The difference between an AI agent that helps you and one that guesses is context — the knowledge it loads before it does anything. We package that as skills in swamp, and test them in CI the same way we test code. stack72.dev/skills-are-c...
stack72.devSkills Are Context, and Context Needs TestsSkills are context. They're the thing an agent reads before it decides how to use swamp. If the skills are wrong, everything downstream is wrong — so we test them in CI the same way we test code, using tessl for quality and promptfoo for routing, across every model we care about.
0 reposts0 likes