Skill v1.0.1

currentAutomated scan100/100

oliver-kriska/claude-elixir-phoenix/phx-examples

+3 new

──Details

PublishedAugust 31, 2026 at 06:30 AM

Content Hashsha256:811b78dc740a0843...

Git SHA428674d35234

Bump Typepatch

Compare with v1.0.0

──Files

Files (1 file, 4.0 KB)

SKILL.md4.0 KBactive

SKILL.md · 142 lines · 4.0 KB

version: "1.0.1" name: phx-examples description: Provide Phoenix, LiveView, Ecto, OTP, or Oban examples. Use when asked for sample code, a walkthrough, a proper implementation, or expected workflow output. Pair with domain skills. NOT for debugging, direct changes, best-practice advice, or audits.

Examples & Walkthroughs

Official Phoenix Guides (Reference)

For standard implementation patterns, always check official guides first:

Topic	Guide
Contexts	hexdocs.pm/phoenix/contexts
Ecto Basics	hexdocs.pm/phoenix/ecto
LiveView	hexdocs.pm/phoenix_live_view
Authentication	mix phx.gen.auth
Channels	hexdocs.pm/phoenix/channels
Testing	hexdocs.pm/phoenix/testing
Deployment	hexdocs.pm/phoenix/deployment

Plugin-Specific Patterns

Patterns NOT in official guides (unique to this plugin):

Tidewave Integration Workflow

text

# Requires connected mcp__tidewave__* tools
 
# Get exact docs for YOUR dependency versions
mcp__tidewave__get_docs "Ecto.Query"
 
# Execute code in running app
mcp__tidewave__project_eval "MyApp.Accounts.list_users() |> length()"
 
# Query database directly
mcp__tidewave__execute_sql_query "SELECT count(*) FROM users"

Multi-Agent Review Workflow

bash

# 1. Plan feature with specialist agents
/skill:phx-plan Add user avatars with S3 upload
 
# 2. After implementation, review with multiple perspectives
/skill:phx-review lib/my_app/accounts.ex  # Elixir idioms
# Security analyzer runs automatically on auth code
 
# 3. Before deployment
# Deployment validator checks production readiness

Iron Laws Enforcement

This plugin enforces non-negotiable rules across all agents:

Elixir Idioms:

NO process without runtime reason
Messages are copied (keep small)
Changesets for external data

LiveView:

NEVER query DB in mount
ALWAYS use streams for lists
RE-AUTHORIZE in every handle_event

Oban:

Jobs MUST be idempotent
ALWAYS handle {:error, _} returns
Use unique keys for deduplication

Security:

Validate at boundaries
Never interpolate user input in queries
Authorize everywhere (not just mount)

Example Workflows

Bug Investigation

bash

# 1. Start with obvious checks
/skill:phx-investigate Login failing after password reset
 
# 2. Agent checks Ralph Wiggum list:
#    - File saved? Compiled? Migrated?
#    - Atom vs string keys?
#    - Data preloaded?
 
# 3. If complex, escalate to Ralph Wiggum Loop (if installed)
/ralph-loop:ralph-loop "Fix login tests. Output <promise>DONE</promise> when green."

Feature Planning

bash

# 1. Research phase
/skill:phx-research Oban unique jobs best practices
 
# 2. Plan with context analysis
/skill:phx-plan Add daily digest email job
 
# 3. Agents coordinate:
#    - hex-library-researcher evaluates deps
#    - oban-specialist designs worker
#    - ecto-schema-designer plans data model

Security Audit

bash

# 1. Run security analyzer on auth code
/skill:phx-review lib/my_app_web/controllers/session_controller.ex
 
# 2. Check for common vulnerabilities:
#    - SQL injection (parameterized queries?)
#    - XSS (proper escaping?)
#    - CSRF (tokens present?)
#    - Authorization (re-checked in events?)

When to Use Official Docs vs Plugin

Situation	Use
"How do I create a context?"	Official Phoenix guides
"Is my context design idiomatic?"	Plugin's `/skill:phx-review`
"How do I add LiveView?"	Official LiveView guides
"Does my LiveView have memory issues?"	Plugin's Iron Laws
"How do I deploy to Fly.io?"	Official deployment guide
"Is my release config production-ready?"	Plugin's deployment-validator

← v1.0.0 All versions