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
building-dbt-semantic-layer
skills/dbt/skills/building-dbt-semantic-layer/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 clearly defines its scope around dbt Semantic Layer components with excellent specificity. It uses proper third-person voice, includes a 'Use when' clause upfront, and provides comprehensive trigger terms that dbt practitioners would naturally use. The enumeration of specific metric types and components makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and components: 'creating or modifying dbt Semantic Layer components — semantic models, metrics, dimensions, entities, measures, or time spines' plus 'MetricFlow configuration, metric types (simple, derived, cumulative, ratio, conversion), and validation'. | 3 / 3 |
Completeness | Explicitly answers both what ('creating or modifying dbt Semantic Layer components', 'MetricFlow configuration', 'validation') AND when ('Use when creating or modifying...') with clear trigger guidance at the start. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'dbt', 'Semantic Layer', 'semantic models', 'metrics', 'dimensions', 'entities', 'measures', 'time spines', 'MetricFlow', specific metric types, and 'YAML specs' - all terms a dbt user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche - specifically targets dbt Semantic Layer and MetricFlow, unlikely to conflict with general SQL, data modeling, or other dbt skills due to specific component names and metric types mentioned. | 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 with excellent workflow clarity and progressive disclosure. The decision tree for spec selection is clear, validation steps are explicit with proper sequencing, and references to detailed guides are well-organized. Minor verbosity in introductory definitions and entry point descriptions prevents a perfect conciseness score, but overall the content is highly actionable and well-organized.
Suggestions
Remove or significantly condense the bullet definitions at the top (semantic models, entities, dimensions, metrics) - Claude already knows these concepts
Tighten the 'Entry Points' section - the three scenarios could be reduced to a brief routing table rather than detailed prose
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some explanatory text that could be tightened. The bullet definitions at the top (semantic models, entities, dimensions, metrics) explain concepts Claude likely knows, and some sections like 'Entry Points' are verbose for what they convey. | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific CLI commands (dbt parse, dbt sl validate, mf validate-configs), exact Jinja filter syntax with multiple examples, clear decision trees for spec selection, and references to detailed spec guides for YAML authoring. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. The 'Determine Which Spec to Use' section has numbered steps with clear routing logic, and the Validation section explicitly requires two-stage validation with a feedback loop ('Do not consider work complete until both validations pass'). | 3 / 3 |
Progressive Disclosure | Excellent structure with clear overview and well-signaled one-level-deep references. Links to time-spine.md, best-practices.md, latest-spec.md, and legacy-spec.md are clearly labeled with purpose. The main file stays focused on routing and overview while delegating detailed YAML syntax to spec-specific guides. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |