Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Builds and runs automated QA testing bots that simulate real user journeys across websites and web apps. Uses Apify with Puppeteer and Playwright to detect broken flows, 404 errors, and regressions. Captures screenshots and video at each step for visual debugging.
Runs full browser automation in the cloud without managing browser infrastructure locally, and integrates directly into CI/CD pipelines for post-deployment verification.
When to use it
- Testing signup and login flows after a new deployment
- Finding all broken links across a marketing site before launch
- Verifying checkout works on mobile, tablet, and desktop viewports
- Running regression tests automatically on every pull request
- Asserting page load times stay under acceptable thresholds
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: test the registration flow on https://my-app.com/signup
- 1Maps the user journey steps: page load, form fill, submit, redirect assertion
- 2Builds a Puppeteer script targeting the signup form selectors
- 3Runs the actor via Apify API using the APIFY_TOKEN
- 4Collects pass/fail results and screenshot URLs from the dataset
- 5Generates a structured test report flagging any failed steps with error context
A JSON test report showing each step status (PASS/FAIL), duration, error messages, and a screenshot URL for the final state
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.