https://video.ut0pia.org/videos/watch/433db6df-73be-4914-974c-30c2f7acf914 There are thousands of agent skills. Almost none of them are tested. They get vibe-checked with two manual runs, maybe a thumbs-up from a colleague, then shipped. You wouldn't merge code without tests — so why are we shipping skills without evals? This talk covers the full lifecycle of building reliable agent skills: what a skill actually is (and isn't), how to write one that triggers correctly, and how to build a lightweight eval harness that catches failures before your users do. Philipp SchmidStaff Engineer · Google DeepMind X/Twitter · LinkedIn · Website · Blog Philipp Schmid is a Staff Engineer at Google DeepMind working on Gemini and Gemma. His work focuses on helping developers build and benefit from AI responsibly. About This Session— View on the schedule Thu, 16 Jul 2026 03:18:46 GMT https://validator.w3.org/feed/docs/rss2.html PeerTube - https://video.ut0pia.org https://video.ut0pia.org/lazy-static/avatars/0287a09a-aae7-4840-9843-b416426e7046.webp https://video.ut0pia.org/videos/watch/433db6df-73be-4914-974c-30c2f7acf914 All rights reserved, unless otherwise specified in the terms specified at https://video.ut0pia.org/about and potential licenses granted by each content's rightholder.