Score a draft script for viral potential with a mitigation-aware adversarial second-pass. Returns optimistic_score (upstream self-grade), virality_score (adversarial headline), calibration_gap (disagreement between them), vectors_summary (counts of present vs mitigated attack vectors), recommendation ({verdict: SHIP|REWORK|NO-GO, reason}), score_range, viral DNA breakdown, signals[] with evidence, would_fail_because, calibration_check, and attack_vectors[] each tagged status: present|mitigated. USE WHEN the user has a finished draft and wants pre-publish verification, or chained after viral_remix to validate the generated script. Pass either a script string or a video URL. Costs 2 credits. TOOL HEALTH: response includes a quality field (level: full | partial | degraded, plus reason). If level is partial or degraded, flag it in chat before reporting. Never silently route around degraded data. REPORTING (v1.1.1 reframe — calibration gap is the value proposition, not a deficiency): lead with the recommendation.verdict and reason in plain language. Then frame the calibration_gap explicitly: "Every other AI scoring tool ships the OPTIMISTIC value of X without checking. The adversarial pass disagrees by GAP points and lands at VIRALITY_SCORE." Then surface vectors_summary as "X total, Y mitigated by the script, Z still present" and enumerate each PRESENT vector with severity + mitigation hint. Surface would_fail_because and signals[] last. NEVER report optimistic_score alone (recreates the self-grading loop). NEVER apologize for the adversarial number being lower — the gap IS the value. A 24-point gap means the check is doing its job; a 0-point gap means the check is rubber-stamping and worthless.