Plugin Help — Interactive Command Advisor
Helps users find the right command, skill, or agent for their situation.
Usage
/skill:phx-help # Analyze context, suggest commands
/skill:phx-help how do I debug this? # Route to /skill:phx-investigate
/skill:phx-help add a new feature # Route to /skill:phx-plan -> /skill:phx-work
Arguments
$ARGUMENTS — optional description of what the user wants to do- Empty = analyze current context (git status, existing plans, file patterns)
Execution Flow
Step 1: Gather Context
If $ARGUMENTS is non-empty, use it as primary signal.
Always gather ambient context (run in parallel):
- Check for existing plans: use Glob on
.claude/plans/*/plan.md — active work in progress?
- Check git status: uncommitted changes? which files?
- Check for solution docs: use Glob on
.claude/solutions/**/*.md — prior knowledge?
Step 2: Classify Intent
Read references/tool-catalog.md for the full routing table.
Map the user's situation to one of these categories:
| Category |
Signals |
Primary Commands |
| Starting out |
No plans, new to plugin |
/skill:phx-intro |
| Ideation |
"explore", "brainstorm", "not sure", "how to approach", "vague idea" |
/skill:phx-brainstorm |
| New feature |
"add", "build", "implement", multi-file |
/skill:phx-plan → /skill:phx-work |
| Quick change |
Single file, <50 lines, "fix typo" |
/skill:phx-quick |
| Bug |
Error, stack trace, "broken", "failing" |
/skill:phx-investigate |
| Review |
"check", "review", PR ready |
/skill:phx-review |
| Performance |
"slow", "N+1", "memory" |
/skill:phx-perf, /skill:ecto-n1-check, /skill:lv-assigns |
| Research |
"how to", "best practice", "evaluate lib" |
/skill:phx-research |
| Resume work |
Existing plan with unchecked tasks |
/skill:phx-work --continue |
| Post-fix |
"that worked", solved a hard bug |
/skill:phx-compound |
| Full cycle |
Large feature, new domain area |
/skill:phx-full |
| Project health |
"audit", "tech debt", "overall quality" |
/skill:phx-audit, /skill:phx-techdebt |
| Dep update audit |
"audit deps", "supply chain", "post-mix deps.update", "review mix.lock PR" |
/skill:phx-deps-audit |
| Manual dep vetting |
"vet this package", "approve dep", "trust ledger", "after /skill:phx-deps-audit findings" |
/skill:phx-deps-vet |
| Deployment |
"deploy", "release", "production" |
/skill:phx-verify then deploy skill |
| Permissions |
"too many prompts", "allow", "permission fatigue" |
/skill:phx-permissions |
| Returning after time off |
"what did I miss", "back from vacation", "catch up", "what changed while I was out" |
/catchup (companion plugin, separate install) |
Step 3: Respond or Clarify
If high confidence (clear match to one category):
Present the recommendation with:
- The command to run (with exact syntax)
- One-line explanation of what it does
- What artifacts it creates (if any)
- Suggested next step after it completes
If medium confidence (2-3 possible matches):
Use AskUserQuestion with the top options, each with a one-line explanation.
If low confidence (vague or no signal):
Ask ONE focused clarifying question. Examples:
- "Are you starting something new or continuing existing work?"
- "Is this a bug fix or a new feature?"
- "How many files do you expect to change?"
Then recommend based on the answer.
Step 4: Offer Follow-up
After recommending, always add:
- "Run
/skill:phx-help anytime to get routing advice"
- If they seem new: "Try
/skill:phx-intro for a full plugin walkthrough"
Iron Laws
- ONE recommendation — don't dump the full catalog, pick the best match
- MAX ONE clarifying question — don't interrogate, make your best guess
- Show exact syntax —
/skill:phx-plan Add user notifications not just "use the plan command"
- Context over keywords — existing plans + git state matter more than word matching
- NEVER block — if user already knows what they want, DO NOT redirect
Integration
- Complements
intent-detection (auto-trigger) with explicit invocation
- References same routing logic but adds interactive clarification
- Can recommend
/skill:phx-intro for onboarding
1---2name: phx-help3description: Choose Phoenix review, plan, debug, or test command. Use when user asks4 which /skill:phx-* command or plugin skill handles a task; do not route only to5 a domain skill. NEVER for bare /help; NOT for ambiguous requests (use intent-detection)6 or a plugin tour.7---89# Plugin Help — Interactive Command Advisor1011Helps users find the right command, skill, or agent for their situation.1213## Usage1415```16/skill:phx-help # Analyze context, suggest commands17/skill:phx-help how do I debug this? # Route to /skill:phx-investigate18/skill:phx-help add a new feature # Route to /skill:phx-plan -> /skill:phx-work19```2021## Arguments2223- `$ARGUMENTS` — optional description of what the user wants to do24- Empty = analyze current context (git status, existing plans, file patterns)2526## Execution Flow2728### Step 1: Gather Context2930If `$ARGUMENTS` is non-empty, use it as primary signal.3132Always gather ambient context (run in parallel):33341. Check for existing plans: use Glob on `.claude/plans/*/plan.md` — active work in progress?352. Check git status: uncommitted changes? which files?363. Check for solution docs: use Glob on `.claude/solutions/**/*.md` — prior knowledge?3738### Step 2: Classify Intent3940Read `references/tool-catalog.md` for the full routing table.4142Map the user's situation to one of these categories:4344| Category | Signals | Primary Commands |45|----------|---------|-----------------|46| **Starting out** | No plans, new to plugin | `/skill:phx-intro` |47| **Ideation** | "explore", "brainstorm", "not sure", "how to approach", "vague idea" | `/skill:phx-brainstorm` |48| **New feature** | "add", "build", "implement", multi-file | `/skill:phx-plan` → `/skill:phx-work` |49| **Quick change** | Single file, <50 lines, "fix typo" | `/skill:phx-quick` |50| **Bug** | Error, stack trace, "broken", "failing" | `/skill:phx-investigate` |51| **Review** | "check", "review", PR ready | `/skill:phx-review` |52| **Performance** | "slow", "N+1", "memory" | `/skill:phx-perf`, `/skill:ecto-n1-check`, `/skill:lv-assigns` |53| **Research** | "how to", "best practice", "evaluate lib" | `/skill:phx-research` |54| **Resume work** | Existing plan with unchecked tasks | `/skill:phx-work --continue` |55| **Post-fix** | "that worked", solved a hard bug | `/skill:phx-compound` |56| **Full cycle** | Large feature, new domain area | `/skill:phx-full` |57| **Project health** | "audit", "tech debt", "overall quality" | `/skill:phx-audit`, `/skill:phx-techdebt` |58| **Dep update audit** | "audit deps", "supply chain", "post-`mix deps.update`", "review mix.lock PR" | `/skill:phx-deps-audit` |59| **Manual dep vetting** | "vet this package", "approve dep", "trust ledger", "after /skill:phx-deps-audit findings" | `/skill:phx-deps-vet` |60| **Deployment** | "deploy", "release", "production" | `/skill:phx-verify` then deploy skill |61| **Permissions** | "too many prompts", "allow", "permission fatigue" | `/skill:phx-permissions` |62| **Returning after time off** | "what did I miss", "back from vacation", "catch up", "what changed while I was out" | `/catchup` (companion plugin, separate install) |6364### Step 3: Respond or Clarify6566**If high confidence** (clear match to one category):67Present the recommendation with:6869- The command to run (with exact syntax)70- One-line explanation of what it does71- What artifacts it creates (if any)72- Suggested next step after it completes7374**If medium confidence** (2-3 possible matches):75Use `AskUserQuestion` with the top options, each with a one-line explanation.7677**If low confidence** (vague or no signal):78Ask ONE focused clarifying question. Examples:7980- "Are you starting something new or continuing existing work?"81- "Is this a bug fix or a new feature?"82- "How many files do you expect to change?"8384Then recommend based on the answer.8586### Step 4: Offer Follow-up8788After recommending, always add:8990- "Run `/skill:phx-help` anytime to get routing advice"91- If they seem new: "Try `/skill:phx-intro` for a full plugin walkthrough"9293## Iron Laws94951. **ONE recommendation** — don't dump the full catalog, pick the best match962. **MAX ONE clarifying question** — don't interrogate, make your best guess973. **Show exact syntax** — `/skill:phx-plan Add user notifications` not just "use the plan command"984. **Context over keywords** — existing plans + git state matter more than word matching995. **NEVER block** — if user already knows what they want, DO NOT redirect100101## Integration102103- Complements `intent-detection` (auto-trigger) with explicit invocation104- References same routing logic but adds interactive clarification105- Can recommend `/skill:phx-intro` for onboarding
oliver-kriska