- Home
- Skills
- Data & Databases
- 🧪 dbt Test & Quality Auditor
More screenshots
Works with the AI Agents you already use
🧪 dbt Test & Quality Auditor
Get reviewable findings without running dbt or connecting to a warehouse.
$15
🧪 dbt Test & Quality Auditor
Example session with this skill installed
Run the bundled read-only scanner on fixtures/risky-sample and show all findings. Use Python with --format markdown; do not run dbt, query a warehouse or change any files. This is a synthetic demonstration, not a customer project.
- Read your context and instructions
- Compiled the dbt test
Synthetic bundled-fixture run. Workspace prefixes shortened for readability; all eight findings retained. Exit status 1 means findings.
dbt Test Quality Auditor Scan Report
Files scanned: 2
Findings: 8
Heuristic text review only; this does not parse or validate all YAML, compile dbt or execute database tests.
[MEDIUM] DBT005 - fixtures/risky-sample/models\orders.sql:1
Model uses SELECT *.
Remediation: Select explicit columns to stabilize model contracts.
[HIGH] DBT006 - fixtures/risky-sample/models\orders.sql:2
Model references a raw table instead of ref() or source().
Remediation: Use {{ ref('model') }} or {{ source('source','table') }}.
[MEDIUM] DBT004 - fixtures/risky-sample/models\schema.yml:4
Model orders is missing a description.
Remediation: Add a model description in schema.yml.
[HIGH] DBT001 - fixtures/risky-sample/models\schema.yml:4
Model orders has no unique/not_null tests.
Suggested tests YAML
version: 2
models:
- name: model_name
description: Add a clear model description.
columns:
- name: id
tests:
- unique
- not_null
Remediation: Add appropriate unique/not_null tests.
[MEDIUM] DBT003 - fixtures/risky-sample/models\schema.yml:4
Likely key order_id is missing a not_null test.
Suggested tests YAML
version: 2
models:
- name: model_name
description: Add a clear model description.
columns:
- name: id
tests:
- unique
- not_null
Remediation: Add not_null to key columns.
[MEDIUM] DBT003 - fixtures/risky-sample/models\schema.yml:4
Likely key customer_id is missing a not_null test.
Suggested tests YAML
version: 2
models:
- name: model_name
description: Add a clear model description.
columns:
- name: id
tests:
- unique
- not_null
Remediation: Add not_null to key columns.
[MEDIUM] DBT002 - fixtures/risky-sample/models\schema.yml:1
Source has no freshness configuration.
Remediation: Add source freshness thresholds where freshness matters.
[MEDIUM] DBT002 - fixtures/risky-sample/models\schema.yml:1
Source has no tests.
Remediation: Add source tests or data_tests for key fields.
Connects securely to your tools. The creator never sees your data.
About this skill
Catch dbt test gaps before bad data ships
Audit local dbt model SQL and schema YAML for missing tests, source freshness and test gaps, likely-key coverage, missing model descriptions, SELECT *, and raw table references. Get reviewable findings without running dbt or connecting to a warehouse.
See what the scanner can flag
Identify models with no schema entry or unique/not_null tests, sources missing freshness or tests, likely ID columns lacking unique or not_null coverage, models missing descriptions, SELECT * usage, and raw FROM or JOIN references that may need ref() or source().
Get evidence and usable starting points
SQL findings include file and line evidence, severity, a message, and remediation. Missing model-test and likely-key findings also include starter tests YAML to review and adapt; the skill never writes it into the project.
Run locally and read-only
The bundled scanner uses only the Python 3 standard library. It requires no PyYAML, dbt invocation, warehouse credentials, network access, secret reads, or file writes.
Know what still needs verification
The parser is heuristic: unusual YAML can be missed or refused. Model findings cite the model entry line; aggregate source findings cite line 1 and do not verify every source. Confirm each finding in project context before changing tests, freshness thresholds, or model references.
- Heuristic static audit; it does not run dbt, execute tests, or query a warehouse.
- Starter tests YAML is emitted only for missing model-test and likely-key findings; it is a template to review and adapt.
- Unusual YAML layouts can be missed or refused. Model findings cite the model entry line; aggregate source findings cite line 1 and do not verify every source.
- Confirm likely keys, freshness expectations, and intentional raw-table exceptions in project context.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 12 days ago
Requires
Permissions
File Scopes
Read-only inspection first. The bundled auditor reads matching dbt files and prints markdown or JSON findings plus suggested tests: YAML. It installs nothing, transmits nothing, modifies nothing, and never runs dbt or touches your warehouse. Any write, install, deploy, or live-account action requires explicit user confirmation.