skills.rest
marketiv-id
marketiv-idOFFICIAL
Explore all skills by this author →
GitHub

caveman-review

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

Updated Feb 24, 2026
Search Tags:#code review#feedback#pull request#github#diff#severity#review comments
One-click install
npx skills add https://github.com/marketiv-id/marketiv-web --skill caveman-review-marketiv-id
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman-review
Source: https://github.com/marketiv-id/marketiv-web/tree/main/.qwen/skills/caveman-review
Command: npx skills add https://github.com/marketiv-id/marketiv-web --skill caveman-review-marketiv-id

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code review feedback is often buried in verbose, hedged prose that slows down both reviewers and authors. This Skill compresses PR review comments into single actionable lines, removing filler while preserving line numbers, symbol names, and concrete fixes. ## Core Features & Use Cases - Terse Comment Format: Outputs each finding as L<line>: <severity> <problem>. <fix>. with severity emoji (🔴 bug, 🟡 risk, 🔵 nit, ❓ question). - Noise Filtering: Drops hedging, throat-clearing, and restatements of the diff while keeping exact line numbers, backticked symbols, and concrete fixes. - Auto-Clarity Mode: Switches to full explanations for CVE-class security findings, architectural disagreements, and onboarding contexts, then resumes terse output. - Use Case: A reviewer pastes a multi-file pull request diff and receives paste-ready one-line comments like L42: 🔴 bug: user can be null after .find(). Add guard before .email. ## Quick Start Ask the assistant to review this pull request and output caveman-style 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 write concise code review comments for a pull request?▼

Use the format L<line>: <severity> <problem>. <fix>. with one line per finding. Prefix with a severity marker like 🔴 bug, 🟡 risk, 🔵 nit, or ❓ question, and always include a concrete fix rather than a vague suggestion.

What severity levels should code review comments use?▼

This Skill uses four levels: 🔴 bug for broken behavior, 🟡 risk for fragile code like missing null checks or swallowed errors, 🔵 nit for style issues the author can ignore, and ❓ question for genuine clarifications.

When should code review feedback be verbose instead of terse?▼

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

Does this code review tool approve PRs or run linters?▼

No. It only outputs review comments ready to paste into a pull request. It does not write code fixes, approve or request changes, or execute linters or any other tooling.

Can caveman-review handle multi-file diffs?▼

Yes. For multi-file diffs the comment format extends to <file>:L<line>: <problem>. <fix>. so each finding is anchored to both the file and the exact line number.

Related Skills

Explore More Software Engineering Skills→
crbnoscrbnos
2.4k

self-review

Reviews the full branch diff against main and reports must-fix issues, risks, and docs freshness.

Official
Intermediate
generic-automation-and-itgeneric-automation-and-it

ai-review

Parses AI pull request reviews and applies fix or skip decisions on GitHub.

Official
Advanced
Open-PawsOpen-Paws
3

code-review

Automate layered code review for pull requests in CI pipelines.

Official
Advanced
stacklokstacklok
2.0k

pr-inline-review

Submit inline review comments and code suggestions to GitHub Pull Requests via gh CLI.

Official
Intermediate