Skip to content
Skills Library
Programming · Learning & explanation

help

/help

Use when the user asks which /phx: command fits a task (review, plan, debug, test) or how two commands differ. Checks plans and git state, then recommends from the routing table. Not for bare /help, a tour, or ambiguous requests (intent-detection).

Licence
MIT
Last repository change
22.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 22.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when the user asks which /phx: command fits a task (review, plan, debug, test) or how two commands differ. Checks plans and git state, then recommends from the routing table. Not for bare /help, a tour, or ambiguous requests (intent-detection).

Arguments

/help [description of what you want to do]
Original author description

Use when the user asks which /phx: command fits a task (review, plan, debug, test) or how two commands differ. Checks plans and git state, then recommends from the routing table. Not for bare /help, a tour, or ambiguous requests (intent-detection).

How it works

  1. Usage
  2. Arguments
  3. Execution Flow
  4. Iron Laws
  5. Integration
Original SKILL.md headings · 99 lines, 635 words
SKILL.md preview
---
name: help
description: "Use when the user asks which /phx: command fits a task (review, plan, debug, test) or how two commands differ. Checks plans and git state, then recommends from the routing table. Not for bare /help, a tour, or ambiguous requests (intent-detection)."
argument-hint: "[description of what you want to do]"
effort: low
---

# Plugin Help — Interactive Command Advisor

Helps users find the right command, skill, or agent for their situation.

## Usage

```
/phx:help                          # Analyze context, suggest commands
/phx:help how do I debug this?     # Route to /phx:investigate
/phx:help add a new feature        # Route to /phx:plan -> /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):

1. Check for existing plans: use Glob on `.claude/plans/*/plan.md` — active work in progress?
2. Check git status: uncommitted changes? which files?
3. Check for solution docs: use Glob on `.claude/solutions/**/*.md` — prior knowledge?

### Step 2: Classify Intent

Read `${CLAUDE_SKILL_DIR}/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 | `/phx:intro` |
| **Ideation** | "explore", "brainstorm", "not sure", "how to approach", "vague idea" | `/phx:brainstorm` |
| **New feature** | "add", "build", "implement", multi-file | `/phx:plan` → `/phx:work` |
| **Quick change** | Single file, <50 lines, "fix typo" | `/phx:quick` |
| **Bug** | Error, stack trace, "broken", "failing" | `/phx:investigate` |
| **Review** | "check", "review", PR ready | `/phx:review` |
| **Performance** | "slow", "N+1", "memory" | `/phx:perf`, `/ecto:n1-check`, `/lv:assigns` |
| **Research** | "how to", "best practice", "evaluate lib" | `/phx:research` |
| **Resume work** | Existing plan with unchecked tasks | `/phx:work --continue` |
| **Post-fix** | "that worked", solved a hard bug | `/phx:compound` |
| **Full cycle** | Large feature, new domain area | `/phx:full` |
| **Project health** | "audit", "tech debt", "overall quality" | `/phx:audit`, `/phx:techdebt` |
| **Dep update audit** | "audit deps", "supply chain", "post-`mix deps.update`", "review mix.lock PR" | `/phx:deps-audit` |
| **Manual dep vetting** | "vet this package", "approve dep", "trust ledger", "after /phx:deps-audit findings" | `/phx:deps-vet` |
| **Deployment** | "deploy", "release", "production" | `/phx:verify` then deploy skill |
| **Permissions** | "too many prompts", "allow", "permission fatigue" | `/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 `/phx:help` anytime to get routing advice"
- If they seem new: "Try `/phx:intro` for a full plugin walkthrough"

## Iron Laws

1. **ONE recommendation** — don't dump the full catalog, pick the best match
2. **MAX ONE clarifying question** — don't interrogate, make your best guess
3. **Show exact syntax** — `/phx:plan Add user notifications` not just "use the plan command"
4. **Context over keywords** — existing plans + git state matter more than word matching
5. **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 `/phx:intro` for onboarding
Files in this package (2)
  • SKILL.md 4 KB
  • references/tool-catalog.md 9 KB

Versions

RepositoryScoreLicence
This page · oliver-kriska/claude-elixir-phoenix100MIT
Ovich/charrette100MIT
davepoon/buildwithclaude100MIT
crisandrews/clawcode100MIT
lamngockhuong/aiteamkit100MIT
The01Geek/prflow100MIT
Cruna-Noise-To-Signal/cruna-plugins100Apache-2.0
wookiya1364/scv-claude-code100MIT
jeffersonvalente/cardume100MIT

Database snapshot: 13.11.2026 · package version 000ded5291b9 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100phx-help
    Use when the user asks which /skill:phx-* command fits a task (review, plan, debug, test) or how two commands differ. Checks plans and git state, then recommends from the routing table. Not for bare /help, a tour, or ambiguous requests (intent-detection).
  • 100phx-help
    Use when the user asks which /phx-* command fits a task (review, plan, debug, test) or how two commands differ. Checks plans and git state, then recommends from the routing table. Not for bare /help, a tour, or ambiguous requests (intent-detection).
  • 100detect-task
    Internal skill for commands. Detect the active task (any tracker adapter) from the task-state file / git branch name. Do not trigger on user conversation - only when commands need task detection.
  • 90using-rune
    Use when the user asks to review code, plan features, brainstorm ideas, audit a codebase, implement a plan, fix review findings, debug failed builds, analyze code impact, or run end-to-end workflows. Also use when the user seems unsure which Rune command to use, when the user…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.