skills.rest
g-lok
g-lokCOMMUNITY
Explore all skills by this author →
GitHub

caveman-review

Generate one-line code-review comments from pull request diffs.

1|Updated Feb 13, 2018
Search Tags:#automation#code-review#pull-request#review-comments#diff-analysis
One-click install
npx skills add https://github.com/g-lok/gs-dotfiles --skill caveman-review-g-lok
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman-review
Source: https://github.com/g-lok/gs-dotfiles/tree/main/install.d/dotfiles/ai_skills/.agents/skills/caveman-review
Command: npx skills add https://github.com/g-lok/gs-dotfiles --skill caveman-review-g-lok

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ultra-compact code-review comments that cut noise from PR feedback while preserving 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 per finding with explicit location, problem, and fix in a consistent format.
  • Supports single-file and multi-file diffs using the L<line> style for precise references.
  • Severity prefixes allow prioritization (e.g., 🔴 bug:, 🟡 risk:, 🔵 nit:, ❓ q:).
  • Auto-triggers during PR review contexts and when invoked via /caveman-review.

Quick Start

Submit a pull request to caveman-review and receive one-line, location-aware feedback 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 from a pull request diff?▼

To generate concise code review comments from a pull request diff, use an automated tool to parse the diff and output one-line findings. Each comment includes the location, problem, and suggested fix in a consistent L<line> style format.

What is the best way to automate PR feedback and cut noise from review comments?▼

The best way to automate PR feedback and cut noise is to generate terse, actionable review comments that preserve signal. This approach outputs one line per finding with explicit location, problem, and fix details, avoiding verbose explanations.

Can I review multi-file diffs and still get precise line references for each finding?▼

Yes, you can review multi-file diffs and get precise line references for each finding. The diff analysis supports both single-file and multi-file PRs, using the L<line> style to ensure accurate location tracking across all changed files.

How does severity prefixing work in automated code review outputs?▼

Severity prefixing in automated code review outputs works by adding visual tags to categorize findings. Prefixes like bug, risk, nit, and q allow developers to quickly prioritize pull request feedback and address critical issues first.

When should I use terse one-line comments instead of detailed review explanations?▼

Use terse one-line comments instead of detailed explanations when you need to reduce reading friction during pull request reviews. This format is ideal for rapid diff analysis where location, problem, and fix can be stated in a single line without losing actionable context.

Related Skills

Explore More Software Engineering Skills→
guhans6guhans6

caveman-review

Generate code review comments with severity levels for pull requests.

Community
Basic
vnatarajan4061vnatarajan4061

resolve-pr

Resolves GitHub pull-request comment threads, optionally filtered by author or bots.

Community
Intermediate
adryanevadryanev
2

review-pr

Post inline code review comments on GitHub pull requests using the gh CLI.

Community
Advanced
jorgealvesjorgealves
2

pedagogical-code-grader

Automate conceptual grading of student code submissions using AST analysis and rubrics.

Community
Intermediate