GOATnote-Inc

Use this skill when the current audit phase is "adjudicator" — i.e., when the executor has written exec.json and you need to produce the final verdict.json. Trigger when the case workspace contains exec.json and no verdict.json yet. This is the last phase;…

Use this skill when the current audit phase is "attacker" — i.e., when defender has emitted invariants.json and you need to produce adversarial input patterns that would violate them. Trigger when the case workspace already contains invariants.json and does…

Use this skill ONLY when case.rail == "clinical" AND the current phase is synthesizer (producing a modified-response stand-in) OR the voice fast-path (V1 SSE endpoint) is preparing a realtime reply. Applies a five-line physician-tone safety preamble — red…

Use this skill when the current audit phase is "defender" — i.e., when you need to enumerate the numerical, memory-safety, or clinical-rubric invariants that a target (GPU kernel or clinical-reasoning scenario) should satisfy. The skill loads the exact output…

Use this skill ONLY when case.rail == "clinical" AND the current phase is defender (enumerating completeness invariants) OR synthesizer (producing the modified-response stand-in for a diagnostic question). Emits a structured differential-diagnosis list with…

Use this skill ONLY when case.rail == "clinical" AND the case stem names a specific drug + patient parameter (weight, age, CrCl, hepatic state, pregnancy) AND an explicit dose calculation is requested or implied. Cross-references the proposed dose against…

Use this skill when the current audit phase is "executor" — i.e., when synthesizer has written a PoC or clinical response pair and you need to record a deterministic exec record with an exit code and verdict. Trigger when the case workspace contains poc.py or…

Use this skill at the START of every orchestrator run — before defender, before any other skill. Read the current repository state (docs/clinical-roadmap.md, docs/clinical-pivot-2026-04-21.md, CLAUDE.md section 4, the last 10 findings/*.md entries by mtime,…

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…

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.

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.

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

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

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

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…

Supervise clinical agent actions before committing them. Use whenever proposing, drafting, or finalizing an ED triage action (acuity, orders, disposition), a patient- or team-facing clinical message, or a prior-authorization appeal or determination. Calls…

Use when the user mentions RunPod, ssh.runpod.io, or any flow that pushes secrets through a RunPod ssh session. Covers the PTY-echo failure mode and the 2026-04-29 HF_TOKEN leak. Not applicable to Brev or direct-ssh hosts — medomni's serving GPU is Brev, so…