AI Memory System Architecture
System architecture facts: components, data flow, integration boundaries. Load when implementing cross-component features, debugging integration issues, or onboarding to the codebase. Topics: Event sourcing for the billing audit log.
Install
npx skills add hyxnj666-creator/ai-memory --skill ai-memory-system-architecturegit clone --depth 1 https://github.com/hyxnj666-creator/ai-memory.git /tmp/ai-memory
mkdir -p ~/.claude/skills
cp -r /tmp/ai-memory/docs/assets/demo/scenario/.claude/skills/ai-memory-system-architecture ~/.claude/skills/ai-memory-system-architecturePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# System Architecture > Auto-generated by ai-memory from AI chat history. Edit memories via `ai-memory list` / `extract` / `resolve` rather than this file — it is fully regenerated on every `ai-memory rules --target skills`. ## Event sourcing for the billing audit log The billing domain becomes event-sourced. The source of truth is an append-only `billing_events` Postgres table (`InvoiceCreated`, `LineItemAdjusted`, `PaymentCaptured`, etc.), each row carrying a SHA-256 hash chain over `(prev_hash, payload, timestamp)`. The current invoices table becomes a read-side projection rebuilt from the log. The rest of the app stays on the existing CRUD model — only billing needs this. Why: Event sourcing answers compliance directly: every state change is a first-class, immutable record. Hash-chaining provides tamper evidence without an external service. Scoping to billing keeps the operational cost contained. Rejected: Shadow-table journaling rejected — couples write-side logic to bookkeeping and does not give tamper evidence. External audit-log service rejected — added vendor cost without measurable gain over an in-database hash chain.
Details
- Skill name
ai-memory-system-architecture- Repository
- hyxnj666-creator/ai-memory
- Path
docs/assets/demo/scenario/.claude/skills/ai-memory-system-architecture/SKILL.md- License
- MIT
- Repo updated
- 7 May 2026
FAQ
What does the AI Memory System Architecture skill do?
System architecture facts: components, data flow, integration boundaries. Load when implementing cross-component features, debugging integration issues, or onboarding to the codebase. Topics: Event sourcing for the billing audit log.
How do I install the AI Memory System Architecture skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add hyxnj666-creator/ai-memory --skill ai-memory-system-architecture. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is AI Memory System Architecture popular?
It lives in hyxnj666-creator/ai-memory, which has 44 GitHub stars and 5 forks.
Related skills
AI Memory Coding Conventions
44hyxnj666-creator/ai-memory
Project coding conventions extracted from chat history. Load when writing new code, naming things, designing APIs, or reviewing PRs. Topics: Cursor pagination is mandatory for all paged GraphQL endpoints.
AI Memory Decision Log
44hyxnj666-creator/ai-memory
Technical decisions made for this project, with reasoning and rejected alternatives. Load when proposing architectural changes, evaluating alternatives, or asked why a choice was made. Topics: Adopt OAuth 2.0 authorization code flow with PKCE for the customer portal SPA.
Check Crewai API
49crewAIInc/skills
Current crewai 1.15.x API versus the 0.x API that coding assistants remember: imports, Agent/Task/Crew parameters and defaults, kickoff variants, CrewOutput fields, LLM model strings and provider extras, structured output (output_pydantic, response_model, response_format), guardrails, unified Memory, knowledge embedders, the `crewai create crew` wizard vs --classic, reset-memories flags, and removed features. Use when writing, reviewing, or debugging any crewai code, before trusting remembered crewai syntax, or when a user pastes errors like `cannot import name 'BaseTool' from 'crewai_tools'`,
Sankhya API Java
43andressaolivi/sankhya-skills
Conhecimento sobre os pontos de extensão Java do ERP Sankhya — interfaces oficiais de customização e padrões de uso da camada de persistência. Use quando o usuário perguntar sobre customização Java do Sankhya: AcaoRotinaJava, EventoProgramavelJava, RegraNegocioJava, TarefaJava, AcaoReguaCobranca, DynamicVO, JapeSession, EntityFacade, JdbcWrapper, ServiceContext, ServiceBroker; action buttons, eventos programáveis, regras de negócio, workflow Java, régua de cobrança, manipulação de VOs, persistência JAPE, SQL nativo com macros do Sankhya. NÃO use para configuração funcional do ERP (use sankhya-
Singbox Config
34shpirt/singbox-config
Generate, modify, migrate, and debug version-aware sing-box client configuration files for v1.13 and v1.14. Covers TUN and system proxy modes for end-user devices (SFM/SFA/SFI/CLI), RealIP vs FakeIP TUN templates, DNS/routing split rules, remote rule-set downloads, Clash API selectors, and node conversion for VLESS/VMess/Shadowsocks/Trojan/Hysteria2/TUIC/ShadowTLS/AnyTLS. Use when the user mentions sing-box, singbox, SFM/SFA/SFI, TUN/system proxy setup, split routing, DNS hijack, FakeIP, selector behavior, per-app routing, network strategy, TLS fragment/ECH, proxy chaining, or asks to create,
Spec Goal Development
44hanshuang1008-del/spec-goal-development
面向跨项目 Codex 编码智能体的默认开发编排 Skill。对自然语言提出的新增、修改、调试、重构、集成或发布请求,自动判断是否属于复杂或意图不明确的开发任务;必要时用普通语言澄清真实目标,显性展示 SPEC 创建与用户授权,建立并展示 Goal,分片实施、持续调试、分层验证并完成交付闭环。非开发任务和简单、低风险、局部且可逆的开发任务走轻量路径。
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.