Quick-reference for USING the NativeMinuit.jl Julia package (a native-Julia Minuit2 port with an iminuit / IMinuit.jl-style API) to minimize a χ²/likelihood and analyze fit errors. Use when writing or editing Julia code that fits data with `Minuit`, `migrad!`, `minos!`, `hesse!`, the cost-function objects (`LeastSquares`/`UnbinnedNLL`/`BinnedNLL`/…), `mncontour`/`profile`, `extremize`/`profile_band` (derived-quantity intervals & error bands), `bayesian`/`posterior_sample` (Bayesian posterior, priors & credible intervals/limits), `bootstrap`/`jackknife`, `get_contours_samples`, `find_solution_modes`, or `find_deeper_minimum`; or when porting Python-iminuit or IMinuit.jl fitting code to NativeMinuit. Covers the bang-method idiom (`migrad!(m)` not `m.migrad()`), the FCN/result conventions, AD & threaded gradients, bounds/fixed parameters, and the error-analysis decision guide — so the API is recalled, not guessed.
2026-07-06