Skip to content

JPeetz/agent-skills / skills/data/dbt-data-transformation

dbt-data-transformation

Verified

Use this skill when working with dbt (data build tool): model development, testing, documentation, semantic layer (MetricFlow), dbt Mesh governance, incremental strategies, and migration workflows. Follows dbt Labs best practices for data transformation and multi-project collaboration.

FileKindSize
CHANGELOG.mdmarkdown2.7 KB
LICENSEother1.1 KB
SKILL.mdskill md44.6 KB
evals/eval_cases.jsonconfig3.9 KB
evals/evals.jsonconfig3.7 KB
references/dbt-mesh-governance.mdmarkdown15.6 KB
references/dbt-model-patterns.mdmarkdown17.1 KB
references/dbt-semantic-layer.mdmarkdown21.0 KB
scripts/dbt-test-runner.shexecutablescript11.0 KB
scripts/validate-dbt-project.shexecutablescript9.0 KB

CHANGELOG.md

View on GitHub
# Changelog

All notable changes to the dbt-data-transformation agent skill.

## [1.0.0] — 2026-06-18

### Initial Release

Consolidated from the dbt-labs/dbt-agent-skills collection (10+ separate skills) into a single comprehensive, progressively-disclosed skill covering the complete dbt analytics engineering workflow.

### What's Included

- **5-Level Progressive Disclosure Architecture**
  - Level 1: Analytics Engineering — model patterns, materializations, Jinja macros, sources, seeds
  - Level 2: Testing — data tests, unit tests, singular tests, custom generic tests, severity thresholds
  - Level 3: Semantic Layer — MetricFlow, semantic models, metrics, dimensions, measures, saved queries
  - Level 4: dbt Mesh — cross-project refs, model contracts, access controls, groups, versions, governance
  - Level 5: Platform & Operations — job troubleshooting, CLI commands, MCP server, migration, warehouse optimization

### Key Improvements Over Source Collection

| Original (dbt-labs/dbt-agent-skills) | This Skill |
|---|---|
| 10+ separate granular skills | 1 consolidated skill with progressive disclosure |
| No domain routing / trigger mapping | Explicit trigger → domain routing table |
| No evaluation framework | Integrated eval suite (5 trigger + 2 near-miss cases) |
| No cost optimization | Warehouse cost optimization guide |
| No performance tuning | Query performance patterns + materialization decision matrix |
| No troubleshooting guide | Comprehensive job error reference table |
| No MCP server config | Full dbt MCP server configuration documentation |
| No migration guidance | v1.5+ → v1.9+ migration checklist |

### Artifacts

- `SKILL.md` — Comprehensive cross-platform skill definition (all major AI coding platforms)
- `LICENSE` — MIT
- `CHANGELOG.md` — This file
- `evals/eval_cases.json` — 7 evaluation test cases (5 trigger-positive, 2 near-miss negative)
- `scripts/validate-dbt-project.sh` — Project structure validation + compile + DAG check
- `scripts/dbt-test-runner.sh` — Test runner with severity filtering + structured reports
- `references/dbt-model-patterns.md` — Staging/intermediate/marts patterns, materialization matrix, incremental strategies
- `references/dbt-mesh-governance.md` — Cross-project refs, contracts, access controls, group/version management
- `references/dbt-semantic-layer.md` — MetricFlow patterns, semantic models, metrics, dimensions, saved queries

## v1.0.1 — 2026-10-28

### Changed
- Description rewritten to trigger form ("Use this skill when..."); removed "Production-grade" marketing word
- Replaced machine-local `/Users/username` paths in the dbt MCP config with portable `~` paths
- Added evals/evals.json with 7 cases (5 positive, 2 near-miss negatives)
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall