phx:full

Full Phoenix Feature Development

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "phx:full" with this command: npx skills add oliver-kriska/claude-elixir-phoenix/oliver-kriska-claude-elixir-phoenix-phx-full

Full Phoenix Feature Development

Execute complete Elixir/Phoenix feature development autonomously: research patterns, plan with specialist agents, implement with verification, Elixir code review. Cycles back automatically if review finds issues.

Usage

/phx:full Add user authentication with magic links /phx:full Real-time notification system with Phoenix PubSub /phx:full Background job processing for email campaigns --max-cycles 5

Workflow Overview

┌──────────────────────────────────────────────────────────────────┐ │ /phx:full {feature} │ ├──────────────────────────────────────────────────────────────────┤ │ │ │ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ │ │ │Discover│→ │ Plan │→ │ Work │→ │ Verify │→ │ Review │→ │Compound│→Done│ │ │ Assess │ │[Pn-Tm] │ │Execute │ │ Full │ │4 Agents│ │Capture │ │ │ │ Decide │ │ Phases │ │ Tasks │ │ Loop │ │Parallel│ │ Solve │ │ │ └───┬────┘ └────────┘ └────────┘ └───┬────┘ └────────┘ └────────┘ │ │ │ ↑ │ ↑ │ │ │ ├── "just do it" ────────────┤ │ │ │ │ │ ├── "plan it" ──┐ │ ↓ │ │ │ │ │ ↓ │ ┌────────┐│ │ │ │ │ ┌──────────────┐ │ │Fix ││ ┌─────────┐ │ │ │ │ │ PLANNING │ │ │Issues │└─│ Fix │←┘ │ │ │ └──────────────┘ │ └───┬────┘ │ Review │ │ │ │ │ ↓ │ Findings│ │ │ │ ┌────┴─────────┐ └────┬────┘ │ │ │ │ VERIFYING │←──────┘ │ │ └── "research it" ─────┘ (re-verify) │ │ (comprehensive plan) │ │ │ │ On Completion: │ │ Auto-compound: Capture solved problems → .claude/solutions/ │ │ Auto-suggest: /phx:document → /phx:learn │ │ │ └──────────────────────────────────────────────────────────────────┘

State Machine

STATES: INITIALIZING → DISCOVERING → PLANNING → WORKING → VERIFYING → REVIEWING → COMPLETED → COMPOUNDING | BLOCKED

Track state in .claude/plans/{slug}/progress.md AND via Claude Code tasks. Create one task per phase at start, mark in_progress on entry and completed on exit:

TaskCreate({subject: "Discover & assess complexity", activeForm: "Discovering..."}) TaskCreate({subject: "Plan feature", activeForm: "Planning..."}) TaskCreate({subject: "Implement tasks", activeForm: "Working..."}) TaskCreate({subject: "Verify implementation", activeForm: "Verifying..."}) TaskCreate({subject: "Review with specialists", activeForm: "Reviewing..."}) TaskCreate({subject: "Capture solutions", activeForm: "Compounding..."})

Set up blockedBy dependencies between phases (sequential).

On COMPLETED: auto-run COMPOUNDING phase to capture solved problems as searchable solution docs in .claude/solutions/ . Then suggest /phx:document for docs and /phx:learn for quick pattern capture.

Cycle Limits

Setting Default Description

--max-cycles

10 Max plan→review cycles

--max-retries

3 Max retries per task

--max-blockers

5 Max blockers before stopping

When limits exceeded, output INCOMPLETE status with remaining work and recommended action.

Integration

/phx:full = /phx:plan → /phx:work → /phx:verify → /phx:review → (fix → /phx:verify) → /phx:compound

For fully autonomous execution with Ralph Wiggum Loop:

/ralph-loop:ralph-loop "/phx:full {feature}" --completion-promise "DONE" --max-iterations 50

Iron Laws

  • NEVER skip verification — Every task must pass mix compile --warnings-as-errors
  • mix test before moving to the next. Skipping compounds errors across tasks
  • Respect cycle limits — When --max-cycles is exhausted, STOP with INCOMPLETE status. Do not continue indefinitely hoping the next fix works

  • One state transition at a time — Follow the state machine strictly. Never jump from PLANNING to REVIEWING — each state produces artifacts the next state needs

  • Discover before deciding — Always run DISCOVERING phase to assess complexity. Skipping it for "simple" features leads to underplanned implementations

  • Agent output is findings, not fixes — Review agents report issues. Only the WORKING state makes code changes

References

  • references/execution-steps.md — Detailed step-by-step execution

  • references/example-run.md — Example full cycle run

  • references/safety-recovery.md — Safety rails, resume, rollback

  • references/cycle-patterns.md — Advanced cycling strategies

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

oban

No summary provided by upstream source.

Repository SourceNeeds Review
General

ecto-patterns

No summary provided by upstream source.

Repository SourceNeeds Review
General

tidewave-integration

No summary provided by upstream source.

Repository SourceNeeds Review
General

phx:boundaries

No summary provided by upstream source.

Repository SourceNeeds Review