caveman-review

Generate one-line code review comments with location, problem, and fix.

Updated Apr 23, 2026
One-click install
npx skills add https://github.com/fableindigo-gif/animated-system --skill caveman-review-fableindigo-gif
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: caveman-review
Source: https://github.com/fableindigo-gif/animated-system/tree/main/omnianalytix-mirror/.agents/skills/caveman-review
Command: npx skills add https://github.com/fableindigo-gif/animated-system --skill caveman-review-fableindigo-gif

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

Core Features & Use Cases

  • One-line findings: Each issue is reported as a single line containing location, problem, and fix.
  • Format enforcement: Use the exact L<line>: <problem>. <fix>. syntax or <file>:L<line>: ... for multi-file diffs, with optional severity prefixes like 🔴 bug:, 🟡 risk:, 🔵 nit:, ❓ q: for mixed findings.
  • Drop & Keep rules: Drop hedging phrases and filler, keep precise numbers, identifiers, and concrete fixes.
  • Output clips: Ready-to-paste review comments suitable for PR threads.

Quick Start

Provide a pull request diff and I will generate concise one-line comments for each finding.

Frequently Asked Questions about caveman-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write concise code review comments for pull requests?

The format uses L<line>: <problem>. <fix>. for single files and <file>:L<line>: ... for multi-file diffs. Optional severity prefixes like 🔴 bug:, 🟡 risk:, 🔵 nit:, and ❓ q: can be added to guide prioritization.

How do I automate terse inline reviews for multi-file diffs?

It auto-triggers when reviewing pull requests or when a user says "review this PR", "code review", "review the diff", or invokes /caveman-review, generating line-precise findings across all changed files.

Can I prioritize code review findings by severity in PR comments?

Each prefixed comment remains a single line combining location, problem, and fix, ensuring the prioritized feedback stays ultra-brief and actionable within automated review triggers.

What is the best way to reduce noise in automated code review feedback?

This approach ensures automated pull request reviews output ultra-compressed comments that deliver high signal without overwhelming the developer with verbose explanations.