Skill · Testing
cavecrew
Testingmcpso
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline...
Install
$
npx skills add juliusbrussee/caveman --skill cavecrewGeneric steps — the original listing is authoritative. Copy the command, run it where you keep agent skills, then confirm version and requirements in the original listing.
At a glance
- Decision guide for delegating to caveman-style subagents.
- Published by juliusbrussee — listed by mcpso. Setup details live in the original listing.
How to use
- Copy the Install command above.
- Run it where you keep agent skills.
- Confirm version and requirements in the original listing.
More in Testing
- tdd — Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green
- diagnose — Disciplined diagnosis loop for hard bugs and performance regressions.
- caveman-review — Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Eac
- minimal-run-and-audit — Rigor Run skill for README-first deep learning repo reproduction.
- diagnosing-bugs — Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or r
- receiving-code-review — Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear
More from juliusbrussee
- caveman — Compressed caveman-mode agent workflows
- caveman-commit — Write concise conventional commit messages
- caveman-learn — Learn in compressed caveman mode
- safe-refactor — Refactor code safely
← Back to Skills catalog · View original listing ↗
Outdated or wrong? Report this listing.