skills.rest
shirulot
shirulotCOMMUNITY
Explore all skills by this author →
GitHub

caveman-review

Generate concise code review comments from pull request diffs.

Updated Jul 6, 2026
Search Tags:#automation#software engineering#code review#pull request#productivity#refactoring
One-click install
npx skills add https://github.com/shirulot/codex-skill --skill caveman-review-shirulot
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman-review
Source: https://github.com/shirulot/codex-skill/tree/main/caveman-review
Command: npx skills add https://github.com/shirulot/codex-skill --skill caveman-review-shirulot

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates noise, hedging, and repetitive pleasantries in code reviews, allowing developers to focus purely on actionable technical feedback.

Core Features & Use Cases

  • Terse Formatting: Enforces a strict one-line format per finding, including location, problem, and concrete fix.
  • Severity Tagging: Uses standardized emoji prefixes to distinguish between critical bugs, risks, nits, and questions.
  • Auto-Clarity: Automatically switches to verbose mode for complex security or architectural issues while maintaining brevity for standard code quality feedback.

Quick Start

Invoke the review process by typing /caveman-review when analyzing a pull request diff.

Frequently Asked Questions about caveman-review

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

FAQPage Schema
How do I get concise code review feedback on a pull request without conversational filler?▼

To get concise code review feedback, the caveman-review Skill generates actionable comments by stripping pleasantries and enforcing a strict location-problem-fix syntax. It provides immediate, high-signal feedback on pull request diffs.

How does automated code review severity tagging work for identifying bugs and risks?▼

Automated code review severity tagging works by using standardized emoji prefixes to distinguish between critical bugs, risks, nits, and questions. This visual hierarchy helps developers quickly prioritize pull request fixes.

What is the best way to format code review comments for high signal and low noise?▼

The best way to format code review comments is using a strict one-line format per finding that includes the location, problem, and concrete fix. This eliminates hedging and repetitive noise, focusing purely on actionable technical feedback.

Can automated code review tools switch to verbose mode for complex architectural discussions?▼

Yes, automated code review tools like this Skill can switch to verbose mode for complex security or architectural issues. It automatically adjusts feedback depth while maintaining brevity for standard code quality improvements.

How do I run an automated code review on a pull request diff?▼

To run an automated code review, invoke the review process by typing /caveman-review when analyzing a pull request diff. The Skill then parses code changes to identify bugs, risks, and stylistic improvements.

What are the limitations of strict one-line code review formats?▼

The limitation of strict one-line code review formats is that complex security or architectural issues cannot be adequately summarized in a single line. The tool mitigates this by automatically switching to verbose mode for these complex contexts.

Related Skills

Explore More Software Engineering Skills→
achmfachmf

caveman-review

Parse pull request diffs and output one-line bug, risk, and style suggestions.

Community
Basic
elijahmurrayelijahmurray
2

pr-implement-feedback

Implements Pull request review feedback by executing a dedicated command.

Community
Basic
FullFranFullFran
1

pr-flow

Enforce branch naming, PR descriptions, and review processes for pull requests.

Community
Intermediate
austinwilcoxaustinwilcox
1

caveman-review

Generate one-line code review comments with locations and fixes for PR diffs.

Community
Basic