caveman-review

Generates concise, actionable pull request code review comments with severity levels.

1|Updated Feb 19, 2025
One-click install
npx skills add https://github.com/trystan2k/favoritable-old --skill caveman-review-trystan2k
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: caveman-review
Source: https://github.com/trystan2k/favoritable-old/tree/main/.agents/skills/caveman-review
Command: npx skills add https://github.com/trystan2k/favoritable-old --skill caveman-review-trystan2k

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Pull request code reviews are often cluttered with unnecessary fluff, hedging, and restated context that buries actionable feedback and wastes both reviewer and author time. This skill eliminates that noise to deliver clear, direct review comments that highlight issues and fixes instantly.

Core Features & Use Cases

  • One-line actionable findings: Each comment includes exact line location, severity level, clear problem statement, and concrete fix, with no redundant throat-clearing or restated context.
  • Standardized severity tagging: Uses clear emoji prefixes (🔴 bug, 🟡 risk, 🔵 nit, ❓ question) to help authors prioritize feedback instantly.
  • Context-aware clarity mode: Automatically expands to detailed explanations for high-severity security vulnerabilities, architectural disagreements, or onboarding scenarios where extra context is required, then reverts to terse mode for all other findings.
  • Use case: When reviewing a PR with a missing null check after a database .find() call, the skill outputs a single line pointing to the exact line, flagging it as a bug, and suggesting the exact guard to add, instead of a long paragraph re-explaining what the code does.

Quick Start

Use the caveman-review skill to generate terse, actionable code review comments for the current open 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 write concise code review comments for a pull request?

Concise pull request code review comments are generated by compressing feedback into one-line actionable findings that include exact line locations, severity tags, problem statements, and concrete fixes without redundant context.

What is severity tagging in actionable code review feedback?

Severity tagging in code review feedback uses standardized emoji prefixes like red circle for bugs, yellow circle for risks, blue circle for nits, and question mark for questions to help authors prioritize pull request findings instantly.

Can I use terse code review comments for high-severity security vulnerabilities?

Yes, you can use terse code review comments for security vulnerabilities because the system automatically expands into a detailed clarity mode for high-severity security issues, architectural disagreements, or onboarding scenarios before reverting to terse mode.

Does this pull request review approach work across any programming language?

Yes, this pull request review approach applies to all programming languages and codebases, automatically adjusting its output format to deliver scannable, actionable feedback regardless of the specific technology stack being reviewed.

Why are my pull request code reviews cluttered with unnecessary context?

Pull request code reviews are cluttered because traditional feedback often includes hedging and restated context that buries actionable findings, which can be solved by generating ultra-compressed comments that highlight exact issues and fixes instantly.

When should I not use ultra-compressed comments for code review?

You should not use ultra-compressed comments when dealing with architectural discussions, high-severity security vulnerabilities, or onboarding contexts, as these scenarios require expanded explanations to provide the necessary clarity for the author.