Menu
Route ambiguous Phoenix requests to the right workflow.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Recommend the right `$elixir-phoenix-*` skill for the current task.
Elixir/Phoenix: Review lifecycle, state-machine, Oban, persistence, pause/resume, retry, and restart-sensitive changes before commit, push, or PR. Use for concurrency-sensitive runtime work to produce explicit blocking vs optional findings, require durability checks, and verify smoke plus restart resilience when applicable.
Capture a solved Phoenix problem as a reusable solution doc.
Audit LiveView assigns for memory bloat, dead assigns, and stream candidates.
Audit project health across architecture, security, performance, tests, and deps.
Analyze Phoenix context boundaries and coupling with `mix xref`.
| name | elixir-phoenix-intent-detection |
| description | Route ambiguous Phoenix requests to the right workflow. |
| metadata | {"short-description":"Route ambiguous Phoenix requests"} |
When user describes work WITHOUT specifying a $elixir-phoenix-* skill, analyze their intent and suggest the appropriate workflow BEFORE starting work.
| Signal | Detected Intent | Suggest |
|---|---|---|
| "bug", "error", "crash", "failing", "broken", stack trace | Bug investigation | $elixir-phoenix-investigate |
| "brainstorm", "explore idea", "not sure what I need", "vague idea", "let's discuss", "how to approach" | Ideation/requirements | $elixir-phoenix-brainstorm |
| "add", "implement", "build", "create" + multi-step | New feature | $elixir-phoenix-plan |
| "review", "check", "audit" code | Code review | $elixir-phoenix-review |
| "fix" + small/specific scope | Quick fix | handle directly or $elixir-phoenix-quick |
| "refactor", "clean up", "improve" | Refactoring | $elixir-phoenix-plan (needs scope) |
| "research", "how to", "what's the best" | Research | $elixir-phoenix-research |
| "evaluate", "compare", "adopt", "library", "should we use" | Library evaluation | ``$elixir-phoenix-research --library |
| "test", "spec", "coverage" | Testing | handle directly or $elixir-phoenix-plan |
| Describes 1-2 file changes, < 50 lines | Small task | handle directly |
| "deploy", "release", "production" | Deployment | $elixir-phoenix-verify then deploy |
| "performance", "slow", "N+1", "memory" | Performance | $elixir-phoenix-perf |
| "PR review", "review comments", "address feedback", "respond to PR" | PR response | $elixir-phoenix-pr-review |
| "that worked", "fixed it", "problem solved" | Knowledge capture | $elixir-phoenix-compound |
| "enhance plan", "more detail", "deepen" | Plan enhancement | ``$elixir-phoenix-plan --existing |
| "triage", "which findings", "prioritize fixes" | Finding triage | $elixir-phoenix-triage |
[command] — want me to run it, or should I just dive in?"$elixir-phoenix-* skill: follow it, don't re-suggestHigh confidence (suggest immediately):
$elixir-phoenix-investigate$elixir-phoenix-plan$elixir-phoenix-reviewMedium confidence (suggest with caveat):
Low confidence (just do it):
When a task matches a workflow command, check complexity before suggesting:
Trivial signals (suggest $elixir-phoenix-quick or handle directly):
Complex signals (suggest $elixir-phoenix-plan or $elixir-phoenix-investigate):
Override rule: If user invokes $elixir-phoenix-full but task matches trivial signals:
"This looks like a quick fix. Want $elixir-phoenix-quick instead, or stick with the full cycle?"
if has_slash_command($ARGUMENTS) -> follow command directly
elif has_stack_trace(message) -> suggest `$elixir-phoenix-investigate`
elif matches("add|build|implement", message) and multi_step -> suggest `$elixir-phoenix-plan`
elif matches("fix", message) and small_scope -> handle directly or `$elixir-phoenix-quick`
elif matches("review|audit", message) -> suggest `$elixir-phoenix-review`
else -> handle directly (no suggestion)
This skill is consulted at session start. It works alongside: