4 tagged adversarial-evaluation, measured the same way as everything else here.
Skill Claude CodeCodex
CRUCIBLE: a Claude-only adversarial expert workshop that stress-tests a scientific paper and then, opt-in, rebuilds it. ACT I (TRIBUNAL): from the paper PDF (plus a few public cited works it fetches), a topic-adapted fleet of expert referee subagents (every contested claim argued from at least two COMPETING…
Skill Claude CodeCodex
Part of ade
This skill should be used when the user asks about evaluation methodology, scoring rubrics, testing tools, "how does scoring work", "evaluation criteria", "rubric format", "add a rubric", "create testing tool", "evaluate my feature", "run evaluation", "why did evaluation fail", or needs guidance on adversarial…
Skill Claude CodeCodex
Part of ade
Use when asking about the ADE build process, how the generator works, iteration strategy, "why is the generator doing X", "how does building work", "commit conventions", "pivot vs refine", or understanding the implementation phase of the ADE workflow. This skill covers the Generator's methodology for implementing…
Skill Claude CodeCodex
Part of ade
Use when the user wants to plan any work — building an app, adding a feature, fixing a bug, solving a problem, refactoring, or any task that benefits from thinking before doing. Triggers on "plan", "build me", "I want to", "fix this", "add a", "we need to", "how should we", or when the user describes something they…