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
adding-dbt-unit-test
skills/dbt/skills/adding-dbt-unit-test/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 well-crafted skill description that excels across all dimensions. It provides specific concrete actions, includes natural trigger terms users would actually say, explicitly addresses both what and when, and carves out a distinct niche within the dbt ecosystem. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Creates unit test YAML definitions', 'mock upstream model inputs', and 'validate expected outputs'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Creates unit test YAML definitions that mock upstream model inputs and validate expected outputs') and when ('Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'unit tests', 'dbt model', 'test-driven development', 'TDD', 'YAML'. These cover common variations of how users would request this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche combining dbt, unit testing, and YAML definitions. The combination of 'dbt model', 'unit test YAML', and 'TDD in dbt' creates a distinct trigger profile unlikely to conflict with general testing or other dbt skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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 progressive disclosure and actionable examples. The content provides concrete, executable YAML and shell commands that Claude can use immediately. The main weaknesses are some verbosity in explanatory sections and a workflow that could benefit from more explicit validation checkpoints, particularly around the test-fix-retest cycle.
Suggestions
Add explicit validation checkpoints to the workflow section, such as 'Run unit test → If fails, check actual vs expected diff → Fix model or test → Re-run until passing'
Trim the 'When to use' section by removing redundant bullet points (e.g., 'Logic for which you had bugs reported before' overlaps with 'Verifying that a bug fix solves a bug report')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations (e.g., 'Self explanatory -- the title says it all!') and could be tightened in places, but overall respects Claude's intelligence and avoids excessive padding. The 'When to use' and 'When not to use' sections are somewhat verbose. | 2 / 3 |
Actionability | Provides fully executable YAML and SQL examples that are copy-paste ready. The minimal unit test example, realistic example, and shell commands are concrete and specific. The workflow steps are clear with actual commands. | 3 / 3 |
Workflow Clarity | The workflow section provides numbered steps but lacks explicit validation checkpoints. The 'When a unit test fails' section explains outcomes but doesn't provide a clear feedback loop for fixing issues. Missing explicit 'validate before proceeding' steps in the main workflow. | 2 / 3 |
Progressive Disclosure | Excellent structure with a comprehensive 'Additional Resources' section at the top linking to 12 reference files. Content is well-organized with clear sections, and references are one level deep with descriptive labels. The main content provides overview while pointing to detailed materials. | 3 / 3 |
Total | 10 / 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 | |