← LeaderboardThe Skill Leaderboard

review-julia

Run the Julia code review protocol on Julia scripts. Checks code quality, type stability, parallel computing patterns, and scientific computing standards. Produces a report without editing files.

Published by brycewang-stanford ↗brycewang-stanford/Auto-Empirical-Research-Skills

Try your first task

review-julia

Start a fresh conversation. Replace the highlighted placeholders.

Use review-julia to review [Julia script or all] for correctness, performance, type stability, parallel patterns, and scientific-computing standards; produce a report only and do not edit source files.

Required inputs

  • [Julia script or all]

User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗

SKILL.md

name: review-juliadescription: Run the Julia code review protocol on Julia scripts. Checks code quality, type stability, parallel computing patterns, and scientific computing standards. Produces a report without editing files.disable-model-invocation: trueargument-hint: "[filename or 'all']"allowed-tools: ["Read", "Grep", "Glob", "Write", "Task"]

Review Julia Code

Run a comprehensive Julia code review on the specified script(s). Do NOT edit any source files -- produce a report only.

Steps

  1. Identify target: Use $ARGUMENTS to find the Julia file(s). If all, scan all .jl files in the project.

  2. Read standards from .claude/rules/julia-code-conventions.md.

  3. Check these categories:

    • Module Structure: Proper module organization, exports, includes
    • Parallel Computing: @everywhere annotations, pmap usage, worker data distribution
    • Optimization: Convergence checks, multiple starting values, grid search patterns
    • Type Stability: Concrete types in hot loops, @code_warntype recommendations
    • Path Conventions: joinpath() usage, no hardcoded OS-specific separators
    • Naming: snake_case functions, CamelCase types, paper notation alignment
    • Common Pitfalls: Missing @everywhere, local minima, large closures in pmap

  4. Save report to quality_reports/[script_name]_julia_review.md.

  5. Present summary: Total issues, severity breakdown, top critical issues.

Important

  • NEVER edit source files. Report only.
  • Prioritize correctness and performance over style.
  • For Julia code generation patterns (MLE, GMM, simulation), see /econometrics-julia.
review-julia by brycewang-stanford · The Skill Leaderboard