CommunityCoding & Developmentgithub.com

google-adk-healthcare-pathway-escalation-agent

A secure Google ADK multi-agent system for synthetic NHS pathway assessment, MCP-based evidence retrieval, guardrails and human-in-the-loop escalation review.

What is google-adk-healthcare-pathway-escalation-agent?

google-adk-healthcare-pathway-escalation-agent is a Claude Code agent skill that a secure Google ADK multi-agent system for synthetic NHS pathway assessment, MCP-based evidence retrieval, guardrails and human-in-the-loop escalation review.

Works with~Claude Code~Codex CLI~Cursor
npx skills add Ibraheemolasupogit/google-adk-healthcare-pathway-escalation-agent

Installed? Explore more Coding & Development skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Calculate Risk Skill

Purpose

Calculate deterministic, explainable operational risk for a synthetic pathway case.

When To Use

Use to run the deterministic assessment and return exact risk score, level and factors.

When Not To Use

Do not use to create alternative model-based scores or clinical prioritisation.

Inputs

Validated synthetic case ID.

Outputs

Breach status, target consumption, variance, risk score, risk level, risk factors, audit trace ID and human-review requirement.

Dependencies

Pathway Rules MCP server and deterministic assessment service.

Deterministic vs Model Components

All calculations are deterministic. Models may only explain supplied factors.

Failure Conditions

Unknown case, unsupported pathway, malformed timestamps, unavailable MCP capability.

Example Invocation

python -m app.main run-skill --skill calculate_risk --case-id SYN-CANCER-2WW-001

Evaluation Criteria

Exact deterministic risk values preserved and every factor explained.

Current Limitations

Operational risk only; no clinical logic.

Safety Requirements

  • Use transparent factors.
  • Keep calculations reproducible.
  • Do not infer clinical diagnosis or treatment needs.
  • Require human review for downstream outputs.

Related Skills