Dts
- Updated July 7, 2026
- Big-Time-Data/homebrew-dts
dts (Data Tool Suite) provides LLM-observable workflows for dbt projects, executing queries and interpreting their results. A data or analytics engineer uses it to run and reason about dbt transformations with an agent that can both run SQL and explain the output.
Key points
- Data Tool Suite for dbt
- Query execution
- LLM-observable workflows
- Result interpretation
Dts by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin marketplace add Big-Time-Data/homebrew-dts/plugin install dts@dts-marketplaceAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Last updated | July 7, 2026 |
|---|---|
| Repository | Big-Time-Data/homebrew-dts ↗ |
What it does
Run and interpret dbt project queries with LLM-observable workflows, executing SQL and explaining results.
README.md
DTS Query Workflow Plugin
Claude Code plugin for LLM-observable data exploration workflows. Orchestrates reasoning, query execution, interpretation, and annotation handling through the DTS MCP server.
Features
- Commands:
/query,/explore-data,/validate,/annotations,/dts-prime - Auto-initialization:
dts-primeruns at session start to establish schema context - LLM Observability: All queries tracked with intent, reasoning recorded via observer
- Cross-environment: Compare dev vs prod with fully-qualified table names
Commands
| Command | Description |
|---|---|
/query <model> |
Start a query workflow against a model or topic |
/explore-data <model> |
Rich exploration with data quality checks |
/validate <model> against <source> |
Validate data against expectations/CSV/prod |
/annotations |
Check for pending human annotations |
/dts-prime |
Re-initialize schema context |
Requirements
- dbt project with
dbt_project.ymland accessibleprofiles.yml - Database credentials configured in dbt profiles
Related skills
Microsoft FoundryDeploy, evaluate, and continuously improve Microsoft Foundry agents from a single agent interface.490k1.3k
Ai Research ReproductionOrchestrate trustworthy, auditable reproduction of deep learning repositories directly from their READMEs.176k511Run TrainSafely execute selected deep learning training commands with standardized evidence capture.176k511Explore RunSafely run isolated exploratory experiments with clear recording and conservative selection before committing changes.176k511Paper Context ResolverFetch precise reproduction-critical details like dataset splits, preprocessing steps, or evaluation protocols from the original academic paper when the repo README leav141k511Repo Intake And PlanScan unfamiliar AI research repositories and receive a minimal, trustworthy reproduction target before investing significant time.140k511