This is a disciplined build process for Cursor that stops you from shipping half-tested code. It enforces a loop: implement the task, run /review and fix everything it finds, test the actual user flow including edge cases, then fix again until clean. It works from plan files with checkboxes or from direct prompts, and it won't let you skip to the next task while tests are broken. The review step checks against design tokens if your project has them, which catches hardcoded colors before they ship. Honest about what it is: a forcing function for the boring verification work you know you should do but often don't when you're moving fast.
npx -y skills add buildgreatproducts/builder-os --skill build-loop-cursor --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
kubesphere/kubesphere
supercent-io/skills-template