/help

name: help
description: "Show the Digital Marketing Pro guide with live plugin state — version, agent, skill, command, and connector counts read from plugin-metadata.py, never hardcoded — plus getting-started steps, examples, and troubleshooting. Includes the --intent goal-routing mode, which turns a stated goal into up to 3 ordered skill chains ending at a quality gate, and renders depth-tier badges — [E] executes scripts, [M] measured output, [G] structured guidance — read from skills-index.json. Triggers on \"/digital-marketing-pro:help\", \"what can this plugin do\", \"which skill should I use for more leads\", \"list all the commands\", \"how do I get started\". Pairs with /digital-marketing-pro:status and /digital-marketing-pro:integrations for brand and connector state."
argument-hint: "[--commands | --skills | --examples | --connectors | --troubleshoot | --brand | --intent \"<goal>\"]"

/digital-marketing-pro:help

Show the Digital Marketing Pro user guide with **live plugin state** (version, agent/skill/command/script counts, connector counts, runtime environment) pulled from disk — not hardcoded — plus getting-started steps, usage examples, and troubleshooting.

CRITICAL: never hardcode version, counts, or connector numbers

Versions and counts in this plugin used to be baked into this skill body as literal version and count strings — a hardcoded version number, a fixed slash-command count, a fixed integrations count. Those drifted out of sync with the actual install every release and misreported the plugin to users.

**Always read live values from `scripts/plugin-metadata.py`. Never quote a version number, skill count, agent count, command count, or connector count from memory or from this skill body.**

Behavior

Step 1 — Fetch live plugin metadata

Run **first**, every time this skill is invoked (any argument or none):

python "${CLAUDE_PLUGIN_ROOT}/scripts/plugin-metadata.py" --section all-with-environment

This returns JSON with:

• `version` — `{ version, name, required_min_version, ... }`
• `assets` — `{ agents, skills_total, commands, scripts, reference_docs }`
• `connectors` — `{ available_http, available_npx, available_total, active_count, active_names, cowork_compatible_count }`
• `skills` — array of `{ skill_dir, slash_command, description }`
• `commands` — array of `{ command_file, slash_command, description }`
• `environment` — runtime detection (local Claude Code vs Cowork sandbox, with a warning if filesystem writes won't reach the user's host)

Substitute the values from this JSON into every place the help output references a count, a version, or a slash-command list. Do **not** invent or quote numbers from elsewhere.

Step 2 — Default rendering (no args)

Render a clean orientation using the live data. Suggested format (fill every `<...>` from the JSON):

=== DIGITAL MARKETING PRO ===
Version: <version.version>
Agents: <assets.agents> | Skills: <assets.skills_total> | Commands: <assets.commands> | Scripts: <assets.scripts>
Connectors: <connectors.available_http> HTTP + <connectors.available_npx> npx available
  (<connectors.active_count> currently active in your .mcp.json)
  Cowork-compatible: <connectors.cowork_compatible_count> (HTTP only — npx connectors don't run in Cowork)
Environment: <environment.environment>
<if environment.cowork_warning is non-null, show it as a WARNING block>

Getting Started:
  1. /digital-marketing-pro:brand-setup       — Create your brand profile (start here)
  2. /digital-marketing-pro:import-guidelines  — Import voice guides, restrictions, templates
  3. /digital-marketing-pro:integrations       — See which connectors are active
  4. /digital-marketing-pro:connect <name>     — Set up a new connector
  5. Just ask!                                 — Describe what you need in natural language

Step 3 — Cowork warning (when applicable)

If `environment.cowork_warning` is non-null, surface it prominently after the orientation block, explaining that brand-state writes to `~/.claude-marketing/` land inside the sandbox and won't persist to the user's host; recommend `/digital-marketing-pro:cowork-setup` to route state through a Drive MCP.

Step 4 — Argument routing

| Argument | What to render | |----------|----------------| | (none) | Steps 2 + 3 + a short "just ask" prompt | | `--commands` | Steps 2 + 3 + list every command from JSON `commands` array (its `slash_command` + `description`), grouped by category if helpful | | `--skills` | Steps 2 + 3 + list every skill from JSON `skills` array (its `slash_command` + `description`) | | `--connectors` | Steps 2 + 3 + redirect: "For active/available connector status, run `/digital-marketing-pro:integrations`" | | `--examples` | Steps 2 + 3 + the worked-example prompts (see below) | | `--troubleshoot` | Steps 2 + 3 + troubleshooting matrix (see below) | | `--brand` | Steps 2 + 3 + current brand summary (run `/digital-marketing-pro:status --section brand`) | | `--intent "<goal>"` | Intent routing (see Step 4.5) — a skill CHAIN for the goal, not a list |

When rendering the skills/commands list, **iterate over the JSON arrays** — do not paste a hand-maintained list, and do not state a total count from memory. Each row shows the `slash_command` field as the user-facing label and the `description` field as the explanation.

When rendering `--skills`, ALSO read `${CLAUDE_PLUGIN_ROOT}/skills-index.json` (generated by `scripts/build_skills_index.py`, machine-verified against the repo every release) and annotate each skill with its depth tier: **[E]** executes real scripts, **[M]** output measured through the quality machinery, **[G]** structured guidance. Show the legend once at the top. The tier is the skill's published contract — never guess it, always read it from the index.

Step 4.5 — Intent routing (`--intent "<goal>"`, or any natural-language ask about "which skill")

An alphabetical list of 150+ skills answers nothing. When the user s