Backend Elixir

Use when the user asks about Phoenix, Phoenix LiveView, Ecto schemas and changesets, GenServer state, OTP supervision trees, Oban jobs or Phoenix PubSub. Produces Phoenix/Elixir backend code organized by contexts. Not for Elixir language basics (use lang-elixir).

45 stars 6 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add j4flmao/agent-skills --skill backend-elixir
Manual install
git clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/backend/elixir ~/.claude/skills/backend-elixir

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Elixir

## Purpose
Build fault-tolerant, concurrent applications with Elixir/OTP — Phoenix web layer, LiveView interactivity, Ecto persistence, supervision trees, process architecture.

## Agent Protocol

### Trigger
User request includes: `Elixir`, `Phoenix`, `Phoenix LiveView`, `OTP`, `BEAM`, `Elixir macros`, `Ecto`, `mix`, `phx.gen`, `Supervisor`, `GenServer`, `Phoenix channels`, `Phoenix PubSub`, `Elixir processes`, `iex`.

### Input Context
- Framework (Phoenix, Phoenix LiveView, bare Elixir)
- Persistence (Ecto with PostgreSQL, Ecto with SQLite, ETS)
- State management (GenServer, Agent, ETS, Phoenix PubSub)
- Deployment (Elixir releases, Docker, Gigalixir, Fly.io)

### Output Artifact
Phoenix project structure, OTP supervision tree, Ecto schema, LiveView module, router config.

### Response Format
Produce artifact directly. No preamble, no postamble, no explanations. No filler, no hedging, no transitions. Strip articles a/an/the where unambiguous. Compress output — why use many token when few do trick.

### Completion Criteria
- Phoenix project generated with mix phx.new
- Contexts separated by domain boundary
- Ecto schemas with proper associations
- LiveView with state management and event handling
- Supervision tree with appropriate restart strategy

### Max Response Length
4096 tokens

## Workflow

### Step 1: Phoenix Project Setup
Read the full skill on GitHub

Details

Skill name
backend-elixir
Path
skills/backend/elixir/SKILL.md
License
MIT
Repo updated
17 November 2026

FAQ

What does the Backend Elixir skill do?

Use when the user asks about Phoenix, Phoenix LiveView, Ecto schemas and changesets, GenServer state, OTP supervision trees, Oban jobs or Phoenix PubSub. Produces Phoenix/Elixir backend code organized by contexts. Not for Elixir language basics (use lang-elixir).

How do I install the Backend Elixir skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill backend-elixir. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Backend Elixir popular?

It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.

Related skills

Agent Observability

45

j4flmao/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).

DevOps & Cloud

AI Agent Architectures

45

j4flmao/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, LLMs & Agents

AI Agent Core Loop

45

j4flmao/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).

AI, LLMs & Agents

Backend Event Driven

45

j4flmao/agent-skills

Use when the user asks about event-driven architecture, domain vs integration events, publishing events between services, Kafka or RabbitMQ consumers, event schema versioning, DLQs or sagas. Produces event catalog, topology and consumer code. Not for event stores (use backend-event-sourcing) or broker operations (use backend-message-queue).

Software Development

Backend Distributed Locking

45

j4flmao/agent-skills

Use when the user asks about a distributed lock, two workers processing the same job, Redis lock (SET NX PX), Redlock, pg_advisory_lock, leases or fencing tokens. Produces a lock design with TTLs, fencing and failure handling. Not for job deduplication via idempotency keys (use backend-idempotency).

Software Development

Backend Event Sourcing

45

j4flmao/agent-skills

Use when the user asks about event sourcing, storing every change as an append-only event log, event store, rehydrating aggregates, snapshots, upcasting or projection rebuilds. Produces an event-sourced aggregate and store design. Not for CQRS without event sourcing (use backend-cqrs-patterns).

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.