Update to Brainerce

{
  "description": "Sweep a Brainerce store for the things that quietly go wrong and hand the merchant a short list of what to fix. Use when the merchant says check my store, is everything ok, spring clean, audit the shop, what am I missing, anything broken, or I have not looked at this in a while. Finds products left as drafts, items out of stock, promotions that expired or were never switched off, orders stuck waiting on someone, and on the full connector dead webhooks, bounced emails and a missing backup schedule. For store owners, not developers. Not for the morning check-in (brainerce-daily-summary), one metric or trend (brainerce-analytics), one known order (brainerce-order-handling), or how the catalog is structured rather than its state (brainerce-store-architecture). Keywords: store health, audit, check my store, spring clean, tidy up, what is broken, drafts, out of stock, expired discount, stuck orders, housekeeping, review my shop.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 1127
    },
    {
      "relative_path": "assets/icon.png",
      "size_in_bytes": 3208
    }
  ],
  "name": "brainerce-store-health",
  "skill_md_contents": "---\nname: brainerce-store-health\ndescription: \"Sweep a Brainerce store for the things that quietly go wrong and hand the merchant a short list of what to fix. Use when the merchant says check my store, is everything ok, spring clean, audit the shop, what am I missing, anything broken, or I have not looked at this in a while. Finds products left as drafts, items out of stock, promotions that expired or were never switched off, orders stuck waiting on someone, and on the full connector dead webhooks, bounced emails and a missing backup schedule. For store owners, not developers. Not for the morning check-in (brainerce-daily-summary), one metric or trend (brainerce-analytics), one known order (brainerce-order-handling), or how the catalog is structured rather than its state (brainerce-store-architecture). Keywords: store health, audit, check my store, spring clean, tidy up, what is broken, drafts, out of stock, expired discount, stuck orders, housekeeping, review my shop.\"\ncompatibility: ChatGPT, Claude Code, Claude Desktop, Cursor\nmaintainer: Brainerce\nmetadata:\n  author: Brainerce\n  version: '1.0.0'\n---\n\n⛔ **Before you call anything a dashboard task, look for `search_tools` in your tool list.** Some connections carry a small curated list PLUS a way to reach everything else. Where `search_tools` exists, search for what the merchant asked for and call any hit through the `call_read_tool` / `call_write_tool` / `call_destructive_tool` it names. The dashboard is the honest answer only when your list has no `search_tools`, or the search comes back empty. A few things are refused through it deliberately (payment provider setup, refunds and recording payments, gift cards), which is why an empty result there is a real answer rather than a gap.\n\nFind the quiet problems a busy merchant stops seeing, and give them an ordered list of what to do about it.\n\n## Core principle\n\nThe output is a to-do list, not a report. Every line should name a real thing, say why it costs the merchant something, and be actionable. A finding with no consequence attached gets ignored, and rightly so.\n\nRead only. This skill diagnoses. Fixing happens after the merchant picks something.\n\n## When to use this skill first\n\n- \"Check my store\", \"is everything ok\", \"anything broken\".\n- \"Spring clean\", \"tidy up the shop\", \"audit this\".\n- \"I have not looked at this in months\".\n- \"What am I missing\".\n\n## When NOT to use this skill first\n\n- The routine \"how did yesterday go\": use `brainerce-daily-summary`.\n- One number or a trend: use `brainerce-analytics`.\n- One known order: use `brainerce-order-handling`.\n- How the catalog is STRUCTURED rather than what state it is in, so variant explosion, a flat category tree, tags doing a category's job: use `brainerce-store-architecture`. This sweep is about state; that one is about shape.\n\n---\n\n## The four sweeps, and a fifth on the full connector\n\nRun all four, and the fifth when its tools are in your list. A sweep that finds nothing is still worth one line, because \"no drafts left hanging\" is information.\n\nOne call comes before them on a store that has taken no orders yet, or whenever the question is \"what am I missing before I can sell\": `get_store_setup_status`. It returns the six setup steps (store name, sales channel, products published to a channel, shipping, payment provider, tax) with done or not done and a `nextAction` for each, and a payment provider in test mode counts as not done. Report its first undone step at the top of the list, above anything the four sweeps find, because a store that cannot take an order has no other problem worth fixing first.\n\n### 1. Products that are not really for sale\n\n- `list_products` filtered to draft status: products the merchant created and forgot to publish. These are invisible to customers and the merchant usually believes they are live.\n- `list_products` plus `get_product_inventory` on what comes back: items at zero stock. Cross-check against `get_top_selling_products`, because a best seller at zero is urgent and a slow mover at zero is housekeeping.\n- `list_products` with `hasImages: \"false\"`: products with no picture at all. Shoppers do not buy what they cannot see, and this is a real filter on the tool.\n- ⛔ There is no way to ask for products with no category. `list_products` takes a `categories` filter that narrows to a category you name; it cannot ask for the products that have none, and paging the whole catalog to work it out is exactly what that tool warns against (\"NOT for counting\"). Uncategorised products are found in the dashboard, on the Products page. Say that rather than guessing at a number.\n\n### 2. Promotions nobody is watching\n\n- `list_discount_rules` and `list_coupons`. Look for two different problems, and do not merge them:\n  - **Expired**: past its end date and cluttering the list. Low priority.