qa-browser-tester

Launch a real headless browser on the server and perform exhaustive end-to-end QA testing of a web application — clicking every button, filling every form, n...

This skill will install Playwright/Chromium (potentially by running get-pip.py and pip), run system package installs, disable Chromium's sandbox flags, probe system files, and then automatically click and submit everything it finds on the target site. Those actions can be destructive (create/delete data, send emails, trigger payments) and weaken process isolation (no-sandbox). Only run this on an isolated test or staging environment you control. Before running: (1) set BASE_URL to a safe test target, (2) review and optionally run the Phase 0 commands manually to inspect environment, (3) consider running inside a disposable Docker container or VM with limited network access and snapshots, (4) do not run against production systems with real data/credentials, and (5) ensure you have backups and approval for any automated actions. If you need safer behavior, request a dry-run mode, a whitelist of paths, or confirmation prompts before submissions/clicks.

Type: OpenClaw Skill Name: qa-browser-tester Version: 1.0.0 The skill is a comprehensive QA automation tool that uses Playwright to perform end-to-end testing of web applications. It includes detailed environment discovery (OS, Docker status, package managers) and automated installation of dependencies (Playwright, Chromium) in SKILL.md. The provided Python script in references/test-phases.md performs site crawling, form testing, user journey simulation, and basic security checks (unauthenticated access to common protected routes). All actions, including the extensive environment checks and software installation, are transparently documented and directly support the stated purpose of ensuring a functional browser environment on various Linux and Docker configurations. No malicious intent or unauthorized data exfiltration was detected.