playwright) and lists several areas (browser automation, visual regression, cross-browser testing, CI/CD integration), but these read more like category labels than concrete actions. It doesn't specify actions like 'write tests', 'generate page objects', 'configure test runners', or 'debug failing tests'.	3 / 5
Completeness	The 'what' is present (end-to-end testing workflow with Playwright covering several areas), but there is no explicit 'when' clause. There is no 'Use when...' guidance telling Claude when to select this skill, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes strong trigger terms like 'Playwright', 'end-to-end testing', 'browser automation', 'visual regression', 'cross-browser testing', and 'CI/CD'. Missing some natural user phrases like 'e2e tests', 'test automation', 'screenshot comparison', 'headless browser', or file/config references like 'playwright.config.ts'.	4 / 5
Distinctiveness Conflict Risk	Mentioning 'Playwright' specifically makes it fairly distinct from generic testing skills or other test frameworks like Cypress or Selenium. However, broad terms like 'browser automation' and 'CI/CD integration' could overlap with other skills covering those areas.	4 / 5
	Total	14 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/e2e-testing/SKILL.md
Commit: 57c135b

Reviewed: 3 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.