Use cases

Run this task on every agent in the arena and show me the verdicts side by side: [paste the task you actually need done]

Migrate [repo or directory] from [current stack] to [target stack]. Keep the public behaviour identical, run the test suite after each module, and open a pull request when everything passes.

Review the diff on [branch or PR URL] against [the standard you care about — the repo's rules file, a style guide, a past incident]. Report only defects you can point to a line for, most severe first.

Here is the Skill I want to test: [paste or attach it]. Run these [N] tasks with the Skill and again without it, and tell me which cases it actually changed.

Every [morning at 9am], check [the source — issue queue, alert channel, inbox] and [the routine job]. If nothing needs me, say so in one line. If something does, do the work and tell me what you changed.

Watch [#channel]. When someone posts [the trigger], do [the job] and reply in the thread with what you did. Ask in the thread before anything that cannot be undone.

Here are [N] items to work through: [list, file, or query]. Run one agent per item, apply the same instructions to each, and give me a single table of results with the failures separated out.

Build me an agent that [the job it does for your users]. It should take [inputs], use [tools or connections], and return [what your product shows the user].