Phoenix Contexts logo

Phoenix Contexts

Community
oliver-kriska
phoenix-contexts

Phoenix context design — creating/splitting contexts, Scope (1.8+), Ecto.Multi, PubSub, routers, plugs, controllers. Use when editing contexts, routers, or designing boundaries.

Overview

Publisheroliver-kriska
Repositoryclaude-elixir-phoenix
Skill namephoenix-contexts
Stars
555
Forks
40
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by oliver-kriska on GitHub. Read the source before you install it.

Installation

Install the Phoenix Contexts AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git /tmp/claude-elixir-phoenix
mkdir -p .claude/skills
cp -r /tmp/claude-elixir-phoenix/plugins/elixir-phoenix/skills/phoenix-contexts .claude/skills/phoenix-contexts
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Phoenix Contexts in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Phoenix Contexts on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Phoenix Contexts is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Phoenix Contexts Reference

Ash projects: Ash.Domain replaces Phoenix contexts for data access — use the ash-framework skill. Context boundary and PubSub patterns still apply.

Reference for designing and implementing Phoenix contexts (bounded contexts).

Iron Laws — Never Violate These

  1. CONTEXTS OWN THEIR DATA — Never query another context's schema directly via Repo
  2. SCOPES ARE MANDATORY (Phoenix 1.8+) — Every context function MUST accept scope as first parameter
  3. THIN CONTROLLERS/LIVEVIEWS — Controllers translate HTTP, business logic stays in contexts
  4. NO SIDE EFFECTS IN SCHEMAS — Use Ecto.Multi for transactions with side effects

Context Structure

lib/my_app/
├── accounts/           # Context directory
│   ├── user.ex         # Schema
│   ├── scope.ex        # Scope struct (Phoenix 1.8+)
├── accounts.ex         # Context module (public API)

Phoenix 1.8+ Scopes (CRITICAL)

All context functions MUST accept scope as first parameter:

elixir
def list_posts(%Scope{} = scope) do
  from(p in Post, where: p.user_id == ^scope.user.id)
  |> Repo.all()
end

def create_post(%Scope{} = scope, attrs) do
  %Post{user_id: scope.user.id}
  |> Post.changeset(attrs)
  |> Repo.insert()
  |> broadcast(scope, :created)
end

Quick Decisions

When to SPLIT contexts?

  • Module exceeds ~400 lines
  • Functions don't share domain language
  • Could theoretically be a separate microservice
  • Team member could own it independently

When to KEEP together?

  • Resources share vocabulary and domain concepts
  • Functions frequently operate on same data together
  • Splitting would create excessive cross-context calls

Cross-Context References

elixir
# ✅ Reference by ID, convert at boundary
def create_order(%Scope{} = scope, user_id, product_ids) do
  with {:ok, user} <- Accounts.fetch_user(scope, user_id) do
    do_create_order(scope, user.id, product_ids)
  end
end

# ❌ Reaching into other context's internals
alias MyApp.Accounts.User  # Don't do this
Repo.all(from o in Order, join: u in User, ...)  # Don't query other schemas

Anti-patterns

WrongRight
Service objects (UserCreationService)Context functions (Accounts.create_user/2)
Repository pattern wrapping RepoRepo IS the repository
Direct Repo calls in controllersDelegate to context
Schema callbacks with side effectsUse Ecto.Multi

Version Notes

  • Phoenix 1.8+: Uses built-in %Scope{} struct for authorization context
  • Phoenix 1.7: Requires manual authorization context (see ${CLAUDE_SKILL_DIR}/references/scopes-auth.md "Pre-Scopes Patterns")

References

For detailed patterns, see:

  • ${CLAUDE_SKILL_DIR}/references/context-patterns.md - Full context module, PubSub, Multi, cross-boundary
  • ${CLAUDE_SKILL_DIR}/references/scopes-auth.md - Scope struct, multi-tenant, authorization, plugs
  • ${CLAUDE_SKILL_DIR}/references/routing-patterns.md - Verified routes, pipelines, API auth
  • ${CLAUDE_SKILL_DIR}/references/plug-patterns.md - Function/module plugs, placement, guards
  • ${CLAUDE_SKILL_DIR}/references/json-api-patterns.md - JSON controllers, FallbackController, API auth

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Phoenix Contexts AI skill do?

Phoenix context design — creating/splitting contexts, Scope (1.8+), Ecto.Multi, PubSub, routers, plugs, controllers. Use when editing contexts, routers, or designing boundaries.

Why use Phoenix Contexts on TypingMind?

Because you install it once and use it with any model. Phoenix Contexts is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Phoenix Contexts in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oliver-kriska/claude-elixir-phoenix/tree/main/plugins/elixir-phoenix/skills/phoenix-contexts. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Phoenix Contexts?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Phoenix Contexts?

As many as you like. As long as a model supports skills, you can use Phoenix Contexts with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Phoenix Contexts AI skill free?

Yes. It is published on GitHub by oliver-kriska under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