templates/skills/languages/julia/SKILL.md
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
npx skillsauth add hivellm/rulebook JuliaInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
CRITICAL: Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
# Complete quality check sequence:
julia -e 'using JuliaFormatter; format(".", overwrite=false)' # Format check
julia -e 'using Lint; lintpkg(".")' # Linting
julia --project=. -e 'using Pkg; Pkg.test()' # All tests
# Security audit:
julia -e 'using Pkg; Pkg.update()' # Update deps
CRITICAL: Use Julia 1.9+ with JuliaFormatter and testing.
name = "YourPackage"
uuid = "12345678-1234-1234-1234-123456789012"
authors = ["Your Name <[email protected]>"]
version = "0.1.0"
[deps]
LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
[compat]
julia = "1.9"
[extras]
Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
[targets]
test = ["Test"]
IMPORTANT: These commands MUST match your GitHub Actions workflows!
# Pre-Commit Checklist (MUST match .github/workflows/*.yml)
# 1. Format check (matches workflow)
julia -e 'using JuliaFormatter; format(".", overwrite=false)'
# 2. Lint (matches workflow)
julia -e 'using Lint; lintpkg("YourPackage")'
# 3. Run all tests (MUST pass 100% - matches workflow)
julia --project=. -e 'using Pkg; Pkg.test()'
# 4. Check coverage (matches workflow)
julia --project=. --code-coverage=user -e 'using Pkg; Pkg.test()'
# If ANY fails: ❌ DO NOT COMMIT - Fix first!
Why This Matters:
format(..., overwrite=true) locally but overwrite=false in CI = failureusing Test
using YourPackage
@testset "DataProcessor tests" begin
@testset "process function" begin
@test process([1, 2, 3]) == [2, 4, 6]
@test process([]) == []
@test_throws ArgumentError process(nothing)
end
@testset "validate function" begin
@test validate("test") == true
@test validate("") == false
end
end
<!-- JULIA:END -->research
Create structured analyses with numbered findings, execution plans, and task materialization
research
Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.
development
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
data-ai
Autonomous AI agent loop for iterative task implementation (@hivehub/rulebook ralph)