Caveman Review

If you're tired of PR comments that bury the fix in three paragraphs of throat-clearing, this is the antidote. It strips code review down to location, problem, fix. One line per finding. You get `L42: 🔴 bug: user can be null after .find(). Add guard before .email.` instead of "I noticed that you might want to consider..." It keeps severity prefixes when issues are mixed (bug/risk/nit/question), drops all hedging and restating, and knows when to break its own rules for security issues or onboarding contexts. Invoke it with "/review" or "/caveman-review" and paste the output straight into GitHub. It won't write the fix or approve the PR, just give you the actionable signal without the noise.

GitHub stars: 504
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill caveman-review --agent claude-code

Installs into .claude/skills of the current project.

Files

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

Rules

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

Severity prefix (optional, when mixed):

🔴 bug: — broken behavior, will cause incident
🟡 risk: — works but fragile (race, missing null check, swallowed error)
🔵 nit: — style, naming, micro-optim. Author can ignore
❓ q: — genuine question, not a suggestion

Drop:

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

Keep: