caveman-review

Generates one-line code review comments with line numbers, severity, and concrete fixes.

1|Updated May 3, 2021
One-click install
npx skills add https://github.com/leogurja/dotfiles --skill caveman-review-leogurja
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman-review
Source: https://github.com/leogurja/dotfiles/tree/main/home/dot_agents/skills/caveman-review
Command: npx skills add https://github.com/leogurja/dotfiles --skill caveman-review-leogurja

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code review comments often bury the actual finding under hedging, filler phrases, and restatements of the diff, slowing down both reviewers and PR authors. This Skill produces terse, actionable review comments that state the location, problem, and fix in a single line. ## Core Features & Use Cases - One-line findings: Outputs comments in the format L<line>: <severity> <problem>. <fix>. with exact line numbers and backticked symbol names. - Severity tagging: Classifies findings as bug, risk, nit, or question using emoji prefixes so authors can triage quickly. - Auto-clarity mode: Automatically switches to full explanations for security findings, architectural disagreements, and onboarding contexts, then resumes terse output. - Use Case: Paste a pull request diff and ask for a review; receive paste-ready comments like L42: bug: user can be null after .find(). Add guard before .email. ## Quick Start Ask the assistant to review this PR diff using caveman-review and output 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 get terse one-line code review comments for a PR?▼

Invoke the skill with /caveman-review or phrases like "review this PR" or "review the diff". It outputs one line per finding in the format L<line>: severity, problem, fix, ready to paste into the pull request.

What severity levels does the code review output use?▼

Findings are tagged as bug (broken behavior), risk (fragile but working code), nit (style or minor issues), or question. Each uses an emoji prefix so authors can triage comments by severity at a glance.

Does caveman-review approve or request changes on pull requests?▼

No. The skill only outputs review comments; it does not approve, request changes, write code fixes, or run linters. You paste the generated comments into the PR yourself.

When does the review switch from terse to detailed explanations?▼

Terse mode is dropped automatically for CVE-class security findings, architectural disagreements, and onboarding contexts where the author needs the reasoning. After those findings, output resumes in one-line format.

How do I turn off terse review mode?▼

Say "stop caveman-review" or "normal mode" and the assistant reverts to standard verbose review style for subsequent feedback.