skills.rest
camercu
camercuCOMMUNITY
Explore all skills by this author →
GitHub

caveman-review

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

2|2|Updated Jun 28, 2015
Search Tags:#code review#feedback#pull request#github#diff#severity#review comments
One-click install
npx skills add https://github.com/camercu/dotfiles --skill caveman-review-camercu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman-review
Source: https://github.com/camercu/dotfiles/tree/main/common/.config/agents/skills/caveman-review
Command: npx skills add https://github.com/camercu/dotfiles --skill caveman-review-camercu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code review comments often bury actionable feedback in verbose, hedged prose, slowing down both reviewers and PR authors. This Skill compresses each finding into a single line containing the exact location, severity, problem, and concrete fix. ## Core Features & Use Cases - Terse Comment Format: Outputs findings as L<line>: <severity> <problem>. <fix>. with severity emoji (🔴 bug, 🟡 risk, 🔵 nit, ❓ question). - Auto-Clarity Mode: Automatically expands to full paragraphs for CVE-class security findings, architectural disagreements, and onboarding contexts, then resumes terse style. - Use Case: Paste a multi-file PR diff and receive paste-ready review comments like L42: 🔴 bug: user can be null after .find(). Add guard before .email. without writing the fixes yourself. ## Quick Start Ask the AI to review this PR diff using caveman-review and output one-line findings with severity and fixes.

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 comments for a pull request?▼

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 PR.

What severity levels does the code review output use?▼

Four severity prefixes are used: 🔴 bug for broken behavior, 🟡 risk for fragile code like races or missing null checks, 🔵 nit for style issues, and ❓ q for genuine questions. Severity is optional when findings are uniform.

Can caveman-review handle multi-file diffs?▼

Yes, multi-file diffs are supported by prefixing findings with the file path, using the format <file>:L<line>: problem. fix. Line ranges like L88-140 are also supported for findings spanning multiple lines.

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

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 cases, then terse style resumes for remaining findings.

What are the limitations of this code review approach?▼

The skill only outputs review comments; it does not write code fixes, approve or request changes on the PR, or run linters. Saying "stop caveman-review" or "normal mode" reverts to verbose review style.

Related Skills

Explore More Software Engineering Skills→
NeoLabHQNeoLabHQ
1.5k

attach-review-to-pr

Add line-specific review comments to GitHub pull requests via the gh CLI API.

Official
Intermediate
jhlee0409jhlee0409
7

afc:pr-comment

Post severity-categorized review comments to GitHub Pull Requests.

Community
Advanced
Open-PawsOpen-Paws
3

code-review

Automate layered code review for pull requests in CI pipelines.

Official
Advanced
in-the-loop-labsin-the-loop-labs
48

ai-critic

Fetches and applies AI-generated code review suggestions from pair-review.

Official
Intermediate