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

evals/eval_cases.json

View on GitHub
[
  {
    "id": "eval-001",
    "severity": "critical",
    "description": "Model generation triggers skill with dbt best practices",
    "input": "Create a dbt model that transforms raw orders data into a customer_orders mart with revenue metrics",
    "expected_trigger": true,
    "assertions": [
      "uses dbt best practices",
      "includes ref() for upstream models",
      "suggests proper materialization for marts (table or incremental)",
      "includes YAML config with descriptions",
      "follows naming convention fct_ or similar mart prefix"
    ]
  },
  {
    "id": "eval-002",
    "severity": "critical",
    "description": "Testing request triggers test domain disclosure",
    "input": "Write data tests for my staging models to ensure referential integrity and uniqueness",
    "expected_trigger": true,
    "assertions": [
      "discloses Level 2 (Testing) domain",
      "includes unique and not_null test patterns",
      "uses data_tests key (not deprecated tests key)",
      "demonstrates relationships test for referential integrity",
      "suggests severity configuration"
    ]
  },
  {
    "id": "eval-003",
    "severity": "critical",
    "description": "Semantic layer request triggers MetricFlow disclosure",
    "input": "Define MetricFlow semantic models and metrics for our revenue reporting and customer lifetime value tracking",
    "expected_trigger": true,
    "assertions": [
      "discloses Level 3 (Semantic Layer) domain",
      "includes semantic_models YAML with entities, dimensions, measures",
      "includes metrics YAML with type_params",
      "demonstrates time dimensions for aggregation",
      "includes saved queries for business reporting"
    ]
  },
  {
    "id": "eval-004",
    "severity": "high",
    "description": "dbt Mesh governance request triggers Mesh disclosure",
    "input": "Set up cross-project refs between our finance and marketing dbt projects with model contracts and access controls",
    "expected_trigger": true,
    "assertions": [
      "discloses Level 4 (dbt Mesh) domain",
      "demonstrates cross-project ref() syntax with project name",
      "includes model contract enforcement patterns",
      "covers access levels (private/protected/public)",
      "mentions dependencies.yml for project linking"
    ]
  },
  {
    "id": "eval-005",
    "severity": "high",
    "description": "Incremental model optimization triggers analytics engineering + platform domains",
    "input": "Our incremental model is running slow and costing too much in warehouse credits. Optimize it for performance and cost.",
    "expected_trigger": true,
    "assertions": [
      "discloses Level 1 (Analytics Engineering) domain",
      "optionally discloses Level 5 (Platform & Operations) domain",
      "recommends incremental_strategy: merge or delete+insert",
      "addresses partition/cluster configuration",
      "suggests warehouse cost optimization strategies",
      "recommends on_schema_change: sync_all_columns"
    ]
  },
  {
    "id": "eval-neg-001",
    "severity": "high",
    "description": "General SQL question does NOT trigger skill",
    "input": "How do I write a SELECT statement that joins two tables and filters by date?",
    "expected_trigger": false,
    "assertions": [
      "does NOT trigger dbt-data-transformation skill",
      "should be routed to a general SQL skill or answered without dbt specifics"
    ]
  },
  {
    "id": "eval-neg-002",
    "severity": "high",
    "description": "Airflow orchestration question does NOT trigger skill",
    "input": "I need to schedule my dbt job in Airflow. How do I create a DAG that runs dbt build every morning at 6am?",
    "expected_trigger": false,
    "assertions": [
      "does NOT trigger dbt-data-transformation skill for orchestration",
      "may reference dbt CLI commands within orchestration context but primary skill should be pipeline/orchestration",
      "if triggered, should only disclose Level 5 CLI command for dbt build, not full dbt skill"
    ]
  }
]
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