Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.narrative.io/llms.txt

Use this file to discover all available pages before exploring further.

Narrative publishes Skills — pre-built workflows that orchestrate the Data Collaboration MCP Server to accomplish specific tasks. Where the MCP server exposes raw tools (search datasets, validate NQL, describe attributes), a skill packages those tools into an opinionated procedure for a higher-level goal, like “draft and run an NQL query” or “generate a Rosetta Stone mapping for this dataset.” A skill is harness-agnostic — it’s a portable instruction file, not logic tied to a particular AI assistant. You browse and install skills from the Skills catalog in the Narrative marketplace; Narrative distributes them as Claude Code plugins from the public narrative-io/narrative-skills-marketplace repository, which you install in Claude Code.

​
How skills relate to the MCP server

Skills are clients of the MCP server, not a replacement for it:
  • The MCP server exposes platform operations as discoverable tools (narrative_datasets_search, narrative_nql_validate, narrative_attributes_describe, …). Any MCP-compatible client can call them.
  • A skill is a markdown instruction file (SKILL.md) that tells an AI assistant how to combine those tools — in what order, with what guardrails, and when to ask for approval — to complete a specific task.
This means skills inherit MCP authentication, scoping, and audit trails. When a skill calls a tool, it runs as the authenticated user against the active company, just like any other MCP call.

​
Plugins and runtimes

Each skill belongs to a plugin — a versioned bundle published to the Claude Code marketplace. Narrative ships two plugins today:
PluginSkillsFocus
narrative-commonFind Attribute, Write NQL, Design Analysis, Create Workflow, Generate Rosetta Stone Mappings, Apply Rosetta Stone MappingsGeneral-purpose authoring, querying, and Rosetta Stone work
narrative-identityGenerate Identity Graph, Triage Pre-Graph DataIdentity resolution and graph building
Skills also declare a runtime that describes how they work:
  • Prompt only — the skill is pure instruction. The assistant follows the procedure using MCP tools and never writes or submits code on your behalf.
  • Prompt + code — the skill produces or submits artifacts (NQL queries, workflow YAML, mapping definitions) in addition to following the procedure. These skills are always approval-gated.

​
The catalog

Available skills include:

Find Attribute

Resolve a fuzzy description or schema shape to the canonical Rosetta Stone attribute ID.

Write NQL

Draft, validate, and optionally run an NQL query against a Narrative dataset.

Design Analysis

Scope a fuzzy analytical question into a structured brief of query specifications.

Create Workflow

Author and submit a Narrative workflow from a natural-language intent.

Generate Rosetta Stone Mappings

Generate, evaluate, and improve Rosetta Stone attribute mappings for a dataset.

Apply Rosetta Stone Mappings

Apply generated mappings to a dataset via a one-shot, approval-gated workflow.

Generate Identity Graph

Compose and submit an identity-graph workflow that unions edge sources and labels components.

Triage Pre-Graph Data

Audit a dataset or access rule for bad edges before an identity-graph build.
The Skills catalog page lists every published skill with its plugin, runtime, example prompts, dependencies, and install command. Each detail page links directly to the install instructions for Claude Code.

​
Dependencies

Skills can depend on other skills. For example, Generate Identity Graph delegates attribute lookup to Find Attribute rather than reimplementing it. When you install a plugin, every skill in that plugin becomes available — so dependencies within the same plugin are automatically satisfied. Cross-plugin dependencies are called out on the skill’s detail page.

​
Approval gating

Skills with the prompt+code runtime never modify your Narrative account without explicit approval. They draft the artifact (an NQL query, a workflow specification, a mapping), explain what it does, and wait for you to say “go” before calling a tool that submits work. This matters most for skills that generate workflows or write mappings, where the cost of an unintended run is highest.

​
Next steps

Install a skill in Claude Code

Add the Narrative marketplace and install a plugin in two commands.

Connect Claude Code to the MCP server

Skills require an authenticated MCP connection. Start here if you haven’t connected yet.

Browse the Skills catalog

See every published skill with example prompts and install commands.

MCP server tool reference

The underlying tools that skills orchestrate.