Propose changes to a Narrative dataset's Rosetta Stone mappings as structured output, for a workflow run with no person in the loop. Reads the dataset as it is, applies the Rosetta Stone mapping rules, and returns the mappings to add, replace and remove, the ones to keep, and the columns it leaves unmapped, each scored for confidence. Writes nothing: the workflow applies the proposals that meet its threshold.
| Prompt | When to use it |
|---|---|
Infer Rosetta Stone mappings for dataset 123 and answer with the workflow's schema | A workflow task proposes mappings for a newly registered dataset, with nobody there to answer questions. |
Propose changes to dataset 456's existing mappings | Get adds, replaces and removes against the mappings a dataset already has, each scored so the workflow applies only the confident ones. |
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