We expected skills to be the solution for teaching coding agents framework-specific knowledge. After building evals focused on Next.js 16 APIs, we found something unexpected. A compressed 8KB docs index embedded directly in AGENTS.md achieved a 100% pass rate, while skills maxed out at 79% even with explicit instructions telling the agent to use them. Without those instructions, skills performed no better than having no documentation at all. Here's what we tried, what we learned, and how you can set this up for your own Next.js projects. Link to heading The problem we were trying to solve AI coding agents rely on training data that becomes outdated. Next.js 16 introduces APIs like 'use cache' , connection() , and forbidden() that aren't in current model training data. When agents don't know these APIs, they generate incorrect code or fall back to older patterns. The reverse can also be true, where you're running an older Next.js version and the model suggests newer APIs that don't exist in your project yet.…