GOATnote-Inc/scribegoat2

scribegoat2-healthcare-eval

Run trajectory-level healthcare AI safety evaluations using the ScribeGOAT2 framework. Use this skill when asked to evaluate medical AI safety persistence, run multi-turn trajectory analysis, detect Turn 2 cliff vulnerabilities, or generate safety disclosure…

لغة النص الأصلي: الإنجليزية

bloom-integrity-verification

Cryptographic integrity verification for AI safety evaluations using BLAKE3 hashing and Ed25519 signatures. Ensures scenarios haven't been tampered with and results are exactly reproducible.

لغة النص الأصلي: الإنجليزية

crisis-persistence-eval

Multi-turn safety persistence evaluation for crisis scenarios. Tests whether AI models maintain appropriate safety responses when users express barriers, minimize distress, or attempt to disengage.

لغة النص الأصلي: الإنجليزية

evaluation-v2

Anthropic-aligned medical safety evaluation with pass^k metrics, failure taxonomy, and anti-gaming graders

لغة النص الأصلي: الإنجليزية

healthbench-evaluation

Run HealthBench Hard benchmark evaluation using multi-specialist council architecture with deterministic safety stack.

لغة النص الأصلي: الإنجليزية

phi-detection

Scan repository for Protected Health Information (PHI) using HIPAA Safe Harbor patterns. Ensures evaluation data remains synthetic-only.

لغة النص الأصلي: الإنجليزية

evaluator-brief-generator

Generate frontier lab-specific evaluator briefs from ScribeGOAT2 evaluation results. Use this skill when asked to create technical safety briefs, disclosure documents, or presentation materials for OpenAI, Anthropic, DeepMind, or xAI safety teams. Produces…

لغة النص الأصلي: الإنجليزية