---

Generated from tasks/brand-iq-setup/task.yaml by /task-authoring.

Do not edit here — edit the definition and regenerate.

name: task-brand-iq-setup description: >- Multi-step TASK — Brand IQ auto-analysis and setup. Enter when: the merchant asks for an analysis of their store or shop in general terms ("analysis my shop", "analyze my store"), or to auto-set-up Brand IQ (brand voice, target audiences, style guide) — a general store analysis IS this Brand IQ analysis, not a free-form audit you write yourself; the merchant clicks "Analyze My Store & Auto-Setup"; the merchant asks to re-scan or re-analyze the store. Do NOT enter: they only ask what their current brand voice or audiences are — just read and answer; they ask to update or edit their brand voice, audiences or style guide — those values are changed in the Setting Hub's Brand IQ section (settings boundary), and this task is only for re-scanning the store when they actually ask for a scan; they want an actual article or post written (that is task-content-publish); they want a content plan or schedule covering a period (that is task-calendar-plan); they want to change a setting, connect or disconnect a channel, or edit their account — that is not Brand IQ, and they do it themselves in the Setting Hub. Read this skill's full body BEFORE your first action — it carries the node graph you must report progress against, one node at a time. kind: task task_name: "Brand IQ setup" label_template: Brand IQ setup nodes:

• id: analyze label: Analysing your store purpose: Read the store's own evidence and draft a brand proposal from it. advance_by: agent tools:
  • yepairag_marketing__ANALYZE_STORE_BRAND
  • yepairag_marketing__SHOW_BRAND_ANALYSIS_PROPOSAL artifact: type: brand_profile route: marketing-hub/brand-iq next:
  • to: confirm when: the proposal card is out
  • to: analyze when: the merchant asks to re-analyze, or wants a revised proposal
• id: confirm label: Ready for your confirmation purpose: Hand the proposal over — saving is the merchant's decision. advance_by: external tools: [] route: marketing-hub/brand-iq revisable: false tags: [internal, task, marketing, requires-yepai-tools] license: MIT-0

---

Task — Brand Iq Setup

Flow

flowchart TD
    analyze["Analysing your store"]
    confirm{{"Ready for your confirmation"}}

    analyze -->|"the proposal card is out"| confirm
    analyze -.->|"the merchant asks to re-analyze, or wa…"| analyze

    classDef terminal stroke-width:3px
    class confirm terminal

Rounded = waiting on the merchant · square = you are working · dashed = going back · bold border = terminal.

analyze

Analysing your store — Read the store's own evidence and draft a brand proposal from it.

1. Call ANALYZE_STORE_BRAND. It is READ-ONLY and returns brand evidence (product naming, category mix, price band, vendors, image-style hints) — it does NOT write anything and does NOT decide the brand voice for you.

2. Open with ONE short sentence naming your read of the brand (e.g. "Bold, design-led snowboard brand spanning entry-level to premium"). Do NOT restate the evidence back — product counts, vendors and price band are already known, and repeating them wastes time. Then go straight to three TIGHT drafts:

   • one Brand Voice — a name plus ONE short guideline paragraph (≤ 80 words) on tone and do's / don'ts
   • 2–3 Audiences — each a name plus a one-line profile with a demographic or lifestyle cue AND what they respond to
   • one Style Guide — a name plus 4–5 concrete terminology / grammar / punctuation rules

   Ground every draft in the real evidence (actual categories, price positioning, recurring vocabulary) — never generic filler, never padding. Be concise: the merchant is waiting, and shorter drafts generate faster.

3. Call SHOW_BRAND_ANALYSIS_PROPOSAL with FLAT arguments (no nested objects): voice_name, voice_content, style_guide_name, style_guide_content, and audiences as a list of plain strings shaped "Name: description". This tool writes nothing — it hands the proposal to the frontend as a review card.

If the store has no products, ANALYZE_STORE_BRAND returns an error — tell the merchant to add products or set up Brand IQ manually. Never fabricate a brand.

"Re-analyze" / "re-scan my store" runs the same loop from step 1 and produces a fresh proposal. Treat existing Brand IQ entries as context to improve on, not something to silently overwrite — the merchant confirms the new proposal before anything changes.

confirm

Ready for your confirmation — Hand the proposal over — saving is the merchant's decision.

The proposal card is with the merchant — end your turn. Saving happens in the frontend after they approve (via chatbot-api's existing brand-voice / audience / style-guide routes); it is NOT a tool you call.

Do not confirm on the merchant's behalf and do not chase them.

How a task runs

This part is the same for every task; only the nodes differ.

1 — Entering the task. Report the first node before doing anything else. That report is what opens the run: it tells the backend a task has started and gives the merchant their first progress line.

2 — Entering each node. Report it the moment you enter, before doing that node's work. One report per node. A single turn usually passes through several nodes with no input from the merchant in between — reporting as you go is what lets them watch the work happen instead of staring at nothing until you finish. A node whose work is a single tool call still gets its report first.

3 — Reaching the end. A terminal node is one with no way out except back to itself. Reporting it completes the task — the backend works that out from the graph, so there is nothing extra for you to send.

4 — After completion. A completed task is not sealed. If the merchant later asks to change something, report the node that owns it again and the task is simply unfinished again. Never open a second task for a change to work you already did.

How to report

yepairag_task__REPORT_TASK_STEP
  task: "brand-iq-setup"
  node: "<the node you just entered>"

• Two fields, both read straight off the graph above. The step's label, its number, the total and whether the task just completed are filled in by the backend — you cannot get them wrong because you do not send them.
• The reply carries legal_next: the only nodes you may report next.
• ok: false means nothing was recorded and the run has not moved. Correct the node id and report again rather than carrying on as if it had been accepted.
• Never restate any of it to the merchant. It drives a progress bar they are already looking at.