Data Safety Suite
Three local auditors that catch data disasters before they reach production. SQL Migration Safety Doctor flags destructive or locking migration operations (DROP, TRUNCATE, non-concurrent index builds, NOT NULL without a default) and offers safer rewrites. dbt Test & Quality Auditor finds untested models, sources without freshness, and undocumented keys, with suggested tests YAML to drop into schema.yml. PII & Data-Leak Scanner finds personal data (emails, SSNs, card numbers, phones) in schemas, seed data, and logs before it leaks. For data and backend engineers who want migrations that won't lock the table, dbt projects that actually test their data, and seed files that aren't quietly shipping real PII. Read-only and evidence-first; nothing connects to your database or leaves your machine.
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 3 skills unlock instantly in your library.
What's included
3 skillsAudit local dbt SQL and YAML for missing model tests, source freshness and test gaps, likely-key coverage, missing model descriptions, SELECT *, and raw table references. Get severity-ranked findings plus starter tests YAML for model/key gaps without running dbt or querying a warehouse.
Scan local SQL, CSV, JSON, seed, fixture, and log files for PII-indicating names plus email-, SSN-, card-, and phone-like values. Get file/line findings with matched values redacted by default—no network, writes, database connection, or compliance claim.
Catch the dangerous migration before it locks or wrecks your production database. Scans SQL migration files for destructive and risky operations: DROP and TRUNCATE, drops without IF EXISTS, lossy column-type changes, NOT NULL added without a default, DELETE or UPDATE with no WHERE, non-concurrent index builds, dropped constraints, renames, and data backfills mixed into schema changes. Each finding is ranked by severity with a safer rewrite. Postgres, MySQL, and SQLite.
See it in action
🧪 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.
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 these skills and uses them on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
3 uses
Times these skills were used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.