SkillAgentSearch skills...

ash-framework

Ash Framework — resources, actions, policies, aggregates, calculations, AshPhoenix.Form, LiveView, migrations

Install / Use

npx skills add oliver-kriska/claude-elixir-phoenix --skill ash-framework

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

84/100

Category

Security

Supported Platforms

Universal

Our assessment of ash-framework

ash-framework scores 84/100 on our quality scale, 829th of 1,097 Security skills we index.

Its SKILL.md is 5.3 KB long, well organised into 14 sections with 4 code examples: a solid amount of guidance for an agent.

It has 574 GitHub stars, a meaningful sign that others use it.

Substance
26/30
Structure
20/20
Description
12/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 13 days ago, so ash-framework is actively maintained.
  • Our last check on 2026-11-05 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

ash-framework compared with similar skills

All 4 of these similar skills score higher than ash-framework; compare them before choosing.

SkillScoreStarsUpdatedFormat
ash-framework (this skill)by oliver-kriska8457413d agoSKILL.md
algorithmic-artby anthropics100177.9k58d agoSKILL.md
pptxby anthropics100177.9k58d agoSKILL.md
prospectingby coreyhaines3110060.1k8d agoSKILL.md
ad-creativeby coreyhaines3110060.1k8d agoSKILL.md

Frequently asked questions

How do I install ash-framework?
Run npx skills add oliver-kriska/claude-elixir-phoenix --skill ash-framework. The install tabs above show the steps for each supported agent.
Which AI agents does ash-framework work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is ash-framework safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is ash-framework still maintained?
The repository was last updated 13 days ago, so ash-framework is actively maintained.

name: ash-framework description: "Ash Framework — resources, actions, policies, aggregates, calculations, AshPhoenix.Form, LiveView, migrations. Use when generating resources via mix ash.codegen, editing changes, checks, types, validations, or domain code interfaces." effort: medium user-invocable: false

Ash Framework Reference

Reference for Ash Framework in Phoenix/LiveView projects. Ash complements Phoenix/Ecto — LiveView, security, and OTP Iron Laws still apply. Only data access patterns shift toward Ash actions and domain code interfaces.

Iron Laws

  1. USE DOMAIN CODE INTERFACES — Never call Ash.create/Ash.read directly in LiveViews or Controllers; use domain code interfaces: MyApp.Accounts.register_user() not Ash.create(User, attrs)
  2. SET ACTOR/SCOPE AT QUERY PREP, NOT EXECUTION — Give actor: or scope: to for_read/for_create/for_action (prep), NOT to Ash.read!/Ash.create! (execution); execution-level actor bypasses row-level policy evaluation. If project uses Ash.Scope, use scope: consistently instead of bare actor: — do not mix styles
  3. GENERATORS FIRST — Before writing Ash code manually, run mix ash.gen.resource or mix ash.gen.domain with --yes; check mix help ash.gen.<task> for options
  4. CODEGEN AFTER RESOURCE CHANGES — Always run mix ash.codegen after modifying resources; this generates migrations from resource snapshots — never write AshPostgres migrations by hand
  5. ACTIONS OVER FUNCTIONS — Put business logic in named actions, not domain functions; expose via code interfaces defined on the domain
  6. NEVER EDIT RESOURCE SNAPSHOTS — priv/resource_snapshots/ is owned exclusively by mix ash.codegen; manual edits corrupt migration tracking
  7. NO DIRECT Repo.* IN ASH PROJECTS — Repo.all/get/insert bypass Ash policies and notifications; use domain code interfaces. Any Repo call in an Ash project is an escape hatch and must be documented

Quick Reference

Domain Code Interface Pattern

# Domain definition
defmodule MyApp.Accounts do
  use Ash.Domain

  resources do
    resource MyApp.Accounts.User do
      define :register_user, action: :create, args: [:email, :name]
      define :get_user_by_email, action: :read, get_by: [:email]
    end
  end
end

# In LiveView/Controller — always via domain, never Ash.create directly
{:ok, user} = MyApp.Accounts.register_user(email, name, actor: nil)
user = MyApp.Accounts.get_user_by_email!(email, actor: current_user)

Authorization — Actor/Scope at Query Prep

# CORRECT — actor at query prep, policies evaluated per-row
MyApp.Post
|> Ash.Query.for_read(:list_published, %{}, actor: current_user)
|> Ash.read!()

# CORRECT with Ash.Scope (carries actor + tenant + context; use if project adopts it)
MyApp.Post
|> Ash.Query.for_read(:list_published, %{}, scope: scope)
|> Ash.read!()

# WRONG — actor at execution bypasses row-level policy evaluation
MyApp.Post
|> Ash.Query.for_read(:list_published)
|> Ash.read!(actor: current_user)

Ash.Scope — When the Project Uses It

Ash.Scope bundles actor + tenant + context into a single struct carried through actions. Implement Ash.Scope.ToOpts on a project-defined scope struct:

defimpl Ash.Scope.ToOpts, for: MyApp.Scope do
  def get_actor(%{current_user: u}), do: {:ok, u}
  def get_tenant(%{current_tenant: t}), do: {:ok, t}
  def get_context(%{locale: l}), do: {:ok, %{shared: %{locale: l}}}
  def get_tracer(_), do: :error
  def get_authorize?(_), do: :error
end

Detection: if the project has a Scope module implementing Ash.Scope.ToOpts, use scope: everywhere instead of bare actor:. Do NOT mix the two styles in the same codebase. See mix usage_rules.docs Ash.Scope for full protocol spec.

File Conventions (from mix ash.gen.*)

| File | Location | Behaviour | | -------------- | --------------------------------- | ----------------------------- | | Changes | lib/app/ctx/changes/name.ex | use Ash.Resource.Change | | Policy Checks | lib/app/ctx/checks/name.ex | use Ash.Policy.Check | | Custom Actions | lib/app/ctx/actions/name.ex | generic action logic | | Custom Types | lib/app/ctx/types/name.ex | use Ash.Type | | Validations | lib/app/ctx/validations/name.ex | use Ash.Resource.Validation |

Generator Workflow

mix ash.gen.resource MyApp.Accounts.User --yes
mix ash.gen.domain MyApp.Accounts --yes
mix ash.codegen        # reads resource snapshots → generates migration
mix ash.migrate

Research

Prefer the highest-fidelity source available:

  1. Tidewave (exact version from mix.lock):

    mcp__tidewave__get_docs(module: "Ash.Resource")
    mcp__tidewave__get_docs(module: "AshPhoenix.Form")
    
  2. usage_rules (project-synced to your installed ash_* dep versions):

    mix usage_rules.search_docs "<topic>" -p ash -p ash_phoenix -p ash_postgres -p ash_authentication -p ash_oban
    mix usage_rules.docs Ash.Resource
    
  3. WebFetch hexdocs.pm (fallback when neither is available):

    WebFetch(url: "https://hexdocs.pm/ash/Ash.Resource.html", prompt: "Extract module docs.")
    

If usage_rules is not configured, the SessionStart hook suggests how to install it.

Related Skills

View on GitHub
GitHub Stars574
CategorySecurity
Updated13d ago
Forks45

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions