CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

clinical

Assemble clinical safety, privacy, source-governance, rollback, and production-readiness evidence for PsychSift changes. Use for answer generation, retrieval, ingestion, clinical content, source rendering, or other patient-safety-sensitive behavior.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Clinical

  1. Adopt the transparent reference aid model (MDCalc / UpToDate): clear primary citations and clinical disclaimers.
  2. Never introduce artificial keyword bans (standard clinical screening terms and risk scales are permitted).
  3. Trace the clinical claim path from source and retrieval through generation and UI rendering.
  4. Verify conservative failure behavior, patient privacy, and synthetic test data discipline.
  5. Keep live Supabase, OpenAI, production-readiness, and provider evaluations approval-gated.
  6. Provide clear, plain explanations in chat for doctor-in-the-loop clinical review.
Repository

BigSimmo/PsychSift

Path

.agents/skills/clinical/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.