Skills for Real Engineers. Straight from my .agents directory.
clinical-decision-support
Agent skill fromK-Dense-AI/scientific-agent-skills
Prepares and validates research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts. Supports aggregate or synthetic research documentation and traceability, excluding patient care and live clinical operation.
How to install clinical-decision-support
npx skills add K-Dense-AI/scientific-agent-skills# or add only this skill to Claude Code: copy the folder
skills/clinical-decision-support/
# into
~/.claude/skills/clinical-decision-support/ (all projects)
.claude/skills/clinical-decision-support/ (one project)
1# Clinical Decision-Support Research and Evaluation23## Hard Safety Boundary45This skill produces **research, evaluation, documentation, and governance artifacts only**.67Never use it to:89- diagnose or classify a person;10- recommend, select, sequence, start, stop, or modify treatment;11- calculate or communicate a patient-specific dose;12- triage, prioritize, alarm, alert, or determine urgency;13- make or automate a patient-specific clinical decision;14- support bedside, point-of-care, or live clinical operation;15- replace professional judgment or a validated, authorized clinical system;16- claim FDA authorization, regulatory conformity, HIPAA compliance, or legal compliance.1718If a request could affect care for a person, stop the workflow and route the matter to a licensed healthcare professional using locally validated and appropriately authorized systems. Do not redirect to another skill for patient-specific care.1920## In Scope2122- Intended-use and limitation statements for research artifacts23- Aggregate cohort table shells with disclosure controls24- Statistical analysis plans and survival-analysis plan review25- Aggregate model or biomarker performance evaluation26- Transparent GRADE evidence-profile checklists27- Evidence-source and decision-logic traceability28- De-identification process checklists29- Fairness, subgroup, calibration, uncertainty, external-validation, monitoring, change-control, audit, and human-factors documentation30…
Excerpt shown under the repository's MIT license.
More skills in scientific-agent-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
