Summary
A structured code review assistant that walks you through changes step by step instead of dumping everything at once. When you say "checkpoint" or "human review," it kicks off a workflow that starts with orientation and context, then progressively dives into details. It's explicitly designed to front-load information in single coherent messages rather than ask questions mid-stream, which is refreshing if you hate the chatbot back-and-forth. Relies on a customization system with team and personal overrides, and references implementation artifacts from a bmm config. Best for teams who want consistent review rituals without the usual LLM conversation sprawl.
Install to Claude Code
npx -y skills add bmad-code-org/bmad-method --skill bmad-checkpoint-preview --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
