Elysia Architecture
Use when the user asks about an Elysia API on Bun with typed routes, Elysia project structure, plugin/module layout, lifecycle hook order, TypeBox schemas or auth macros. Produces an Elysia app structure with fail-fast config. Not for Eden Treaty, WebSocket or macro recipes (use elysia-patterns).
Install
npx skills add j4flmao/agent-skills --skill elysia-architecturegit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/backend/elysia/architecture ~/.claude/skills/elysia-architecturePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Elysia Architecture ## Purpose Structure Elysia.js applications with plugin-based architecture — lifecycle hooks, type-safe schema, Eden Treaty client generation, and production middleware configuration. ## Agent Protocol ### Trigger User request includes: `elysia app structure`, `elysia project layout`, `elysia plugin`, `elysia lifecycle`, `elysia architecture`, `elysia folder structure`, `elysia config`. ### Input Context - Bun version (1.0+) - Elysia version (1.x) - Plugins used (cors, swagger, websocket, auth) - Database (Bun SQLite, Drizzle, Prisma) ### Output Artifact Project structure, plugin layout, lifecycle hook order, configuration, Eden Treaty client setup. ### Response Format Produce artifact directly. No preamble, no postamble, no explanations. No filler, no hedging. ### Completion Criteria - Plugin-based architecture with clear separation - Lifecycle hooks in correct order - Type-safe schemas with Elysia `t` (TypeBox) for body, query, params and response - Eden Treaty client typed from the exported `App` type - Environment validated at startup ### Max Response Length 4096 tokens ## Architecture Decision Trees ### Plugin Architecture vs Monolithic | Criterion | Plugin Architecture | Monolithic | |-----------|-------------------|------------| | Feature count | 5+ features | 1-3 features | | Team size | 2+ developers | Solo | | Reuse | Multiple apps share plugins | Single app | | Testing | Isolated per plugin | End-to-end |
Details
- Skill name
elysia-architecture- Repository
- j4flmao/agent-skills
- Path
skills/backend/elysia/architecture/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Elysia Architecture skill do?
Use when the user asks about an Elysia API on Bun with typed routes, Elysia project structure, plugin/module layout, lifecycle hook order, TypeBox schemas or auth macros. Produces an Elysia app structure with fail-fast config. Not for Eden Treaty, WebSocket or macro recipes (use elysia-patterns).
How do I install the Elysia Architecture skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill elysia-architecture. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Elysia Architecture popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Elysia Patterns
45j4flmao/agent-skills
Use when the user asks about Elysia Eden Treaty clients, Elysia WebSocket pub/sub, Elysia macros, custom plugins, hook scopes (local, scoped, global) or file upload validation. Produces Elysia recipe code. Not for app folder structure (use elysia-architecture).
Ecmwf Mars
23ecmwf/ecmwf-weather-skills
Handles any question about ECMWF MARS, including whether MARS access works from this machine — load it first. Writes, checks, sizes and runs requests against ECMWF's MARS archive — the full operational IFS archive (HRES, ENS, waves, past runs, model levels) ERA5 and the CARRA/CERRA regional reanalyses (class=rr) via MARS — through the ECMWF Web API (~/.ecmwfapirc) or a local mars client on ECMWF systems. Use when a task mentions MARS, asks whether MARS or the ECMWF Web API works from this machine, the ECMWF archive, past operational forecasts older than Open Data keeps, ensemble members or mod
Enterprise Architecture Governance
45j4flmao/agent-skills
Use when the user asks about an architecture review board (ARB), architecture decision rights, architecture principles, design review gates, exception and waiver process or compliance with standards. Produces ARB charter, review process and principle checks. Not for the TOGAF ADM method (use enterprise-togaf-zachman) or a single design doc (use create-tech-spec).
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.