\n  - **Still running and probably should not be**: no end date, or an end date that already passed while the rule stayed enabled, or a promotion the merchant set up for an event that is over. This one costs money every day, so it goes at the top.\n\n### 3. Orders waiting on somebody\n\n- `get_orders_by_status` gives the **shape** of the backlog and nothing more: a count and a percentage per status. ⛔ Two limits, and both bite exactly here. It returns no order ids and no dates, so it cannot be ranked by age. And it only counts orders from the **last 30 days**, so the genuinely stuck order this sweep exists to find is not even in its numbers. Use it for \"roughly how many are waiting\", never for \"which one has waited longest\".\n- `list_orders` is what finds the old ones. Pass `sortBy: \"createdAt\"` and `sortOrder: \"asc\"` to put the oldest first; every row comes back with `orderNumber`, `customerName`, `status` and `createdAt`, and there is no 30-day window on it.\n- The `status` filter takes **one status at a time**, so this is a call per state rather than one call. The states that mean \"waiting on the merchant\" are `PENDING`, `PROCESSING`, `PAID` and `ON_HOLD`. There is no `UNFULFILLED` status: unfulfilled means an order that has not yet reached `SHIPPED`, `FULFILLED`, `DELIVERED` or `COMPLETED`.\n- `get_recent_orders` to see whether the backlog is growing or is a one-off.\n\n### 4. Signals from customers\n\n- `list_product_reviews` filtered to low ratings, and `get_product_review_stats` on the products that sell most. A best seller whose rating has slipped is worth knowing about before it shows up in the revenue.\n\n### 5. The plumbing, full connector only\n\nThese four reads exist on the full connector (Claude Code, Cursor, Claude Desktop) since 2026-09-15 and not on the ChatGPT app, so run them when they are in your tool list and skip the sweep silently otherwise.\n\n- `get_connection_health`: every storefront channel and installed app with its status, last ping and last error. A channel that has not pinged in days, or an app in error, is a storefront that may be quietly down.\n- `get_webhook_health`: deliveries succeeded and failed in the last 24 hours and any subscription whose circuit breaker is open. An open breaker means the merchant's integration stopped receiving orders and nobody was told; `update_webhook_subscription` with `isActive: true` resets it, after the merchant has fixed the endpoint.\n- `list_email_logs` filtered to BOUNCED or FAILED: order emails that never reached customers. A run of bounces on one domain usually means a sending domain that lost verification; `list_email_domains` shows the status.\n- `get_backup_schedule`: `schedule: null` on a store with real orders is worth one line, because nothing is backing it up. `upsert_backup_schedule` fixes it in one call, and restoring a backup is dashboard-only.\n\n`get_inventory_summary` also belongs here as the one-call version of sweep 1's stock check: products counted, units available, how many are low and how many are out.\n\n## Shape the answer\n\nOrder by cost to the merchant, not by category. Put money-losing first, customer-facing second, housekeeping last. Cap the list; five real problems beat thirty observations.\n\n**Use this shape:**\n\n> ✓ I went through your store. Four things worth your time, most costly first:\n>\n> 1. **A 30% sale is still running on Summer Dresses.** It has no end date and it started in June. Every order since then has been discounted. Want me to switch it off?\n> 2. **Six orders are unfulfilled**, the oldest from 4 November. That customer has been waiting eleven days.\n> 3. **Ceramic Mug is out of stock** and it was your best seller last week. Every day it stays at zero is lost sales.\n> 4. **Three products are still drafts**: Linen Scarf, Wool Hat, Gift Box. Customers cannot see them.\n>\n> Also fine: no expired coupons cluttering things up, and your review ratings are all above 4.\n>\n> Which of these do you want to start with?\n\n**Clean store, use this shape:**\n\n> ✓ Your store looks in good shape. No drafts left hanging, nothing out of stock, every product has a picture, no promotions running past their date, and no orders sitting unfulfilled for more than a day.\n>\n> The one thing I would keep an eye on: Ceramic Mug is down to 4 in stock and it sells about 3 a day.\n\n## Rules\n\n- Read only. Do not fix anything during the sweep, even something obviously wrong. Report, then let the merchant choose.\n- Every finding needs a consequence. \"Three drafts\" is a fact; \"three drafts customers cannot see\" is a reason to care.\n- Rank by cost. An overrunning discount outranks an untidy tag list, always.\n- Name real items and real dates. Vague findings get ignored.\n- Say what came back clean. Otherwise the merchant cannot tell whether you checked.\n- Cap the list at around five items and offer to go deeper. A thirty-item audit gets closed.\n- Do not report the same thing twice under two headings.\n- Offer `toggle_discount_rule` to switch a promotion off. That is the reversible move and it is the one to lead with.\n- Deleting is not available on the ChatGPT app, which carries a curated list with no delete tool on it. On the full connector `delete_product`, `delete_coupon` and `delete_discount_rule` do exist. If a delete tool is not in your list, say so and point at the Brainerce dashboard rather than claiming the platform cannot do it.\n\n## Cross-skill connections\n\n- The merchant picks a promotion to switch off or change: `brainerce-launch-a-sale`.\n- They pick an order out of the list: `brainerce-order-handling`.\n- They want to restock or publish a draft: `brainerce-product-onboarding`.\n- They want to understand a trend the sweep hinted at: `brainerce-analytics`.\n- The sweep keeps hitting the same structural problem, such as one product with hundreds of variants: `brainerce-store-architecture`.\n\nRoute once, and do not bounce back and forth.\n"
}