Skip to content
caveman-review logo

Caveman Review

caveman-review

Ultra-compressed code review comments: location, problem, fix on one line each.

SKILL.md

Full skill instructions

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.

More Code Review & Quality skills

azure-enterprise-infra-planner logo
Code Review & Quality

azure-enterprise-infra-planner

Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.

1.5K 454.3K
View
requesting-code-review logo
Code Review & Quality

requesting-code-review

Dispatch code review subagents with focused context to catch issues before they compound.

295.4K 245.8K
View
executing-plans logo
Code Review & Quality

executing-plans

Execute a written implementation plan with critical review and task checkpoints.

295.4K 229.1K
View
subagent-driven-development logo
Code Review & Quality

subagent-driven-development

Dispatch fresh subagents per task with two-stage review (spec compliance, then code quality) in the current session.

295.4K 221.7K
View
seo-audit logo
Code Review & Quality

seo-audit

Comprehensive SEO auditing framework covering crawlability, indexation, speed, on-page optimization, and content quality.

53.3K 220.8K
View
receiving-code-review logo
Code Review & Quality

receiving-code-review

Evaluate code review feedback with technical rigor before implementing, avoiding performative agreement and blind implementation.

295.4K 208.8K
View
gpt-image-2 logo
Code Review & Quality

gpt-image-2

Generate images via your ChatGPT subscription using text-to-image, image editing, and style transfer.

16 169.5K
View
mcp-builder logo
Code Review & Quality

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

179.7K 122.7K
View
elevenlabs-music-generation logo
Code Review & Quality

elevenlabs-music-generation

Generate studio-quality songs and instrumentals from text descriptions, 5 seconds to 5 minutes, with section-level structure control.

52 116.9K
View
site-architecture logo
Code Review & Quality

site-architecture

Plan and optimize your website's page hierarchy, navigation, URL structure, and internal linking.

53.3K 112.8K
View
workers-best-practices logo
Code Review & Quality

workers-best-practices

Cloudflare Workers code review and authoring against production best practices.

3K 100.4K
View
brand-guidelines logo
Code Review & Quality

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

179.7K 100.1K
View

Coding & apps AI tools

Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View
Imagica logo
Coding & apps

Imagica

Build a no-code AI app in minutes.

Freemium
View
E
Coding & apps

Emergent.sh

An IDE for code migration from legacy to modern frameworks through coding agents.

Freemium
View
Wonder Dynamics logo
Coding & apps

Wonder Dynamics

Automate CGI animation in live-action scenes

Paid
View
M
Coding & apps

Mixo

Launch a website in seconds with AI.

Paid
View
AI Code Convert logo
Coding & apps

AI Code Convert

Streamline Your Coding Experience with AI Code Helper

Free
View