This is the recorded version of the 80-minute workshop Nick Nisi and I delivered at AI Engineering London: Skills at Scale: Leveraging Skills Across Workflows, Agents, and Teams.
We taught how to build Claude Code skills that are portable across projects and tools, executable (scripts inject real data into the skill's context at runtime), and composable (small, focused units that call each other). Constraints over instructions. Evidence over guesses. Measurement over vibes.
For the full write-up, see the workshop blog post. For the talk details, links, and slides, see the speaking page.
Discussion
Giscus