# Caveman Review

> Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the 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.

Source: https://skillsagentes.com/skills/juliusbrussee/caveman/caveman-review
Repository: https://github.com/JuliusBrussee/caveman
Author: juliusbrussee
License: MIT
Updated: hace 3 meses
Context cost: 78 tok installed, 685 tok once triggered, 987 tok with every bundled file
Bundle: 2 files, 4 KB
Permissions requested: none declared

## Install

```bash
npx -y skills add JuliusBrussee/caveman --skill caveman-review --agent claude-code
```

## What it does

- Genera comentarios de revisión de código tersos y accionables: una línea por hallazgo con ubicación, problema y fix concreto, formato `L<línea>: <problema>. <fix>.`
- Usa prefijos de severidad opcionales (🔴 bug, 🟡 risk, 🔵 nit, ❓ q) cuando hay hallazgos mixtos.
- Elimina frases de relleno ("I noticed that...", "you might want to consider...") y hedging; con duda real usa el prefijo `q:` en vez de suavizar.
- Para hallazgos de seguridad clase CVE, desacuerdos de arquitectura, u onboarding de autores nuevos, escribe un párrafo normal con contexto completo en vez de comprimir a una línea.

## Use it when

- El usuario dice "review this PR", "code review", "/review" o invoca /caveman-review.
- Al revisar pull requests (auto-trigger según el archivo).

## What triggers it

- "/caveman-review"
- "revisa este PR"
- "dame comentarios de review para este diff"

## Before you install

- Ninguno: solo revisa, el archivo dice explícitamente que no escribe el fix, no aprueba/rechaza el PR ni corre linters.

## Files

- README.md — 1 KB
- SKILL.md — 3 KB

## SKILL.md

Reproduced verbatim from JuliusBrussee/caveman under MIT. This section is the upstream document and is in English.

Write code review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.

## Rules

**Format:** `L<line>: <problem>. <fix>.` — or `<file>:L<line>: ...` when reviewing multi-file diffs.

**Severity prefix (optional, when mixed):**
- `🔴 bug:` — broken behavior, will cause incident
- `🟡 risk:` — works but fragile (race, missing null check, swallowed error)
- `🔵 nit:` — style, naming, micro-optim. Author can ignore
- `❓ q:` — genuine question, not a suggestion

**Drop:**
- "I noticed that...", "It seems like...", "You might want to consider..."
- "This is just a suggestion but..." — use `nit:` instead
- "Great work!", "Looks good overall but..." — say it once at the top, not per comment
- Restating what the line does — the reviewer can read the diff
- Hedging ("perhaps", "maybe", "I think") — if unsure use `q:`

**Keep:**
- Exact line numbers
- Exact symbol/function/variable names in backticks
- Concrete fix, not "consider refactoring this"
- The *why* if the fix isn't obvious from the problem statement

## Examples

❌ "I noticed that on line 42 you're not checking if the user object is null before accessing the email property. This could potentially cause a crash if the user is not found in the database. You might want to add a null check here."

✅ `L42: 🔴 bug: user can be null after .find(). Add guard before .email.`

❌ "It looks like this function is doing a lot of things and might benefit from being broken up into smaller functions for readability."

✅ `L88-140: 🔵 nit: 50-line fn does 4 things. Extract validate/normalize/persist.`

❌ "Have you considered what happens if the API returns a 429? I think we should probably handle that case."

✅ `L23: 🟡 risk: no retry on 429. Wrap in withBackoff(3).`

## Auto-Clarity

Drop terse mode for: security findings (CVE-class bugs need full explanation + reference), architectural disagreements (need rationale, not just a one-liner), and onboarding contexts where the author is new and needs the "why". In those cases write a normal paragraph, then resume terse for the rest.

## Boundaries

Reviews only — does not write the code fix, does not approve/request-changes, does not run linters. Output the comment(s) ready to paste into the PR. "stop caveman-review" or "normal mode": revert to verbose review style.

---

Skills Agentes — https://skillsagentes.com/skills/juliusbrussee/caveman/caveman-review