Building Vibium Skills That Actually Drive Fixes Introduction This post is about turning a skills system into a real testing accelerator. I wanted a Vibium-only testing skill that would steer an agent away from Playwright and into purposeful negative tests. That meant carving out a dedicated SKILL.md file, proving the description would be recognised byContinue reading “Agent Skills – how to create and test them”
Category Archives: Agentic
Experimenting with AI Agents: sending Mailinator emails with Zapier MCP, Goose and CursorAI
So in my recent posts, I’ve been exploring AI and agentic AI:- I heard on the LinkedIn grapevine the news that workflow automation specialists Zapier have embraced the MCP bandwagon and decided to serve up all of their integrations via the MCP route. Thanks for the heads up Angie. This will allow AI Agents toContinue reading “Experimenting with AI Agents: sending Mailinator emails with Zapier MCP, Goose and CursorAI”
Exploring Agentic AI with Block’s Goose and Selenium MCP: Tips and Demos
When I’m not spending my weekends on such life affirming tasks as taking son to football practice, watching Gladiators or drinking wine, I like to indulge in some hands on learning. At the moment its been focussed on chipping away at the ever expanding pool of knowledge surrounding AI and test automation. Here are someContinue reading “Exploring Agentic AI with Block’s Goose and Selenium MCP: Tips and Demos”
Beth The Tester's Tales 