caveman-review

PurposeThe caveman-review skill generates ultra-compressed code review comments. Each finding is a single line: location, problem, fix. Supports four severity prefixes (🔴 bug/🟡 risk/🔵 nit/❓ q), strips filler like "I noticed" or "you might want to". Key output: one-line review comments ready to paste into PRs, dramatically reducing reading burden while preserving all actionable signals.

Domains

Coding

Forms

Workflow

Required Tools

—None

Languages

—No strong dependency

Package Manager

—N/A

Skill Composition

SKILL.md50.0%
other50.0%

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger

User explicitly requests PR review: "review this PR", "code review", "review the diff", "/review", or /caveman-review.
Auto-triggers when the model is reviewing pull requests.

Mechanism

Each finding follows a fixed format: L<line>: <problem>. <fix>. or <file>:L<line>: ... (for multi-file diffs).
Optional severity prefix (🔴 bug / 🟡 risk / 🔵 nit / ❓ q) strips filler automatically.
Only outputs review comments — does not write code fixes, approve/reject, or run linters.
Auto-Clarity: switches to full paragraphs for security findings and architectural disagreements.

Result

One-line actionable review comments ready to paste into PR platforms.
Each comment includes: location, severity, problem, fix.
Reviewers and authors understand issues quickly without decoding verbose filler.

Use Cases

Two Typical Use Cases

Scenario 01

Daily PR code review

When a developer submits a PR and needs peer review, the user says "review this PR", "code review", "/review", or `/caveman-review`. The agent automatically reviews the diff and outputs one-line comments like `L42: 🔴 bug: user can be null after .find(). Add guard before .email.`, allowing both reviewer and author to quickly locate and understand each issue.

Scenario 02

Security and architecture-level deep review

For CVE-class security vulnerabilities or architectural disagreements requiring detailed explanation, caveman-review has a built-in Auto-Clarity mechanism: it switches to full paragraph explanation with rationale for critical findings, then resumes terse style afterward. This balances brevity with depth, ensuring important matters are not over-compressed.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md50.0%
other50.0%

▸skills/caveman-review/
▸caveman-review
- ·README.md
- ·SKILL.md

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.