Intent Detection Skill for Claude

Intent Detection — Workflow Routing

When user describes work WITHOUT specifying a $elixir-phoenix:phx-* command, analyze their intent and suggest the appropriate workflow BEFORE starting work.

Hard guard — check FIRST: if the message starts with any slash command

($elixir-phoenix:phx-*, $elixir-phoenix:ecto-*, $elixir-phoenix:lv-*, or any other /command), this skill does not apply.

Follow the invoked command directly — no routing analysis, no suggestion, zero

output from this skill.

Routing Table

| Signal | Detected Intent | Suggest |

|--------|----------------|---------|

| "bug", "error", "crash", "failing", "broken", stack trace | Bug investigation | $elixir-phoenix:phx-investigate |

| "brainstorm", "explore idea", "not sure what I need", "vague idea", "let's discuss", "how to approach" | Ideation/requirements | $elixir-phoenix:phx-brainstorm |

| "add", "implement", "build", "create" + multi-step | New feature | $elixir-phoenix:phx-plan |

| "review", "check", "audit" code | Code review | $elixir-phoenix:phx-review |

| "fix" + small/specific scope | Quick fix | handle directly or $elixir-phoenix:phx-quick |

| "refactor", "clean up", "improve" | Refactoring | $elixir-phoenix:phx-plan (needs scope) |

| "research", "how to", "what's the best" | Research | $elixir-phoenix:phx-research |

| "evaluate", "compare", "adopt", "library", "should we use" | Library evaluation | $elixir-phoenix:phx-research --library |

| "test", "spec", "coverage" | Testing | handle directly or $elixir-phoenix:phx-plan |

| Describes 1-2 file changes, < 50 lines | Small task | handle directly |

| "deploy", "release", "production" | Deployment | $elixir-phoenix:phx-verify then deploy |

| "performance", "slow", "N+1", "memory" | Performance | $elixir-phoenix:phx-perf |

| "PR review", "review comments", "address feedback", "respond to PR" | PR response | $elixir-phoenix:phx-pr-review |

| "that worked", "fixed it", "problem solved" | Knowledge capture | $elixir-phoenix:phx-compound |

| "enhance plan", "more detail", "deepen" | Plan enhancement | $elixir-phoenix:phx-plan --existing |

| "triage", "which findings", "prioritize fixes" | Finding triage | $elixir-phoenix:phx-triage |

Behavior

• Read user's first message
• Match against routing table (use keyword + context signals, not exact match)
• If match found with multi-step workflow: "This looks like [intent]. I'd suggest [command] — want me to run it, or should I just dive in?"
• If trivial task (typo, single-line fix, config change): skip suggestion, just do it
• If user already specified a $elixir-phoenix:phx-* command: follow it, don't re-suggest
• NEVER block the user — suggestion only, not mandatory

Confidence Signals

High confidence (suggest immediately):

• Stack trace or error message pasted → $elixir-phoenix:phx-investigate
• "Add [feature] with [multiple components]" → $elixir-phoenix:phx-plan
• "Review my changes" or "check this PR" → $elixir-phoenix:phx-review

Medium confidence (suggest with caveat):

• "Fix [thing]" — could be quick or complex, suggest based on scope description
• "Update [thing]" — could be small edit or refactor

Low confidence (just do it):

• Single file mentioned, clear change
• "Change X to Y"
• Configuration or dependency updates

Complexity Signals

When a task matches a workflow command, check complexity before suggesting:

Trivial signals (suggest $elixir-phoenix:phx-quick or handle directly):

• Single file mentioned explicitly
• "exclude X from Y", "add X to config", "rename", "change X to Y"
• Problem + solution both stated ("X is wrong, change to Y")
• One-line fix described

Complex signals (suggest $elixir-phoenix:phx-plan or $elixir-phoenix:phx-investigate):

• 3+ modules or files mentioned
• "intermittent", "race condition", "sometimes", "random"
• Stack trace with 5+ frames
• "across", "all", "every" (scope indicators)

Override rule: If user invokes $elixir-phoenix:phx-full but task matches trivial signals:

"This looks like a quick fix. Want $elixir-phoenix:phx-quick instead, or stick with the full cycle?"

Iron Laws

• NEVER block on suggestion — If user starts explaining, just do the work
• One suggestion max — Don't re-suggest if user ignores first suggestion
• Commands are shortcuts, not gates — All work can be done without commands

Routing Logic Example

if has_slash_command($ARGUMENTS) -> follow command directly
elif has_stack_trace(message) -> suggest $elixir-phoenix:phx-investigate
elif matches("add|build|implement", message) and multi_step -> suggest $elixir-phoenix:phx-plan
elif matches("fix", message) and small_scope -> handle directly or $elixir-phoenix:phx-quick
elif matches("review|audit", message) -> suggest $elixir-phoenix:phx-review
else -> handle directly (no suggestion)

Integration

This skill is consulted at session start. It works alongside:

• SessionStart hook (shows plugin loaded message)
• CLAUDE.md routing instructions (passive reference)
• Individual workflow skills (activated by commands)