skills.rest
guardiatechnology
guardiatechnologyOFFICIAL
Explore all skills by this author →
WebsiteGitHub

kata-agent-memory-design

Design a three-layer agent memory specification with TTL, retention, and PII controls.

Updated Sep 3, 2025
Search Tags:#architecture#documentation#data retention#agent memory#lgpd#pii redaction#privacy by design
One-click install
npx skills add https://github.com/guardiatechnology/design-system --skill kata-agent-memory-design
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kata-agent-memory-design
Source: https://github.com/guardiatechnology/design-system/tree/main/.claude/skills/kata-agent-memory-design
Command: npx skills add https://github.com/guardiatechnology/design-system --skill kata-agent-memory-design

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps teams define an agent memory architecture that is practical for operations while staying compliant with retention and privacy requirements.

Core Features & Use Cases

  • 3 mandatory memory layers: short (session window), medium (per-tenant client history), and long (shared, stable knowledge).
  • Explicit TTL and retention policies: maps retention to a reference file and enforces right-sizing by event classes.
  • PII-safe handling and deletion workflows: mandates redaction for persistence, anonymization for ingestion, and a defined right-to-be-forgotten API with an SLA.

Quick Start

Ask an AI to generate docs/{context}/agents/{agent}/memory.md by filling in short, medium, and long layer schemas plus retention and deletion details for {agent} within the {context} bounded scope.

Frequently Asked Questions about kata-agent-memory-design

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is a 3-layer agent memory architecture?▼

Agent memory PII redaction mandates redaction before persisting data, applies anonymization during ingestion, and defines a right-to-be-forgotten API with an SLA to execute deletion workflows for compliant data handling.

How do I design an agent memory specification with TTL and retention policies?▼

Agent memory PII redaction mandates redaction before persisting data, applies anonymization during ingestion, and defines a right-to-be-forgotten API with an SLA to execute deletion workflows for compliant data handling.

How do I handle PII redaction and right-to-be-forgotten requests in agent memory?▼

Agent memory PII redaction mandates redaction before persisting data, applies anonymization during ingestion, and defines a right-to-be-forgotten API with an SLA to execute deletion workflows for compliant data handling.

Does agent memory design support LGPD and privacy by design compliance?▼

Agent memory PII redaction mandates redaction before persisting data, applies anonymization during ingestion, and defines a right-to-be-forgotten API with an SLA to execute deletion workflows for compliant data handling.

When do I need a multi-layer agent memory specification?▼

Agent memory PII redaction mandates redaction before persisting data, applies anonymization during ingestion, and defines a right-to-be-forgotten API with an SLA to execute deletion workflows for compliant data handling.

What limitations exist when applying TTL constraints across agent memory layers?▼

Agent memory PII redaction mandates redaction before persisting data, applies anonymization during ingestion, and defines a right-to-be-forgotten API with an SLA to execute deletion workflows for compliant data handling.

Related Skills

Explore More Software Engineering Skills→
0xmariowu0xmariowu
40

autosearch:delegate-subtask

Define auditable execution contracts for delegated subtasks with budgets and schemas.

Community
Advanced
cardinalconseilscardinalconseils
3

api-docs

Detect API endpoints across frameworks and generate Markdown or OpenAPI docs.

Community
Advanced
lawve-ailawve-ai
630

cookie-policy-malik-taiar

Draft CNIL-compliant cookie policies using reference templates and regulatory guidance.

Official
Intermediate
TDMoralesTDMorales

intelligent-cache

Implement a multi-layer caching system with type-specific TTLs and get-or-generate semantics.

Community
Advanced