K-Dense-AI/scientific-agent-skills / skills/clinical-decision-support
clinical-decision-support
VerifiedPrepares 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.
assets/decision_logic_traceability_template.json
View on GitHub{
"schema_version": "1.0",
"metadata": {
"logic_id": "SYNTHETIC-RESEARCH-GOVERNANCE-001",
"title": "Synthetic Research Release Traceability",
"version": "0.1-draft",
"status": "draft",
"owner": "research governance owner",
"purpose": "Document evidence, validation, and human-review gates for an offline research artifact.",
"decision_role": "research_governance_only",
"data_level": "metadata_only",
"patient_care_use": false,
"executable_logic": false,
"change_summary": "Initial synthetic documentation example.",
"monitoring_plan": "Review source currency, validation status, subgroup evidence, and unresolved issues at each version.",
"retirement_criteria": "Retire when sources, validation evidence, ownership, or intended use are obsolete."
},
"intended_use": "Research/governance traceability only; not for patient care or live clinical use.",
"prohibited_uses": [
"No diagnosis, treatment recommendation, dosing, triage, urgency, alarm, or autonomous decision.",
"No care pathway, EHR rule, or executable clinical logic.",
"No claim of authorization or compliance."
],
"limitations": [
"The matrix documents plain-language logic and does not execute it.",
"Source presence does not establish evidence quality.",
"Human review and independent validation remain required."
],
"sources": [
{
"id": "SRC-GOV-001",
"citation": "Synthetic research governance procedure, version 1.",
"url": "not_applicable_for_local_synthetic_source",
"accessed": "2026-07-23"
}
],
"nodes": [
{
"id": "source_gate",
"type": "evidence_rule",
"dependency_ids": [],
"precondition": "An evidence record is proposed for the research artifact.",
"logic_statement": "Check for a stable citation, source version, and retrieval date.",
"output_kind": "flag_for_review",
"output_value": "missing_source_provenance when any required source field is absent",
"source_ids": [
"SRC-GOV-001"
],
"rationale": "Reviewers need reproducible source provenance.",
"validation_tests": [
"Complete source fields produce no provenance flag.",
"Missing retrieval date produces missing_source_provenance."
],
"owner": "evidence review owner",
"reviewer_role": "independent methodologist",
"status": "draft"
},
{
"id": "validation_gate",
"type": "validation_gate",
"dependency_ids": [
"source_gate"
],
"precondition": "Source provenance is complete.",
"logic_statement": "Check whether independent external validation and subgroup uncertainty are documented.",
"output_kind": "release_hold",
"output_value": "true when required validation documentation is absent",
"source_ids": [
"SRC-GOV-001"
],
"rationale": "Transportability claims require independent evidence and uncertainty.",
"validation_tests": [
"Missing external-validation evidence produces a release hold.",
"Complete validation evidence passes to human review."
],
"owner": "validation owner",
"reviewer_role": "independent statistician",
"status": "draft"
},
{
"id": "human_review_gate",
"type": "human_review",
"dependency_ids": [
"validation_gate"
],
"precondition": "Required documentation gates are complete.",
"logic_statement": "Require recorded review by the accountable method, domain, privacy, and governance roles.",
"output_kind": "documentation_status",
"output_value": "pending until all accountable review roles record a decision",
"source_ids": [
"SRC-GOV-001"
],
"rationale": "Automated structural checks cannot approve a research artifact.",
"validation_tests": [
"Absent reviewer decision produces pending status.",
"Recorded reviewer decisions produce complete documentation status."
],
"owner": "governance owner",
"reviewer_role": "authorized governance approver",
"status": "draft"
}
],
"human_review": {
"required": true,
"completed": false,
"approval_boundary": "Only the accountable organization can approve a research artifact; this matrix never authorizes clinical use."
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |