Intent Detection — Workflow Routing
When user describes work WITHOUT specifying a 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
(phx-*, ecto-*, 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 |
phx-investigate |
| "brainstorm", "explore idea", "not sure what I need", "vague idea", "let's discuss", "how to approach" |
Ideation/requirements |
phx-brainstorm |
| "add", "implement", "build", "create" + multi-step |
New feature |
phx-plan |
| "review", "check", "audit" code |
Code review |
phx-review |
| "fix" + small/specific scope |
Quick fix |
handle directly or phx-quick |
| "refactor", "clean up", "improve" |
Refactoring |
phx-plan (needs scope) |
| "research", "how to", "what's the best" |
Research |
phx-research |
| "evaluate", "compare", "adopt", "library", "should we use" |
Library evaluation |
phx-research --library |
| "test", "spec", "coverage" |
Testing |
handle directly or phx-plan |
| Describes 1-2 file changes, < 50 lines |
Small task |
handle directly |
| "deploy", "release", "production" |
Deployment |
phx-verify then deploy |
| "performance", "slow", "N+1", "memory" |
Performance |
phx-perf |
| "PR review", "review comments", "address feedback", "respond to PR" |
PR response |
phx-pr-review |
| "that worked", "fixed it", "problem solved" |
Knowledge capture |
phx-compound |
| "enhance plan", "more detail", "deepen" |
Plan enhancement |
phx-plan --existing |
| "triage", "which findings", "prioritize fixes" |
Finding triage |
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
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 →
phx-investigate
- "Add [feature] with [multiple components]" →
phx-plan
- "Review my changes" or "check this PR" →
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 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 phx-plan or 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 phx-full but task matches trivial signals:
"This looks like a quick fix. Want 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 phx-investigate
elif matches("add|build|implement", message) and multi_step -> suggest phx-plan
elif matches("fix", message) and small_scope -> handle directly or phx-quick
elif matches("review|audit", message) -> suggest 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)
1---2name: intent-detection-43description: Route ambiguous or mixed Phoenix/LiveView/Ecto requests before choosing4 a workflow. Use when user is unsure where to start/how to approach work, asks for5 the right workflow, or combines intents such as fixing and refactoring. NOT for6 a clear task.7metadata:8 source: https://skillmd.com/skills/oliver-kriska/intent-detection-49---1011# Intent Detection — Workflow Routing1213When user describes work WITHOUT specifying a `phx-*` command, analyze their intent and suggest the appropriate workflow BEFORE starting work.1415**Hard guard — check FIRST**: if the message starts with any slash command16(`phx-*`, `ecto-*`, `lv-*`, or any other `/command`), this skill does not apply.17Follow the invoked command directly — no routing analysis, no suggestion, zero18output from this skill.1920## Routing Table2122| Signal | Detected Intent | Suggest |23|--------|----------------|---------|24| "bug", "error", "crash", "failing", "broken", stack trace | Bug investigation | `phx-investigate` |25| "brainstorm", "explore idea", "not sure what I need", "vague idea", "let's discuss", "how to approach" | Ideation/requirements | `phx-brainstorm` |26| "add", "implement", "build", "create" + multi-step | New feature | `phx-plan` |27| "review", "check", "audit" code | Code review | `phx-review` |28| "fix" + small/specific scope | Quick fix | handle directly or `phx-quick` |29| "refactor", "clean up", "improve" | Refactoring | `phx-plan` (needs scope) |30| "research", "how to", "what's the best" | Research | `phx-research` |31| "evaluate", "compare", "adopt", "library", "should we use" | Library evaluation | `phx-research --library` |32| "test", "spec", "coverage" | Testing | handle directly or `phx-plan` |33| Describes 1-2 file changes, < 50 lines | Small task | handle directly |34| "deploy", "release", "production" | Deployment | `phx-verify` then deploy |35| "performance", "slow", "N+1", "memory" | Performance | `phx-perf` |36| "PR review", "review comments", "address feedback", "respond to PR" | PR response | `phx-pr-review` |37| "that worked", "fixed it", "problem solved" | Knowledge capture | `phx-compound` |38| "enhance plan", "more detail", "deepen" | Plan enhancement | `phx-plan --existing` |39| "triage", "which findings", "prioritize fixes" | Finding triage | `phx-triage` |4041## Behavior42431. Read user's first message442. Match against routing table (use keyword + context signals, not exact match)453. 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?"464. If trivial task (typo, single-line fix, config change): skip suggestion, just do it475. If user already specified a `phx-*` command: follow it, don't re-suggest486. **NEVER block the user** — suggestion only, not mandatory4950## Confidence Signals5152High confidence (suggest immediately):5354- Stack trace or error message pasted → `phx-investigate`55- "Add [feature] with [multiple components]" → `phx-plan`56- "Review my changes" or "check this PR" → `phx-review`5758Medium confidence (suggest with caveat):5960- "Fix [thing]" — could be quick or complex, suggest based on scope description61- "Update [thing]" — could be small edit or refactor6263Low confidence (just do it):6465- Single file mentioned, clear change66- "Change X to Y"67- Configuration or dependency updates6869## Complexity Signals7071When a task matches a workflow command, check complexity before suggesting:7273**Trivial signals** (suggest `phx-quick` or handle directly):7475- Single file mentioned explicitly76- "exclude X from Y", "add X to config", "rename", "change X to Y"77- Problem + solution both stated ("X is wrong, change to Y")78- One-line fix described7980**Complex signals** (suggest `phx-plan` or `phx-investigate`):8182- 3+ modules or files mentioned83- "intermittent", "race condition", "sometimes", "random"84- Stack trace with 5+ frames85- "across", "all", "every" (scope indicators)8687**Override rule**: If user invokes `phx-full` but task matches trivial signals:88"This looks like a quick fix. Want `phx-quick` instead, or stick with the full cycle?"8990## Iron Laws91921. **NEVER block on suggestion** — If user starts explaining, just do the work932. **One suggestion max** — Don't re-suggest if user ignores first suggestion943. **Commands are shortcuts, not gates** — All work can be done without commands9596## Routing Logic Example9798```99if has_slash_command($ARGUMENTS) -> follow command directly100elif has_stack_trace(message) -> suggest phx-investigate101elif matches("add|build|implement", message) and multi_step -> suggest phx-plan102elif matches("fix", message) and small_scope -> handle directly or phx-quick103elif matches("review|audit", message) -> suggest phx-review104else -> handle directly (no suggestion)105```106107## Integration108109This skill is consulted at session start. It works alongside:110111- SessionStart hook (shows plugin loaded message)112- CLAUDE.md routing instructions (passive reference)113- Individual workflow skills (activated by commands)