Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
88
86%
Does it follow best practices?
Impact
90%
22.50xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Core navigation and form interaction workflow
Opens via playwright-cli
0%
100%
Snapshot before interaction
0%
100%
Uses element refs
0%
100%
Uses fill for inputs
0%
100%
Click to submit
0%
100%
Re-snapshot after navigation
0%
0%
Screenshot captured
50%
100%
eval for data extraction
0%
100%
Close session
0%
100%
Script is a valid shell script
28%
100%
Multi-tab workflow and data extraction
Opens first URL
0%
100%
tab-new for second tab
0%
100%
tab-list called
0%
100%
tab-select to switch
0%
100%
Snapshot in each tab
0%
0%
eval for title extraction
0%
100%
Screenshots per tab
0%
100%
Close session
0%
100%
Script has playwright-cli commands
0%
100%
Comparison report produced
100%
100%
DevTools debugging with console, network, and tracing
Opens URL
0%
100%
Snapshot before interaction
0%
100%
Uses element refs
0%
100%
tracing-start before interaction
0%
100%
tracing-stop after interaction
0%
100%
console command used
0%
100%
network command used
0%
100%
Screenshot captured
0%
100%
Script has playwright-cli commands
0%
100%
Close session
0%
0%
47823e3
Table of Contents
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.