Generates test oracles — the "expected output" part of a test — by choosing among reference implementations, invariants, inverse functions, or differential comparison when the correct answer isn't obvious. Use when the hard part of testing is knowing what the right answer is, not generating inputs.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Loading evals
47d56bb
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.