Will it choose a standard retention period for every dataset?

No. Periods need a source or explicit approved business decision, with scope and a defined clock trigger.

Does it account for backups and exports?

Yes. It maps copies, derived data, vendors, archives and backup lifecycle rather than assuming primary deletion removes everything.

Can it override a legal hold or delete records?

No hold is overridden by the planning workflow. Disposition requires approved rules, hold checks, scoped previews and explicit human authorization.

Data Retention Architect — Define What Data to Keep

Example session with this skill installed

Illustrative scenario: Create a retention-schedule template for support tickets. We know they exist in the support system, weekly exports and backups. Purpose is issue resolution and service improvement. Owner is Support Operations. No jurisdiction, contract, legal hold process or approved period exists. Do not pick a duration or authorize deletion; identify missing evidence and implementation gates.

Read your context and instructions
Compiled the data retention architect

Retention architecture draft — illustrative, not approved for disposition

Data class: support tickets and attachments. Owner: supplied Support Operations. Systems/copies: support platform, weekly exports and backups; derived analytics and vendors require inventory confirmation. Purpose: issue resolution and service improvement, supplied by user.

Retention rule fields: source/driver; applicable scope; minimum requirement; maximum justified period; event trigger; approved duration; hold exception; disposition method; owner; rule version; approval; implementation control; audit evidence. Duration and trigger remain UNAPPROVED/UNKNOWN. No arbitrary period selected.

Evidence gaps: relevant jurisdictions, ticket content and sensitivity, contract terms, actual legal requirements, business justification after closure, hold ownership, export locations, backup lifecycle, vendor deletion capability and derived-data dependencies. Legal/records professionals determine applicability and approve appropriate rules.

Implementation proposal: map approved class and trigger to system records; exclude active holds; preview counts and minimal masked samples; verify scope and dependency effects; distinguish primary-system deletion from asynchronous backup expiry; track vendor handling and audit outcomes. No “deleted everywhere” claim without evidence.

Governance gates: approved source-backed rule; confirmed tenant/environment and owner; hold checks; technical dry-run review; backup/vendor treatment; authorized disposition approver; audit destination and recovery limitations.

Next action: complete inventory and evidence review before selecting a retention period or changing TTLs.

Execution notes: no records deleted, holds released, settings changed or compliance certified. This is a planning template, not legal advice or destruction authorization.

Connects securely to your tools. The creator never sees your data.

About this skill

Data Retention Architect connects records and data inventory to retention purpose, ownership, systems, event triggers, verified rules and disposition capability. It distinguishes minimum obligations from maximum privacy-oriented retention and avoids arbitrary “keep forever” or unsupported durations.

The workflow accounts for backups, immutable storage, exports, derived data, archives, vendors and legal holds, then produces schedules and implementation specifications with audit evidence. Legal/business drivers and explicit organizational decisions remain traceable; overlapping obligations require appropriate review.

It supports inventory, policy architecture and privacy-engineering planning, not definitive legal advice, statutory applicability decisions or destruction authorization. Exact jurisdiction-specific periods require qualified verification. Deletion, TTL changes, hold release and other consequential operations need separate approval and scoped dry runs; successful deletion is never invented.

How to use

Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

Reviews

No reviews yet

Be one of the first to try it. Every listed skill passes our trust checks below.

Security scanned

Passed 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.

Data Retention Architect — Define What Data to Keep