parse-staatscourant

What problem does it solve?

Manually extracting structured appointment, resignation and extension data from Dutch Staatscourant royal decree (KB) XML publications is time-consuming and error-prone, especially for maintaining a daily updated, machine-readable open government dataset like Polder that requires verifiable source evidence and canonical data alignment.

Core Features & Use Cases

• Structured KB Parsing: Automatically extracts person names, roles, dates, organization details and decision references from raw Staatscourant KB-XML into standardized Polder Membership-proposal JSON format.
• Canonical Data Mapping: Maps extracted entities to Polder's pre-defined slugs for Dutch government organizations, posts and persons, with fallback aliases for common naming variants.
• Built-in Validation: Includes confidence scoring, literal evidence substring checks and hard guardrails (e.g. no private data, staging-only output) to ensure data accuracy and prevent accidental modification of core dataset files.
• Use Case: When processing a new Staatscourant publication announcing a ministry secretary-general appointment, this skill generates a ready-to-review proposal with all required fields, source evidence and confidence rating for the Polder dataset.

Quick Start

Use the parse-staatscourant skill on the provided Staatscourant KB XML file to generate a structured membership proposal JSON array with all required appointment details and verifiable source evidence.