Privacy retention and right to delete
Skill vaquarkhan/data-engineering-agent-skills/skills/privacy-retention-and-right-to-delete
Guides agents through privacy, retention, and deletion workflows in data systems. Use when handling personal data, retention limits, deletion requests, legal holds, or data minimization requirements across pipelines and published datasets.From its SKILL.md
npx -y skills add vaquarkhan/data-engineering-agent-skills --skill privacy-retention-and-right-to-deleteAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.4 KB, 435 tokens by cl100k_base, as published. Nobody here has run it
Privacy, Retention, And Right To Delete
Overview
Use this skill when the data platform must respect privacy obligations as an engineering behavior, not a policy slide. It helps agents make retention, deletion, masking, and minimization explicit across storage, transformations, and publishes.
When to Use
- handling personal or regulated data
- defining retention rules
- implementing deletion or erasure requests
- changing how sensitive fields are stored, copied, or published
- validating that downstream systems do not retain data longer than allowed
Do not assume masking alone satisfies retention or deletion obligations.
Workflow
-
Classify the data and obligations. Clarify:
- sensitive fields
- retention limit
- deletion trigger
- legal hold exceptions
- downstream replication paths
-
Map where the data lives. Include:
- raw landing
- transformed tables
- serving layers
- extracts
- caches and feature stores
-
Define the enforcement path. Decide how the system will:
- prevent unnecessary copies
- enforce retention windows
- process deletions
- prove compliance actions happened
-
Validate downstream propagation. Deletion in one layer is not enough if copies remain elsewhere.
-
Record exceptions and audit evidence.
Common Rationalizations
| Rationalization | Reality |
|---|---|
| "The source system already deleted it." | Downstream data products may still retain copies. |
| "We only use hashed identifiers." | Hashing does not eliminate all privacy or retention duties. |
| "We can clean up old data later." | Retention failures often become expensive compliance incidents. |
Red Flags
- no retention schedule exists
- deletion requests stop at one system boundary
- old extracts and caches are ignored
- privacy controls rely on undocumented manual steps
Verification
- Sensitive data and retention obligations are classified
- All material storage locations and copies are mapped
- Deletion and retention enforcement are explicit and testable
- Audit evidence or runbooks exist for compliance actions
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.