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
answering-natural-language-questions-with-dbt
skills/dbt/skills/answering-natural-language-questions-with-dbt/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 an excellent skill description that hits all the marks. It provides specific capabilities, includes natural trigger terms with concrete examples, explicitly states both what it does and when to use it, and clearly distinguishes itself from related dbt development skills through explicit exclusion criteria.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Writes and executes SQL queries', 'using dbt's Semantic Layer or ad-hoc SQL', 'answer business questions'. Also explicitly states what it's NOT for (validating, testing, building dbt models). | 3 / 3 |
Completeness | Clearly answers both what (writes/executes SQL queries against data warehouse) and when (explicit 'Use when' clause with trigger terms and examples). Also includes helpful exclusion criteria for disambiguation. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'analytics', 'metrics', 'KPIs', 'data', plus concrete examples like 'total sales last quarter' and 'top customers by revenue' that mirror real user queries. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche with specific technology (dbt Semantic Layer), clear use case (answering business questions), and explicit exclusion of dbt development tasks. Unlikely to conflict with other data-related skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent actionability and workflow clarity. The decision flow diagram, quick reference table, and systematic approach hierarchy provide clear, executable guidance. The 'Rationalizations to Resist' and 'Red Flags' sections effectively prevent common failure modes. Minor improvement opportunity in progressive disclosure by splitting detailed approaches into separate files.
Suggestions
Consider splitting the four detailed approaches into a separate APPROACHES.md file, keeping only the decision flow and quick reference table in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude's competence with dbt, SQL, and semantic layers. No unnecessary explanations of basic concepts; every section provides actionable guidance without padding. | 3 / 3 |
Actionability | Provides concrete tool names, specific jq commands, executable SQL examples, and clear decision criteria. The quick reference table and approach sections give copy-paste ready guidance with specific tool sequences. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear decision flow (mermaid diagram), explicit fallback sequences (Approach 1→2→3→4), and validation through the 'Red Flags' and 'Common Mistakes' sections that serve as checkpoints. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but it's a monolithic document. The detailed approaches, examples, and tables could benefit from being split into separate reference files with the main skill providing an overview. | 2 / 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 | |