Summary
Strips all the fluff from code review comments and delivers pure signal. Each finding is one line: exact location, what's broken, how to fix it. Uses severity prefixes for bugs versus nits, drops throat-clearing phrases like "you might consider", and focuses on actionable feedback with concrete variable names and line numbers. Automatically kicks in when you ask Claude to review a PR or diff. Saves tons of time when you're grinding through review queues and need to give quality feedback without writing novels. Switches back to verbose mode for security issues or when onboarding new developers who need the extra context.
Install to Claude Code
npx -y skills add juliusbrussee/caveman --skill caveman-review --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
