Research an engineering question well enough to support a decision: check a claim against primary sources, compare technologies or approaches, test whether an approach will work or scale, or find why something performs badly, using the repository, current documentation and small, reproducible experiments. Ends with a recommendation that names its evidence, tradeoffs and remaining uncertainty, which may be to keep what exists. Use it whenever the user asks whether to adopt, replace, upgrade or remove a dependency, technology or design, which option to choose, whether a switch is safe, or whether an approach will work or scale, even if they never say research, and whenever they ask to research, compare, evaluate or prototype. Not for quick lookups that one source answers, or for carrying out a change already decided.