About


Overview

The rules for mapping a Narrative dataset's columns to Rosetta Stone attributes: choosing the attribute, mapping the source of a derivation, deciding between a value mapping and an object mapping, setting discriminators, validating each expression with NQL, and scoring confidence. It has no flow of its own. Generate Rosetta Stone Mappings and Infer Rosetta Stone Mappings read it, and it answers questions about a single mapping directly.

Rosetta StoneMappingsNormalizationNQL

Specifications


Price
Free
Runtime
Prompt only
Version
0.2.3
Languages
NQL
Required Tools
narrative_attributes_describe, narrative_attributes_search, narrative_nql_validate
Example prompts
PromptWhen to use it
Which Rosetta Stone attribute should the email_addr column map to?Apply the attribute-choice rules to one column, checking its sample values against each candidate attribute's schema.
Is this mapping expression right?Check a value or object mapping against the rules and validate it with NQL before it is applied.

Skill Dependencies


This skill builds on the skills listed below — each runs as a step in its workflow.

Requires MCP Servers


This skill calls tools from the MCP servers listed below — connect them so your agent has the tools the skill needs.

Installation


Install into any spec-compliant agent — no clone or Bun required:

npx skills add narrative-io/narrative-skills-marketplace