domains / families / agent-tooling / goal-test

goal-test

separate

Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent. Use when the user wants to run an agent in a loop, asks how to know when an agent task is finished, or says a goal like "improve X" needs to become checkable. Do NOT use for building eval suites over many cases — that is evals-bootstrap.

When to use

• running an agent in a loop
• determining when an agent task is finished
• making a goal like 'improve X' checkable
• generating a goal-test script
• wrapping an agent in a bounded retry loop

When not to use

• building eval suites over many cases

Skill page

Source