CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

using-dbt-for-analytics-engineering

Builds and modifies dbt models, writes SQL transformations using ref() and source(), creates tests, and validates results with dbt show. Use when doing any dbt work - building or modifying models, debugging errors, exploring unfamiliar data sources, writing tests, or evaluating impact of changes.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is dbt-labs/dbt-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

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

A well-structured overview skill: strong progressive disclosure with real, clearly-purposed reference files, and concrete dbt-specific guidance with validation emphasis throughout. Weaknesses are modest — a few filler lines, no fully worked example command, and an implied rather than explicitly sequenced workflow.

Suggestions

Trim low-information filler such as 'Always use data modelling best practices when working in a project' and the explanatory 'This context prevents...' sentence in the model building section.

Add one copy-paste-ready example, e.g. a sample 'dbt show --limit 20' invocation or a minimal dbt test YAML block, to lift actionability to fully executable.

Consolidate the build/modify guidance into one short ordered workflow (read YAML docs → plan via reference → build → validate with dbt show) so the sequence and its checkpoints are explicit rather than implied.

DimensionReasoningScore

Conciseness

The body is largely lean tables and directives, but contains a few trimmable filler lines such as 'Always use data modelling best practices when working in a project' and 'This context prevents misusing columns or duplicating existing logic' — efficient with minor instances of over-explanation, matching the 4 anchor rather than the every-token-earns-its-place of a 5.

4 / 5

Actionability

Concrete commands and flags appear throughout ('dbt show', '--limit', '--defer --state path/to/prod/artifacts', 'dbt clone', '--select', '{{ ref() }} and {{ source() }}'), but there is no copy-paste-ready example invocation or test snippet; this is mostly executable guidance with minor gaps, not the fully-ready examples of a 5.

4 / 5

Workflow Clarity

For a database-operation skill the body does provide validation feedback loops ('use dbt show regularly to preview... run basic data profiling', 'iterate with dbt show') plus STOP checkpoints and a mistakes/fix table, but the steps are scattered across sections rather than presented as an explicit ordered sequence — clear with most checkpoints present, matching 4 rather than the fully sequenced 5.

4 / 5

Progressive Disclosure

The body is a true overview with a well-signaled 'Guide | Use When' table pointing to seven one-level-deep reference files, all of which exist in references/ with no further nesting, exactly matching the clear-overview top anchor.

5 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

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

A strong description: third-person, concrete, tool-specific capabilities paired with an explicit and detailed 'Use when' trigger clause. The only weakness is modest synonym coverage on the trigger side, which keeps trigger term quality just below the top anchor.

Suggestions

Add one or two common user synonyms to the trigger clause (e.g., 'analytics engineering', 'warehouse transformations', 'SQL models') to broaden natural-keyword coverage.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions with named tools — 'Builds and modifies dbt models, writes SQL transformations using ref() and source(), creates tests, and validates results with dbt show' — covering build, modify, test, and validate comprehensively, matching the top anchor rather than the 'minor gaps' of a 4.

5 / 5

Completeness

Explicitly answers both 'what' (four concrete capabilities) and 'when' with a concrete 'Use when doing any dbt work - building or modifying models, debugging errors, exploring unfamiliar data sources, writing tests, or evaluating impact of changes' clause, exactly matching the top anchor.

5 / 5

Trigger Term Quality

Good keyword coverage with natural phrases users would say ('dbt work', 'debugging errors', 'exploring unfamiliar data sources', 'writing tests', 'evaluating impact of changes'), but a few natural synonyms are missing (e.g., analytics engineering, warehouse, SQL modeling), placing it just below the comprehensive-synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear dbt niche with tool-specific triggers ('ref() and source()', 'dbt show') that no other skill would naturally claim, giving minimal conflict risk; it is not merely 'mostly distinct' as at a 4.

5 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

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

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository

dbt-labs/dbt-agent-skills

Path

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

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.