Cursor & AI Coding prompts

Agent-ready prompts for building features, fixing bugs and auditing repos.

Save time. Work smarter.

Jump straight into search and find the prompt you need.

Cursor

Brief a coding agent to ship a feature by matching local patterns, touching only the files that matter.

Cursor

Force the agent to reproduce the bug, write or run a failing test, then apply a minimal fix.

Cursor

Run a structured audit: correctness, security, a11y, and dead code — with file:line findings, not vibes.

Cursor

Ask the agent to polish a screen using existing design tokens, with mobile and dark mode in the same pass.

Cursor

Add tests that match the repo's runner and style, covering the behaviour that would actually break users.