What problem does it solve? Code review feedback is often buried under hedging, filler phrases, and restated diff content, making it slow to write and slow to act on. This Skill compresses PR feedback into terse, actionable one-line comments without losing the technical signal. ## Core Features & Use Cases - One-line comment format: Each finding follows L<line>: <severity> <problem>. <fix>. with exact line numbers and backticked symbol names. - Severity tagging: Uses emoji prefixes to classify findings — 🔴 bug, 🟡 risk, 🔵 nit, ❓ question — so authors can triage at a glance. - Auto-clarity mode: Automatically switches to full explanations for CVE-class security findings, architectural disagreements, and onboarding contexts, then resumes terse output. - Use Case: Paste a pull request diff and ask for a review; receive a ready-to-paste list of comments like L42: 🔴 bug: user can be null after .find(). Add guard before .email. ## Quick Start Ask the assistant to review this pull request diff using caveman-review and output one-line comments with severity tags.
