AB cm-dbt-model-auditor
Audit dbt (data build tool) projects for model quality, test coverage, documentation completeness, performance, and adherence to best practices. Checks naming conventions, ref/source usage, materialization strategy, DAG structure, and model contracts. Use when asked to audit a dbt project, review dbt models, check dbt test coverage, validate dbt documentation, assess dbt model performance, check dbt best practices, or review data model quality. Triggers on "dbt audit", "dbt review", "dbt model", "dbt quality", "dbt test coverage", "dbt documentation", "dbt best practices", "dbt lint", "data model audit", "dbt project review", "dbt health check".
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, consistency, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (cm-dbt-model-auditor) differs from the folder (dbt-model-auditor)
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 49 steps
- 100Execution cost. Instruction body is 3469 tokens
- low The response is described with custom markup (5 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +3Description length 653: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 49 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.