Stats

Actions

Tags

Help us improve

Share bugs, ideas, or general feedback.

data-engineering-guide | agentspec | ClaudePluginHub

Skill

data-engineering-guide

Routes users to specialized agents for data pipeline design, schema modeling, data quality, SQL optimization, lakehouse, AI pipelines, and data contracts. Provides access to 23 knowledge domains.

data-engineering

$

npx claudepluginhub luanmorenommaciel/agentspec --plugin agentspec

Popularity

Parent stars

183

Parent forks

91

Invocation

How this skill is triggered — by the user, by Claude, or both

Slash command

/agentspec:data-engineering-guide

User invocable

Model invocable

Inline context

Default effort

Context Preview

The summary Claude sees in its skill listing — used to decide when to auto-load this skill

You have access to 23 specialized knowledge base domains and 15+ data engineering agents. Route the user to the right tool based on their task.

SKILL.md

54 lines · ~671 tokens

Similar Skills

data-engineer

38.0k

Builds scalable data pipelines, modern data warehouses, and real-time streaming architectures using Apache Spark, dbt, Airflow, and cloud-native platforms.

antigravity-awesome-skills

flux

41

Handles data engineering tasks: designs database schemas, builds zero-downtime migrations and ETL pipelines, optimizes queries, performs health checks, and inventories databases.

11 tools

Use this skill when

18

faos-data-engineer

Stats

LanguageHTML

Parent stars183

Parent forks91

MaintenanceExcellent

Last CommitMay 19, 2026

Actions

View Source View Plugin View on GitHub View README

Tags

data-engineering

Help us improve

Share bugs, ideas, or general feedback.

Data Engineering Guide

You have access to 23 specialized knowledge base domains and 15+ data engineering agents. Route the user to the right tool based on their task.

Quick Routing

User Task	Command	Agent
Design a data pipeline / DAG	`/agentspec:pipeline`	pipeline-architect
Design a schema / star schema / data model	`/agentspec:schema`	schema-designer
Add data quality checks	`/agentspec:data-quality`	data-quality-analyst
Review SQL performance	`/agentspec:sql-review`	sql-optimizer
Choose table format (Iceberg/Delta)	`/agentspec:lakehouse`	lakehouse-architect
Build RAG / embedding pipeline	`/agentspec:ai-pipeline`	ai-data-engineer
Create a data contract	`/agentspec:data-contract`	data-contracts-engineer
Migrate legacy ETL	`/agentspec:migrate`	dbt-specialist + spark-engineer

Knowledge Domains Available

Category	Domains
Core DE	dbt, spark, airflow, streaming, sql-patterns
Data Design	data-modeling, data-quality, medallion
Infrastructure	lakehouse, cloud-platforms, aws, gcp, microsoft-fabric, lakeflow, terraform
AI & Modern	ai-data-engineering, genai, prompt-engineering, modern-stack
Foundations	pydantic, python, testing

How Agents Use Knowledge

Agent reads KB index at ${CLAUDE_PLUGIN_ROOT}/kb/{domain}/index.md
Loads specific pattern/concept file matching the task
Falls back to MCP if KB insufficient (max 3 MCP calls)
Calculates confidence from evidence matrix

When to Suggest Commands

User mentions "dbt model" or "staging model" → /agentspec:schema or delegate to dbt-specialist
User mentions "pipeline" or "DAG" or "orchestration" → /agentspec:pipeline
User mentions "data quality" or "expectations" or "tests" → /agentspec:data-quality
User mentions "slow query" or "optimize SQL" → /agentspec:sql-review
User mentions "Iceberg" or "Delta Lake" or "table format" → /agentspec:lakehouse
User mentions "RAG" or "embeddings" or "vector" → /agentspec:ai-pipeline
User mentions "contract" or "SLA" or "schema governance" → /agentspec:data-contract
User mentions "migrate" or "legacy" or "SSIS" or "Informatica" → /agentspec:migrate