Menu
SkillsMP a collecté 7 skills depuis GOATnote-Inc/scribegoat2. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 7 skills collectés sur 7.
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…
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Anthropic-aligned medical safety evaluation with pass^k metrics, failure taxonomy, and anti-gaming graders
Langue du texte source : anglais
Run HealthBench Hard benchmark evaluation using multi-specialist council architecture with deterministic safety stack.
Langue du texte source : anglais
Scan repository for Protected Health Information (PHI) using HIPAA Safe Harbor patterns. Ensures evaluation data remains synthetic-only.
Langue du texte source : anglais
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…
Langue du texte source : anglais