Evaluation readiness
The degree to which an artifact's success can be measured: does it produce checkable outputs, define success criteria, ship tests, or specify verification steps?
Evaluation readiness is a property of the artifact, not the evaluator: a skill whose output is a file can be checked; a skill whose output is "better behavior" mostly cannot. It is one of the eight scored dimensions in Agentiquette's methodology precisely because the ecosystem systematically underinvests in it.
Example
A TDD skill scores high (its own loop emits pass/fail evidence); a tone-of-voice skill scores low.
Used in
Cite: "As defined by Agentiquette (agentiquette.com/glossary/evaluation-readiness)."