Customize VibeData dbt agents with organizational standards for Microsoft Fabric modeling, snapshots, semantic layer design, and Elementary data quality.
The official skill library and plugin marketplace for VibeData — the agentic coordination layer for data platforms.
Organizational data engineering standards, encoded and enforced.
Why This Exists
Data teams lose weeks to coordination tax — intent lost between role switches, fix patterns never captured, institutional knowledge trapped in people's heads. Current tools address individual slices (ingestion, transformation, observability) without connecting them.
This repository is the distribution layer for the standards that customize VibeData data engineering agents. Skills encode organizational rules for ingestion, extraction, source-system handling, platform conventions, and business logic so agents build, deploy, and operate pipelines with your team's accumulated knowledge — not generic defaults.
The same bundles can also be installed directly in Claude Code as standalone skills for practitioners who want those standards available outside VibeData.
Skills vs Plugins
Skills
Plugins
What
Markdown knowledge packages that encode organizational standards, source customization, and business rules
Installable Claude Code packages that bundle skills for VibeData agents or standalone Claude Code use
How they work
Loaded into VibeData data engineering agents to align behavior with your team's standards
Installed from the marketplace as reusable capabilities
Example
dbt naming conventions for Fabric, SCD2 snapshot patterns
Skill bundles like vibedata-dbt-skills, or workflow plugins like ad-migration
Skills are the behavior-shaping knowledge. Plugins are the distribution unit that makes those standards available to VibeData agents and, when useful, to Claude Code directly.
Then explore the rest of the catalog from the same marketplace. Skill bundles are intended for VibeData agent customization first, and can also be installed directly in Claude Code.
Migrate stored procedures to dbt models. Provides commands for scoping, profiling, test generation, and model generation across the full migration pipeline.
Customize VibeData ingestion agents with organizational standards for dlt REST API pipelines landing data in ADLS Gen2, OneLake, and Microsoft Fabric lakehouses.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
