SkillNarrative Common
Profile Dataset
Profile a Narrative dataset or access rule: fill rate, cardinality, ranges, top-values, and quality flags.
About
Overview
Produce a coverage and quality profile of a Narrative dataset (or access rule): row count, per-column null/fill rate, cardinality, ranges, top-values, inferred column shape, and quality flags. Reads bundled stats and a sample first, recovers missing or stale stats by configuring and recalculating them, and escalates to a cheap NQL query only for a measure no stat can provide. Descriptive, not prescriptive.
Skill Support
Specifications
- Plugin
- Narrative Common
- Runtime
- Prompt + code
- Version
- 0.1.1
- Languages
- NQL
- Required Tools
- narrative_context_get, narrative_datasets_describe, narrative_dataset_get_column_stats, narrative_dataset_set_column_stats_config, narrative_dataset_recalculate_statistics, narrative_dataset_request_sample, narrative_jobs_describe
- Included Files
- SKILL.md
Arguments
| Argument | Required / Default | Description |
|---|---|---|
--dataset <id> | Optional | Profile a dataset by numeric id. Mutually exclusive with --access-rule. If neither is passed, the skill asks for the id and source type (it does not search). |
--access-rule <id> | Optional | Profile an access rule by id. Access rules behave like datasets in NQL, but their describe returns no bundled stats or sample. Mutually exclusive with --dataset. |
--focus <col,col,...> | Optional | Restrict the profile to these columns (e.g. _rosetta_stone.graph_edge.target_id_type). Default: all columns. |
--histograms | Optional | Include value-distribution histograms. Off by default (they can blow the response cap on wide columns); opt in when the caller needs a distribution. |
--allow-recalc | Optional | Pre-approve the tier-2 stats configure + recalculate recovery step, skipping its confirmation gate. For automation / skill callers. |
--allow-nql | Optional | Pre-approve the tier-3 custom-NQL escalation, skipping its confirmation gate. For automation / skill callers. |
--json | Optional | Emit only the structured profile object, skipping the prose render. Use when the caller is another skill or automation. |
<free-text tail> | Optional | A note about what the caller needs profiled (e.g., "id-type distribution", "fill rate on the email columns"). Steers column focus and which custom measures, if any, matter. |
Example prompts
| Prompt | When to use it |
|---|---|
Profile dataset 123 | Get row count, per-column fill rate, cardinality, ranges, and quality flags in one pass. |
What id types does dataset 123 emit? | Inspect the identifier columns and their coverage before a graph or match build. |
Null rates and cardinality for the email columns of dataset 123 | Focus the profile on a few columns to gauge addressable reach. |
/profile-dataset --dataset 123 --histograms id-type distribution | Include value-distribution histograms and steer the profile toward identifier-type coverage. |
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