caveman-review

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

Updated Aug 7, 2026
One-click install
npx skills add https://github.com/Sambhav242005/Major-Project --skill caveman-review-sambhav242005
Or copy as Structured Prompt for Agentβ–Ό
Please help me install this Agent Skill.
Skill: caveman-review
Source: https://github.com/Sambhav242005/Major-Project/tree/main/.continue/skills/caveman-review
Command: npx skills add https://github.com/Sambhav242005/Major-Project --skill caveman-review-sambhav242005

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? PR review feedback is often buried in verbose, hedged prose that obscures the actionable point. This Skill compresses code review comments into single lines containing the exact location, severity, problem, and concrete fix, so authors can act on feedback immediately. ## Core Features & Use Cases - Terse Comment Format: Outputs findings as L<line>: <severity> <problem>. <fix>. with severity emoji (πŸ”΄ bug, 🟑 risk, πŸ”΅ nit, ❓ question). - Noise Filtering: Drops throat-clearing, hedging, per-comment praise, and restatements of what the diff already shows, while keeping exact line numbers, backticked symbols, and concrete fixes. - Auto-Clarity Mode: Switches to full explanatory paragraphs for CVE-class security findings, architectural disagreements, and onboarding contexts, then resumes terse output. - Use Case: Paste a multi-file pull request diff and receive ready-to-post review comments like L42: πŸ”΄ bug: user can be null after .find(). Add guard before .email. ## Quick Start Ask the AI to review this pull request 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 generate concise code review comments for a pull request?β–Ό

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

What format do the code review comments use?β–Ό

Each comment follows the pattern L<line>: <severity> <problem>. <fix>. with an optional file prefix for multi-file diffs. Severity emoji indicate πŸ”΄ bug, 🟑 risk, πŸ”΅ nit, or ❓ question.

When does terse mode switch to detailed explanations?β–Ό

Terse mode is dropped for CVE-class security findings, architectural disagreements, and onboarding contexts where the author needs the reasoning. A normal paragraph is written for those findings, then terse output resumes.

Can this skill approve PRs or run linters?β–Ό

No. It only produces review comment text. It does not write code fixes, approve or request changes on the PR, or execute linters; the output is meant to be pasted into the review manually.

How do I turn off terse review mode?β–Ό

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