---
title: "majestic-data"
description: "Design, test, and operate data pipelines, contracts, quality controls, dbt projects, and source assessments."
canonical: https://agentpluginsdirectory.com/plugins/majestic-data
last-updated: 2026-09-18
---

# majestic-data
Design, test, and operate data pipelines, contracts, quality controls, dbt projects, and source assessments.
- Slug: majestic-data
- Publisher: Majestic Labs
- Repository: https://github.com/majesticlabs-dev/majestic-abilities
- Manifest: plugins/data/plugin.json
- Version: 0.1.0
- License: MIT
- Category (editorial): other
- Skills: 8 (anomaly-detection, csv-wrangling, data-pipeline-design, data-pipeline-testing, data-quality, data-source-assessment, data-validation, dbt-development)
- MCP servers: 0
- Stars: 1
- Repository created: 2026-08-24
- Repository last pushed: 2026-09-18
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/majestic-data
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- anomaly-detection: Design and evaluate statistical or model-based anomaly detection for tabular, multivariate, or time-series data.
- csv-wrangling: Recover messy CSV or TSV files without dropping or corrupting records, including uncertain encoding, structure, malformed rows, locale values, schema drift, or large files.
- data-pipeline-design: Design reliable batch or incremental ETL, ELT, or CDC pipelines before implementation, with explicit grain, idempotency, recovery, and reconciliation.
- data-pipeline-testing: Design tests and fixtures for ETL, ELT, or dbt pipeline transformation, contracts, incrementality, replay, reconciliation, and failure recovery.
- data-quality: Define and operate ongoing data quality controls, service levels, alerts, scorecards, drift monitoring, ownership, and incident response.
- data-source-assessment: Assess an unfamiliar database, API, file, or event stream before pipeline integration by profiling its schema, grain, changes, quality, and extraction constraints.
- data-validation: Design executable data contracts across records, DataFrames, warehouse models, and pipeline boundaries, including schema evolution, quarantine, and failure policy.
- dbt-development: Build and review dbt models, snapshots, macros, sources, tests, and project structure with explicit grain, layering, materialization, and incremental behavior.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.