Build Loop Cursor

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.

skills.sh installs: 1.5K
GitHub stars: 233
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add buildgreatproducts/builder-os --skill build-loop-cursor --agent claude-code

Installs into .claude/skills of the current project.

Files

Cursor Build Loop

Quality-gated feature work: nothing ships on "it compiles" — every increment is built, reviewed, tested end to end, and fixed before the user hears "done."

Source of work

A plan file exists (roadmap, refactor plan, or task list with - [ ] checkboxes — search the repo): work the first unchecked task. Tasks are ordered intentionally — never skip ahead. If the plan references spec docs, read only the sections relevant to the current task.
No plan (or the request is outside it): build from the user's prompt. Restate it as a verifiable goal with 2–4 success criteria and confirm scope in one message before building.

The loop

Run per task (or per prompted feature). Do not advance until every step passes.

Build. Implement exactly what the task specifies. Simplest implementation that satisfies it, surgical changes, no speculative scope. Match existing project conventions.

SKILL.md on GitHub