CtrlK
BlogDocsLog inGet started
Tessl Logo

dbt-labs/dbt-agent-skills

A curated collection of Agent Skills for working with dbt, to help AI agents understand and execute dbt workflows more effectively.

91

Does it follow best practices?

Validation for skill structure

This version of the tile failed moderation
Moderation failed
Overview
Skills
Evals
Files

using-dbt-for-analytics-engineering

skills/dbt/skills/using-dbt-for-analytics-engineering/SKILL.md

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that excels across all dimensions. It provides specific concrete actions, uses natural dbt-related terminology users would actually say, includes an explicit 'Use when...' clause with comprehensive trigger scenarios, and maintains clear distinctiveness through dbt-specific language that prevents conflicts with general SQL or data transformation skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'Builds and modifies dbt models', 'writes SQL transformations using ref() and source()', 'creates tests', and 'validates results with dbt show'. These are precise, actionable capabilities.

3 / 3

Completeness

Clearly answers both what (builds models, writes SQL transformations, creates tests, validates results) AND when with explicit 'Use when...' clause covering multiple trigger scenarios (building models, debugging, exploring data, writing tests, evaluating changes).

3 / 3

Trigger Term Quality

Includes natural keywords users would say: 'dbt', 'models', 'SQL transformations', 'ref()', 'source()', 'tests', 'dbt show', 'debugging errors', 'data sources'. Good coverage of domain-specific terms users would naturally mention.

3 / 3

Distinctiveness Conflict Risk

Clear niche focused specifically on dbt tooling with distinct triggers like 'ref()', 'source()', 'dbt show', and 'dbt models'. Unlikely to conflict with generic SQL or data skills due to dbt-specific terminology.

3 / 3

Total

12

/

12

Passed

Implementation

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured skill that effectively uses progressive disclosure to organize complex dbt guidance. It excels at workflow clarity with explicit validation checkpoints and a helpful 'Common Mistakes' section. The main weakness is the lack of concrete, executable code examples in the main file - it relies heavily on references for actionable details.

Suggestions

Add 1-2 concrete `dbt show` command examples with full syntax (e.g., `dbt show --select my_model --limit 10`) to make the validation guidance immediately actionable

Include a minimal executable example showing ref() and source() usage in context, rather than just mentioning them as requirements

DimensionReasoningScore

Conciseness

The content is lean and efficient, assuming Claude's competence with dbt concepts. No unnecessary explanations of what dbt is or how SQL works - it jumps straight to actionable guidelines and references.

3 / 3

Actionability

Provides clear guidelines and references to detailed guides, but lacks concrete executable code examples in the main skill file. Commands like `dbt show` and `dbt clone` are mentioned but not demonstrated with full syntax examples.

2 / 3

Workflow Clarity

Clear workflow guidance with explicit validation checkpoints - emphasizes using `dbt show` regularly to validate, includes a 'STOP if you're about to' checklist, and references detailed workflow guides for specific tasks. The Common Mistakes table provides clear error recovery guidance.

3 / 3

Progressive Disclosure

Excellent structure with a clear overview and well-organized reference table pointing to one-level-deep guides for specific tasks. Content is appropriately split between the main skill and detailed reference files with clear navigation.

3 / 3

Total

11

/

12

Passed

Validation

72%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation8 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

8

/

11

Passed