SkillNarrative Common
Generate Rosetta Stone Mappings
Generate, evaluate, and improve Rosetta Stone attribute mappings for a dataset.
About
Overview
Generate, evaluate, and improve Rosetta Stone attribute mappings for a Narrative dataset. Samples the data, drafts normalized attribute mappings, validates the expressions, and scores each mapping so low-confidence suggestions can be improved before they are applied.
Skill Support
Specifications
- Plugin
- Narrative Common
- Runtime
- Prompt + code
- Version
- 0.4.0
- Languages
- NQL
- Required Tools
- narrative_datasets_describe, narrative_dataset_request_sample, narrative_dataset_get_column_stats, narrative_attributes_describe, narrative_nql_validate, narrative_nql_run
- Included Files
- SKILL.md
Arguments
| Argument | Required / Default | Description |
|---|---|---|
<free-text> | Optional | Natural-language intent naming the source dataset and what to map (e.g., "map dataset 12345 to Rosetta Stone", "evaluate the mappings on dataset N"). This skill takes no flags; it resolves the dataset and gathers context interactively. With no arguments, it asks which dataset to map. |
Example prompts
| Prompt | When to use it |
|---|---|
Map dataset 123 to the Rosetta Stone | Auto-suggest normalized attributes (e.g. raw_email → sha256_hashed_email) for an unmapped dataset. |
Why is the email mapping low confidence? | Diagnose and improve a mapping expression that scored poorly on a data sample. |
Suggest normalized attributes for these device columns | Map MAID and IDFA columns to mobile_id_unique_identifier and apple_idfa. |
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