Juminuit Usage | Agent Skills Atlas

About this skill

Quick-reference for USING the JuMinuit.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/profileband (derived-quantity intervals & error bands), bootstrap/jackknife, getcontourssamples, findsolutionmodes, or finddeeperminimum; or when porting Python-iminuit or IMinuit.jl fitting code to JuMinuit. 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.

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 8cbb261735b62503378329eeb2520cfaf6e158c5b87e8725bce9c103498c4e23

About scan coverage and limitations

Original listing metadata

Original name

juminuit-usage

Original description

Quick-reference for USING the JuMinuit.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), `bootstrap`/`jackknife`, `get_contours_samples`, `find_solution_modes`, or `find_deeper_minimum`; or when porting Python-iminuit or IMinuit.jl fitting code to JuMinuit. 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.

About this listing

Category: Engineering
Reported license: LGPL-2.1
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.