caveman-review

SKILL.md

Ultra-compressed code review comments: location, problem, fix on one line each.

Format: L<line>: <problem>. <fix>. with optional severity prefix (🔴 bug:, 🟡 risk:, 🔵 nit:, ❓ q:) for mixed findings

Strips filler language ("I noticed", "you might want", "great work") and restates—keeps exact line numbers, symbol names, concrete fixes, and the why when non-obvious

Auto-triggers on "review this PR", "code review", "/review", or /caveman-review; outputs comments ready to paste into pull requests

Reverts to verbose style on request; escalates security findings, architectural disagreements, and onboarding contexts to full explanations

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: