Identify pathway

Skill Ibraheemolasupogit/google-adk-healthcare-pathway-escalation-agent/skills/identify_pathway

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

Install

npx -y skills add Ibraheemolasupogit/google-adk-healthcare-pathway-escalation-agent --skill identify_pathway

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.5 KB, as published. Nobody here has run it

Identify Pathway Skill

Purpose

Identify the pathway category for a synthetic operational case and retrieve the applicable target from controlled configuration.

When To Use

Use when a synthetic case must be validated and mapped to a controlled demonstration pathway rule.

When Not To Use

Do not use for unsupported pathways, real patient data, or target calculation from model knowledge.

Inputs

case_id or a validated synthetic case.

Outputs

Pathway code, pathway name, rule metadata, target, target unit, demonstration-only flag and validation warnings.

Dependencies

Case Data MCP server and Pathway Rules MCP server.

Deterministic vs Model Components

Case validation and rule lookup are deterministic. Any narrative explanation is model-generated and must not alter deterministic values.

Failure Conditions

Unknown case, unsupported pathway, prohibited identity fields, unavailable MCP capability.

Example Invocation

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

Evaluation Criteria

Correct pathway code, controlled target metadata, warnings present and no invented target values.

Current Limitations

Demonstration-only local data. Validate targets against authoritative guidance before operational use.

Safety Requirements

Use synthetic cases only.
Do not invent pathway targets.
Return uncertainty when a pathway cannot be mapped.
Require human review for downstream outputs.