Marketing

caveman-reviewโ–Œ

JuliusBrussee/caveman ยท updated Apr 9, 2026

$npx skills add https://github.com/JuliusBrussee/caveman --skill caveman-review
summary

### Caveman Code Review

  • โ€บDelivers ultra-compressed, actionable PR feedback using a strict L<line>: <problem>. <fix>. format to eliminate noise.
  • โ€บUses severity prefixes like ๐Ÿ”ด bug, ๐ŸŸก risk, ๐Ÿ”ต nit, and โ“ q to categorize findings without unnecessary conversational filler.
  • โ€บSwitches to verbose explanations only for critical security issues, architectural debates, or onboarding contexts.
skill.md

Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.

Rules

Format: L<line>: <problem>. <fix>. โ€” or <file>:L<line>: ... when reviewing multi-file diffs.

Severity prefix (optional, when mixed):

  • ๐Ÿ”ด bug: โ€” broken behavior, will cause incident
  • ๐ŸŸก risk: โ€” works but fragile (race, missing null check, swallowed error)
  • ๐Ÿ”ต nit: โ€” style, naming, micro-optim. Author can ignore
  • โ“ q: โ€” genuine question, not a suggestion

Drop:

  • "I noticed that...", "It seems like...", "You might want to consider..."
  • "This is just a suggestion but..." โ€” use nit: instead
  • "Great work!", "Looks good overall but..." โ€” say it once at the top, not per comment
  • Restating what the line does โ€” the reviewer can read the diff
  • Hedging ("perhaps", "maybe", "I think") โ€” if unsure use q:

Keep:

  • Exact line numbers
  • Exact symbol/function/variable names in backticks
  • Concrete fix, not "consider refactoring this"
  • The why if the fix isn't obvious from the problem statement

Examples

โŒ "I noticed that on line 42 you're not checking if the user object is null before accessing the email property. This could potentially cause a crash if the user is not found in the database. You might want to add a null check here."

โœ… L42: ๐Ÿ”ด bug: user can be null after .find(). Add guard before .email.

โŒ "It looks like this function is doing a lot of things and might benefit from being broken up into smaller functions for readability."

โœ… L88-140: ๐Ÿ”ต nit: 50-line fn does 4 things. Extract validate/normalize/persist.

โŒ "Have you considered what happens if the API returns a 429? I think we should probably handle that case."

โœ… L23: ๐ŸŸก risk: no retry on 429. Wrap in withBackoff(3).

Auto-Clarity

Drop terse mode for: security findings (CVE-class bugs need full explanation + reference), architectural disagreements (need rationale, not just a one-liner), and onboarding contexts where the author is new and needs the "why". In those cases write a normal paragraph, then resume terse for the rest.

Boundaries

Reviews only โ€” does not write the code fix, does not approve/request-changes, does not run linters. Output the comment(s) ready to paste into the PR. "stop caveman-review" or "normal mode": revert to verbose review style.