From caveman
Generates terse, actionable code review comments in 'L<line>: <problem>. <fix>.' format. Cuts noise from PR feedback, preserves signal. Auto-triggers on pull requests.
How this skill is triggered — by the user, by Claude, or both
Slash command
/caveman:caveman-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.
Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.
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 suggestionDrop:
nit: insteadq:Keep:
❌ "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."
✅ L42: 🔴 bug: user can be null after .find(). Add guard before .email.
❌ "It looks like this function is doing a lot of things and might benefit from being broken up into smaller functions for readability."
✅ L88-140: 🔵 nit: 50-line fn does 4 things. Extract validate/normalize/persist.
❌ "Have you considered what happens if the API returns a 429? I think we should probably handle that case."
✅ L23: 🟡 risk: no retry on 429. Wrap in withBackoff(3).
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.
Reviews only — 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.
npx claudepluginhub dexpal-ai-tools/caveman --plugin cavemanProduces ultra-compressed code review comments: one line per finding with location, problem, and fix. Cuts noise while preserving actionable signal.
Generates ultra-concise PR review comments: one issue per line (L<line>: problem.fix) with severity prefixes (bug, risk, nit, question). Japanese supported. For pull request reviews.
Rewrites code review comments to sound like a human teammate by cutting AI throat-clearing, delivering direct line locations, issues, and concrete fixes. Use for PR reviews.