- Home
- Skills
- Data & Databases
- Data Quality and Governance
More screenshots
Works with the AI Agents you already use
Data Quality and Governance
Ensure quality, observability, lineage, contracts and privacy. 10 ordered skills, starting with Data Quality, Data Observability, Data Catalog and Lineage.
Free
Data Quality and Governance
Example session with this skill installed
Analyze this customer table schema for PII and suggest a data contract using ODCS: customer_id (int), email (string), signup_date (date), credit_score (int). We use dbt and Snowflake.
- Read your context and instructions
- Compiled the data quality
I have analyzed the schema for customer_table. I identified email as a direct identifier and credit_score as sensitive financial data.
Data Contract and PII Analysis
| Column | Classification | Recommendation |
|---|---|---|
| customer_id | Technical ID | Primary Key. No masking required. |
| PII (Direct) | Mask in analytics; encrypt at rest. | |
| signup_date | Quasi-identifier | Round to month if used for broad analytics. |
| credit_score | Sensitive | Restrict access to Finance role; apply differential privacy. |
ODCS Contract Draft (YAML)
dataset: customer_table
version: 1.0.0
status: production
owner: customer_success_team
domain: billing
schema:
- column: customer_id
type: NUMBER
description: Unique internal identifier
primary_key: true
- column: email
type: STRING
classification: pii
pii_handling: encrypted
- column: credit_score
type: NUMBER
classification: sensitive
quality_rules:
- type: not_null
column: customer_id
- type: unique
column: customer_id
- type: pattern_match
column: email
pattern: "^[\\w-\\.]+@([\\w-]+\\.)+[\\w-]{2,4}$"
Next steps
- Implement the dbt
persist_docsconfig to sync these descriptions to Snowflake. - Define a
finance_analystrole in Snowflake with a masking policy for theemailcolumn. - Set up a dbt test to validate the email regex pattern.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Data and compliance leaders often need a repeatable process, not a one-off prompt. This pack targets: Ensure quality, observability, lineage, contracts and privacy.
What's inside (10 skills, suggested learning order)
- Data Quality — Test and monitor data.
- Data Observability — Detect pipeline failures.
- Data Catalog and Lineage — Document data origin and use.
- Data Governance — Policies and responsibilities for data.
- Master Data Management — Consolidate master data.
- Data Contracts — Schema agreements between teams.
- Data Security and Privacy — Protect sensitive data.
- Data Anonymization and Pseudonymization — Reduce re-identification risk in personal data.
- Metadata Management — Organize metadata and glossaries.
- Data Dictionary and Table Documentation — Document the meaning and use of data.
Why a skill pack instead of a one-off prompt
Each skill gives the agent a defined trigger, step-by-step procedure and output format, so results are consistent across sessions and easier to review.
How to use
- Install the pack in your SKILL.md-compatible agent.
- Ask for the task in plain language (for example: "test and monitor data").
- Review the output against the skill's quality checks before using it.
Known limitations
- Outputs are drafts that need human review; they are not professional, legal or financial advice.
- Tools, APIs and prices change; check current vendor documentation before relying on version-specific details.
- Quality depends on the context you give the agent (data, requirements, constraints).
- Tested only where stated in the Compatibility note.
Also by Rodrigo Santos
Data Annotation and Labeling; Cloud Data Platforms and Data for AI; Customer and Sales Analytics
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Data & Databases.
Requires existing schema or DDL metadata to function. Does not provide direct legal counsel or official regulatory certification. Tooling-specific output requires the relevant stack installed.
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 buying a skill.
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
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 4 days ago
- Free with an Agensi account
Nothing to install. It runs in your AI agent.
Instruction-only skills. No network access, shell commands or file writes are required; each skill reads the context you provide and returns a document.