webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
92
76%
Does it follow best practices?
Impact
100%
2.17xAverage score across 7 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/anthropic-webapp-testing/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 establishing a clear niche around Playwright-based local web app testing. Its main weakness is the absence of an explicit 'Use when...' clause, which limits Claude's ability to know exactly when to select this skill. Adding natural trigger terms users might say would also improve selection accuracy.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to test, interact with, or debug a local web application, or mentions Playwright, browser testing, or localhost.'
Include more natural user trigger terms such as 'e2e testing', 'end-to-end', 'localhost', 'open browser', 'click button', 'check page', or 'test my app'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'verifying frontend functionality', 'debugging UI behavior', 'capturing browser screenshots', and 'viewing browser logs'. These are distinct, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the nature of the actions described. | 2 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Playwright', 'browser screenshots', 'browser logs', 'UI', 'frontend', and 'web applications'. However, it misses common user terms like 'click', 'navigate', 'test my app', 'open browser', 'e2e testing', 'end-to-end', or 'localhost'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Playwright', 'local web applications', 'browser screenshots', and 'browser logs' creates a clear niche that is unlikely to conflict with other skills. The combination of browser automation tool + local testing is quite distinctive. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that provides clear, actionable guidance for web application testing with Playwright. The decision tree is an excellent organizational choice that helps Claude quickly determine the right approach. Minor verbosity in best practices (repeating the black-box scripts advice and stating obvious practices) prevents a perfect conciseness score, but overall the skill is effective and well-organized.
Suggestions
Remove redundant best practices that Claude already knows (e.g., 'Always close the browser when done', 'Use sync_playwright() for synchronous scripts') and consolidate the repeated black-box scripts guidance into a single mention.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but has some redundancy - the 'best practices' section repeats the black-box scripts guidance already stated at the top, and some bullet points (like 'always close the browser') are things Claude already knows. The decision tree and examples are well-structured though. | 2 / 3 |
Actionability | Provides fully executable bash commands for with_server.py usage, complete Python code for Playwright automation, and concrete examples of the reconnaissance pattern with real method calls. The decision tree gives specific, actionable guidance for each scenario. | 3 / 3 |
Workflow Clarity | The decision tree clearly sequences the approach based on context. The reconnaissance-then-action pattern is a well-defined 3-step workflow. The common pitfall section serves as a validation checkpoint highlighting the critical networkidle wait. For a testing/automation skill, the workflows are clear and appropriately sequenced. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview with quick-start examples inline, then references examples/ directory with specific file descriptions for deeper patterns. References are one level deep and clearly signaled. Content is appropriately split between the overview and reference files. | 3 / 3 |
Total | 11 / 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
- boisenoise/skills-collections
- Commit
636b862
- 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.