Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.
Use when choosing or running JETLS tests after code changes. Prefer component-specific tests, avoid the full suite unless needed, and use TestRunner for focused iteration.
Use when adding or modifying JETLS tests. Covers test file and module structure, @testset organization, let blocks, withserver usage, and when subroutine tests are sufficient for language-server features.
Add BestieTemplate features (AGENTS.md, changelog, dependabot, pre-commit, lint workflow, testitem runner) to a Julia package with the bestie CLI — no Julia needed. Use when asked to add one of these files/setups to a package, or to see what BestieTemplate can add.
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
Use when setting up or developing a Julia based documentation site with DocumenterVitepress.jl. Also use when the user mentions DocumenterVitepress, VitePress for Julia docs, or wants to preview docs locally with hot reload.
Fix CI failures and performance regressions for a Julia package PR by iterating - triage the latest CI results, fix one root cause, verify locally, push. Use when a PR's GitHub Actions or Buildkite CI is failing, or when CI jobs run slower than they do on the main branch. Verifies CPU and GPU compilation locally…
Build, run, and drive the AgentREPL.jl MCP server. Use when asked to start AgentREPL, launch the Julia REPL MCP server, run its tests, eval Julia code through it, render a plot, or confirm a change works against the running server.