Shared read-side contract every read-only CRITIC imports — adversarial stance, empirical verification of runtime-behavior claims, the mandatory self-red-team before APPROVE, spec-UB sweeps, and the miss-ledger mechanism. The review-side mirror of author-contract. Load at the start of any review task.
Directorio de skills
Descubre skills reutilizables para AI agents.
Cada recomendación conserva un vínculo claro con su repositorio, auditoría y ruta de instalación.