building-dbt-semantic-layer
Use when creating or modifying dbt Semantic Layer components including semantic models, metrics, and dimensions leveraging MetricFlow.
Install with Tessl CLI
npx tessl i github:dbt-labs/dbt-agent-skills --skill building-dbt-semantic-layer82
Quality
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/building-dbt-semantic-layer/SKILL.mdDiscovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively identifies its niche within the dbt ecosystem with strong, distinctive trigger terms that practitioners would naturally use. However, it lacks specificity about concrete actions (what exactly can be done with these components) and reads more as a trigger clause than a complete description of capabilities.
Suggestions
Add specific concrete actions like 'define measures and dimensions, configure time spines, set up entity relationships, create derived metrics'
Separate the 'what' from the 'when' - first describe capabilities, then provide the trigger guidance (e.g., 'Defines semantic models, creates metrics with MetricFlow syntax, configures dimensions and entities. Use when...')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dbt Semantic Layer) and mentions components (semantic models, metrics, dimensions) but doesn't describe concrete actions beyond generic 'creating or modifying'. Lacks specific operations like 'define measures', 'configure time spines', or 'set up entity relationships'. | 2 / 3 |
Completeness | Has a 'Use when' clause which is good, but the 'what' portion is weak - it only says 'creating or modifying' without detailing specific capabilities. The when and what are essentially merged into one vague statement rather than clearly answering both questions. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'dbt', 'Semantic Layer', 'semantic models', 'metrics', 'dimensions', 'MetricFlow'. These are the exact terms practitioners use when working with this technology. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche with distinct triggers - 'dbt Semantic Layer', 'MetricFlow', 'semantic models' are highly specific to this technology stack and unlikely to conflict with other skills. The combination of these terms creates a unique fingerprint. | 3 / 3 |
Total | 10 / 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 strong skill with excellent actionability and workflow clarity. The step-by-step implementation workflow with validation checkpoints is well-designed, and the extensive YAML examples are copy-paste ready. The main weakness is some unnecessary introductory explanation of concepts Claude already knows, which could be trimmed for better token efficiency.
Suggestions
Remove or significantly condense the opening bullet list defining semantic models, entities, dimensions, and metrics - Claude already knows these concepts
Consider moving the 'Common Pitfalls' table to a separate reference file to reduce the main skill length while keeping the core workflow lean
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanation (e.g., defining what semantic models, entities, dimensions, and metrics are at the top when Claude likely knows these concepts). The examples are good but could be more condensed in places. | 2 / 3 |
Actionability | Provides fully executable YAML examples throughout, with copy-paste ready configurations for all metric types. Each step includes concrete code examples showing exact syntax and structure. | 3 / 3 |
Workflow Clarity | Clear 4-step implementation workflow with explicit validation checkpoint at the end (parse validation + semantic layer validation). The 'Do not consider work complete until both validations pass' instruction provides a clear feedback loop. | 3 / 3 |
Progressive Disclosure | Well-structured with clear overview, step-by-step workflow, and advanced examples. References to external files (time-spine.md, best-practices.md) are one level deep and clearly signaled. Content is appropriately split between quick start and advanced features. | 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 — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
- 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.