Skip to lesson
Exit
AI-assisted review, testing & anti-patterns1 / 3

1 min lesson

A mini Bugbot you build yourself

Show why this lesson detail matters: ".cursor/BUGBOT.md tunes the hosted reviewer."

Step 1 of 3

A mini Bugbot you build yourselfa review step as a skill

.cursor/BUGBOT.md tunes the hosted reviewer. A skill lets you build a reviewer of your own that runs locally, in your editor, on your terms. The pattern is simple: write a skill whose instruction is something like "You are an expert code reviewer. Audit this change for X, Y and Z", where X/Y/Z are your team's real risk areas, then set it to run whenever you commit new feature work.

Learn more

Full explanation

A buildable review skill (SKILL.md)

A buildable review skill (SKILL.md). Name + description drive when the agent invokes it.
name: feature-review
description: Expert code review run after feature work. Audit the diff for missing
  error handling, untested edge cases, and any call to the billing API without an
  idempotency key. Report only reproducible findings against the actual diff.
auto-run: after feature work that touches src/ or components/

When you create a skill, Cursor asks the three questions that make it governable: where to store it (project, so it's shared and committed, vs user, so it's personal), how to handle conflicts with other skills, and when it should auto-run (after any feature work touching components, only when you explicitly ask, or whenever tests or adjacent source files change). The auto-run trigger is what turns a one-off prompt into a standing review step.

Verify against the diff, not the vibe

A review skill earns its keep only if it reviews the actual diff and surfaces reproducible findings. Ask it for concrete risks against the change in front of it, then apply only the findings you can reproduce. A skill that lists generic 'best practices' is noise, the same failure mode as an untuned BugbotCursor's automated PR reviewer that posts inline findings and can push fix commits from isolated VMs. Press Enter for the full definition..

Want to know whether your rules are even being obeyed? Install a before-prompt hook that logs which rules are in context, so rule-compliance is auditable instead of assumed.

Learn more

Optional practice

Practice: a mini Bugbot you build yourself

QWhen you create a review skill, what three questions does skill creation ask, and which one turns a one-off prompt into a standing review step?