e2e
Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.
56
45%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/e2e/SKILL.mdQuality
Discovery
67%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 does a good job listing specific capabilities and is clearly scoped to Playwright end-to-end testing, making it distinctive. However, it lacks an explicit 'Use when...' clause which caps completeness, and could benefit from additional natural trigger terms that users commonly use when requesting browser or e2e testing.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks for end-to-end testing, browser testing, UI testing, or mentions Playwright.'
Include common trigger term variations such as 'e2e tests', 'browser testing', 'UI testing', 'automated testing', '.spec.ts' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate tests, run tests, create test journeys, capture screenshots/videos/traces, and upload artifacts. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the capabilities listed. | 2 / 3 |
Trigger Term Quality | Includes good terms like 'Playwright', 'end-to-end tests', 'screenshots', 'videos', 'traces', but misses common user variations like 'e2e tests', 'browser testing', 'UI testing', 'integration tests', or 'automated testing'. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Playwright specifically and end-to-end testing with distinct features like traces and artifact uploads. Unlikely to conflict with other testing or general coding skills due to the Playwright specificity. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a feature overview or README than actionable instructions for Claude. It describes what the e2e-runner agent does but provides almost no concrete, executable guidance on how to actually generate tests, configure browsers, handle failures, or upload artifacts. The content is mostly things Claude already knows about Playwright testing.
Suggestions
Add a concrete, executable example of a generated Playwright test using the Page Object Model pattern, showing the expected file structure and test code.
Include specific workflow steps with validation checkpoints: how to verify test generation succeeded, how to handle test failures, and how to quarantine flaky tests with actual commands or code.
Replace the generic 'Best Practices' and 'When to Use' sections with project-specific configuration details (e.g., actual config file paths, environment setup, artifact upload commands).
Add concrete examples of how artifacts are captured and uploaded, including any project-specific scripts or CI integration configuration.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanation (e.g., 'When to Use' section lists obvious use cases Claude would know, 'Best Practices' section includes generic advice like 'don't test implementation details'). However, it's not excessively verbose and stays relatively organized. | 2 / 3 |
Actionability | The skill is mostly descriptive rather than instructive. It describes what the e2e-runner agent does but provides no concrete code for generating tests, no Page Object Model examples, no configuration snippets, and no actual test file examples. The only executable content is 4 basic CLI commands at the bottom that are standard Playwright commands Claude already knows. | 1 / 3 |
Workflow Clarity | The workflow is described at a high level ('analyze user flow', 'generate Playwright test', 'run tests') but lacks any concrete sequencing, validation checkpoints, or error recovery steps. There's no guidance on what to do when tests fail, how to handle flaky test quarantine, or how artifacts are actually uploaded. | 1 / 3 |
Progressive Disclosure | The content is organized into clear sections with headers, which is good. However, it's somewhat monolithic with no references to external files for detailed configuration, Page Object Model patterns, or example test files that would benefit from separate documents. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- sc30gsw/claude-code-customes
- Commit
7aff694
- Reviewed
Table of Contents
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.