rh-inf-ingest

Plan and execute end-to-end clinical source ingestion workflows via the rh-skills CLI.

12|1|Updated Apr 15, 2026
One-click install
npx skills add https://github.com/reason-healthcare/rh-skills --skill rh-inf-ingest
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rh-inf-ingest
Source: https://github.com/reason-healthcare/rh-skills/tree/main/skills/.curated/rh-inf-ingest
Command: npx skills add https://github.com/reason-healthcare/rh-skills --skill rh-inf-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate end-to-end ingestion of clinical sources by coordinating discovery, download, normalization, topic inference, classification, and annotation to produce ready-to-use artifacts for downstream computable rules.

Core Features & Use Cases

  • Deterministic, CLI-driven workflow for source intake: downloads, normalization to Markdown with frontmatter, topic initialization, and artifact generation.
  • Idempotent operations across plan/implement/verify modes, with clear handling for open, authenticated, and manual sources.
  • Production-ready pipeline for HI evidence synthesis, enabling downstream extraction, formalization, and concept vocabulary generation.
  • On-demand resources management and strict CLI-only I/O to maintain reproducibility and traceability.
  • Example use: ingest a set of open sources to produce sources/normalized files and a topics/<topic>/process/concepts.yaml for L2/L3 processing.

Quick Start

Plan and run an end-to-end ingest for a topic using rh-skills ingest plan <topic> followed by rh-skills ingest implement <topic>.

Frequently Asked Questions about rh-inf-ingest

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate clinical data ingestion and normalization for downstream processing?

Clinical data ingestion automates downloading raw sources, normalizing content into Markdown with frontmatter, and running topic inference to produce computable artifacts and a de-duplicated concepts.yaml file.

What is topic inference and classification in a clinical data pipeline?

Topic inference and classification categorize ingested clinical sources during normalization, initializing topics and generating annotated outputs ready for downstream computable rule extraction.

How do I run an end-to-end clinical source intake workflow using a CLI?

Run rh-skills ingest plan <topic> followed by rh-skills ingest implement <topic> to execute deterministic, idempotent clinical source intake workflows via the CLI.

Does this data pipeline support idempotent operations for both open and authenticated sources?

Yes, the ingestion pipeline enforces idempotence across plan, implement, and verify modes, handling both open and authenticated clinical sources with soft-fail behavior when necessary tools are missing.

Can I process manual clinical sources through this ingestion workflow?

Yes, the ingestion workflow provides clear handling for open, authenticated, and manual clinical sources, maintaining strict CLI-only I/O to ensure reproducibility and traceability.

What are the limitations when required CLI tools are missing during source intake?

When necessary tools are missing, the ingestion pipeline exhibits soft-fail behavior, allowing the workflow to continue gracefully while maintaining strict CLI-only I/O for reproducibility.