oliver-kriska/claude-elixir-phoenix

Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.

What it solves

This project provides a specialized plugin for Claude Code (and other AI coding assistants like Amp, Codex, Pi, and OpenCode) to help developers build Elixir and Phoenix applications. It addresses the gap where general-purpose AI models lack deep, domain-specific knowledge of Elixir/Phoenix pitfalls—such as assign_new behavior during reconnects, Ecto query performance (N+1 queries), and Oban job idempotency.

How it works

The plugin coordinates a fleet of 26 specialist agents (using models like Claude Opus and Sonnet) and 51 skills to automate the development lifecycle. It uses a structured workflow of planning, implementation, and verification:

  • Planning: Research agents analyze the codebase to create a structured plan.
  • Implementation: The system implements tasks and compiles the code after each change, stopping immediately if "Iron Laws" (non-negotiable coding rules) are violated.
  • Review: Specialist agents audit the code for idioms, security, and compilation errors in parallel.
  • Investigation: Tools like phx-investigate and phx-trace help debug deep bugs and trace calls.

Who it’s for

Elixir and Phoenix developers who use AI coding assistants and want to prevent production bugs by enforcing domain-specific best practices and architectural patterns.

Highlights

  • 26 Specialist Agents: Dedicated roles for architecture, security, and domain-specific logic (e.g., Oban specialist, LiveView architect).
  • 51 Canonical Skills: A comprehensive library of skills covering Ecto, LiveView, and Phoenix patterns.
  • Iron Laws: A set of 26 non-negotiable rules that catch bugs tests often miss.
  • Multi-Runtime Support: Compatible with Claude Code, Amp, Codex, Pi, OpenCode, and DeepSeek Harness.
  • Automated Workflows: Integrated commands for planning (/phx:plan), working (/phx:work), and reviewing (/phx:review).

Related

  • Project
    shinpr/claude-code-workflows

    Claude Code Development Workflows is a set of Claude Code plugins that turn the Claude AI assistant into a structured development pipeline. The plugins provide “recipes” (e.g. `/recipe‑implement`, `/recipe‑design`, `/recipe‑review`) that enforce outcome agreement, design documentation, work‑plan generation, task‑level implementation with automated verification, and an independent security review. Three plugin families cover backend, React frontend, and full‑stack projects, and they can be installed via Claude’s marketplace. The system is useful when you need repeatable safety gates and a formal hand‑off between design and code generation; for quick prototypes you can skip it.

  • Project
    plugin87/ux-ui-agent-skills

    UX/UI Agent Skills is a Claude‑agent knowledge kit that provides design tokens, component specs, accessibility audits, and 17 slash‑command‑style “skills” to let the AI act as a senior UI/UX architect. It can generate token‑driven code for any framework (React, Vue, SwiftUI, Flutter, etc.), enforce WCAG 2.2 compliance via 37 CI gates, and includes a library of 138 design systems for aesthetic direction. Install via `npx ux-ui-agent-skills init`; the agent reads a `CLAUDE.md` brief and runs the skills or natural‑language prompts to produce design assets, code, and audits.

  • Project
    pedrohcgs/claude-code-my-workflow

    A fork‑ready framework that uses Anthropic Claude Code to automate academic tasks (slides, papers, data analysis, etc.) via specialised agents, a ten‑gate quality suite, and extensible skills; includes setup scripts, pre‑commit hooks, and detailed documentation.

  • Project
    alchaincyf/huashu-skills

    A curated index of 53 Claude‑compatible *Agent Skills* (design, data, video, writing, persona‑based reasoning, etc.) with install instructions, an update checker, and a machine‑readable catalog. Enables AI agents to perform concrete productivity tasks without custom coding.

  • Project
    Sushegaad/Claude-Skills-Governance-Risk-and-Compliance

    A collection of installable knowledge packages for Claude that provide expert-level guidance and audit-ready documentation for over 30 global Governance, Risk, and Compliance (GRC) frameworks.