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.
| Prompt | When 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. |
This skill builds on the skills listed below — each runs as a step in its workflow.
This skill calls tools from the MCP servers listed below — connect them so your agent has the tools the skill needs.
Install into any spec-compliant agent — no clone or Bun required:
npx skills add narrative-io/narrative-skills-marketplace