Design tenant-scoped memory, retrieval and retention for agents. Use when planning RAG, conversation history, vector stores or remembering across sessions.
Start a fresh conversation. Replace the highlighted placeholders.
Use agent-memory-systems to design retrieval-focused memory for [agent use case] serving [verified tenants/users] within [stack, retention consent, privacy, latency, and context limits]. Read the detailed guide's tenant contract and relevant storage/chunking sections. Specify semantic/episodic/procedural records, source IDs, timestamps, namespaces, bounded retrieval, conflict/version rules, and adapter prerequisites. Preserve originals and propose consolidation without deletion. Deliver architecture, held-out retrieval validation and isolated cross-identity/stale-record/failed-write test plans, plus unresolved adapters, hosted costs, and data destinations. Do not perform persistence/provider operations beyond those explicitly authorized.
Required inputs
[agent use case]
[verified tenants/users]
[stack, retention consent, privacy, latency, and context limits]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: agent-memory-systemsdescription: Design tenant-scoped memory, retrieval and retention for agents. Use when planning RAG, conversation history, vector stores or remembering across sessions.metadata: aas-risk: safe aas-source: vibeship-spawner-skills (Apache 2.0) aas-date-added: '2026-02-27'
Agent Memory Systems
Choose semantic records for facts/preferences, episodic records for events, and procedural records for reusable methods. Keep retrieval quality separate from storage volume and bind persistent access to verified identity.
Procedure
Establish the actual task, authenticated tenant/user, permission to retain content, retention limits and existing store/model versions.
Read the guide's tenant-scoped contract and relevant storage/chunking sections. Select an adapter supported by the installed SDK; the guide's historical sketches are not deployable integrations.
Specify record IDs, source evidence, timestamps, namespace, retrieval limits and conflict/version policy. Preserve originals and propose consolidation without deletion.
Test cross-identity rejection, stale/conflicting records, bounded retrieval and failed writes with isolated fixtures. Benchmark retrieval against held-out questions before expanding storage.
Deliver the architecture and evidence-backed change plan, listing unresolved adapters and hosted cost/data destinations. Apply only the persistence or provider operations actually authorized.
Detailed Guide
Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.
When to Use
Design memory namespaces and retention for an agent serving distinct tenants or users.
Diagnose retrieval of stale, conflicting or unauthorized conversation records.
Plan an embedding/store migration while preserving source records and verifying isolation.
Example
Request: “Our support agent forgets preferences between sessions. Design memory for two customer tenants without sharing their history.”
Output: Load the tenant-scoped contract and background-extraction sections. Propose a semantic namespace per verified tenant/user, records with source IDs and revisions, and bounded retrieval. Retain conflicting preferences until the owner resolves them; include tests that tenant B cannot retrieve or consolidate tenant A records. Identify the existing persistent adapter and consent/retention evidence before any write.
Limitations
Use this skill only when the task clearly matches the scope described above.
Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
agent-memory-systems by sickn33 · The Skill Leaderboard