dbt

dbt (data build tool) patterns for data transformation and analytics engineering. Use when building data models, implementing data quality tests, or managing data transformation pipelines.

Quality

77%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/devops-data/skills/dbt/SKILL.md

Quality

Content

79%

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

This is a solid, concise dbt skill that provides executable patterns for common use cases. Its strengths are token efficiency and actionable code examples. Weaknesses include lack of explicit workflow sequencing for the model development lifecycle and missing references for advanced topics like macros and snapshots.

Suggestions

Add an explicit workflow section showing the sequence: develop model → run dbt run → validate with dbt test → check results before promoting

Include references or brief examples for macros and snapshots since they appear in the project structure but have no guidance

Add a validation checkpoint pattern showing how to verify model outputs (e.g., dbt test, dbt build --select model+)

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient, providing only essential patterns without explaining what dbt is or how SQL works. Every section delivers actionable content without padding.	3 / 3
Actionability	Provides fully executable SQL examples with proper dbt syntax (source(), ref(), config blocks, is_incremental()). The YAML test configuration is copy-paste ready.	3 / 3
Workflow Clarity	The staging → intermediate → marts pattern is mentioned but not explicitly sequenced as a workflow. No validation checkpoints for testing models or verifying transformations before deployment.	2 / 3
Progressive Disclosure	Content is well-organized with clear sections, but seeds, macros, and snapshots directories are shown without explanation or references to detailed documentation. Could benefit from links to advanced topics.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 solid description that clearly identifies its domain (dbt) and provides explicit 'Use when' guidance, making it easy for Claude to know when to select this skill. However, it could be strengthened with more specific concrete actions and additional trigger terms that users commonly associate with dbt workflows.

Suggestions

Add more specific concrete actions like 'write incremental models', 'configure sources and seeds', 'create reusable macros', or 'set up model dependencies'

Include additional natural trigger terms users might say: 'SQL models', 'staging/marts', 'ref() function', 'dbt run', 'dbt test', '.yml schema files'

Dimension	Reasoning	Score
Specificity	Names the domain (dbt/data transformation) and mentions some actions ('building data models', 'implementing data quality tests', 'managing data transformation pipelines'), but doesn't list specific concrete actions like 'write incremental models', 'configure sources', or 'create macros'.	2 / 3
Completeness	Clearly answers both what ('dbt patterns for data transformation and analytics engineering') and when ('Use when building data models, implementing data quality tests, or managing data transformation pipelines') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes relevant terms like 'dbt', 'data build tool', 'data models', 'data quality tests', 'data transformation pipelines', but misses common variations users might say like 'SQL models', 'ref()', 'staging models', 'marts', '.yml files', or 'dbt run/test'.	2 / 3
Distinctiveness Conflict Risk	The explicit mention of 'dbt (data build tool)' creates a clear niche that distinguishes it from general SQL skills or other data tools. The specific terminology around analytics engineering and dbt patterns makes conflicts unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: jpoutrin/product-forge
Commit: 0ebe7ae

Reviewed: 5 months ago

Table of Contents

Discovery Implementation Validation

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.