e2e
Generate and run end-to-end tests with Playwright. Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts.
66
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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.
This is a solid description with strong specificity and clear distinctiveness around Playwright e2e testing. The main weaknesses are the lack of an explicit 'Use when...' clause and missing common trigger term variations that users might naturally say when requesting this functionality.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks for browser automation, e2e tests, UI testing, or mentions Playwright'
Include common term variations users might say: 'e2e', 'browser testing', 'UI tests', 'automated testing', '.spec.ts files'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Creates test journeys, runs tests, captures screenshots/videos/traces, and uploads artifacts' - these are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied through the domain mention. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'Playwright', 'end-to-end tests', 'screenshots', 'videos', 'traces', but missing common variations users might say like 'e2e', 'browser testing', 'UI testing', 'automated testing', or '.spec.ts'. | 2 / 3 |
Distinctiveness Conflict Risk | Clearly identifies Playwright as the specific tool and 'end-to-end tests' as the testing type, making it distinct from unit testing, API testing, or other test frameworks. Unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a decent overview of E2E testing capabilities but lacks the concrete, actionable guidance needed for effective use. The actual invocation mechanism (/e2e command) is never demonstrated, and the content reads more like documentation about what the tool does rather than instructions for how to use it. The quick commands at the end are helpful but disconnected from the agent workflow described above.
Suggestions
Add a concrete example showing how to invoke the /e2e command with sample input and expected output (e.g., '/e2e test login flow' -> what happens next)
Include an actual generated test example showing the Page Object Model pattern mentioned in best practices
Add validation/feedback loop: what to do when tests fail, how to interpret trace files, when to quarantine vs fix flaky tests
Remove redundancy between 'What This Skill Does' and 'How It Works' sections - consolidate into one actionable workflow
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary explanation (e.g., 'What This Skill Does' section largely duplicates 'How It Works'). The best practices section, while useful, explains concepts Claude likely knows. | 2 / 3 |
Actionability | Provides quick commands at the end which are executable, but the core skill invokes an 'e2e-runner agent' without showing how to actually invoke it or what the /e2e command syntax looks like. Missing concrete examples of test generation or the actual command interface. | 2 / 3 |
Workflow Clarity | Lists steps the agent will perform but lacks validation checkpoints. No guidance on what to do if tests fail, how to interpret results, or feedback loops for fixing flaky tests. The workflow is descriptive rather than instructive. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. No references to external documentation for advanced topics like Page Object Model patterns, trace debugging, or browser configuration details that could be split out. | 2 / 3 |
Total | 8 / 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.
- 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.