Turn marketplace data into decisions—and give your AI better context.

Call GET /v1/exports/catalog and confirm my category and market are available and for which months. Then POST /v1/exports with "estimate": true and a body like {"country": "ID", "category_3": ["Shampoo"], "platforms": ["Shopee"], "date_from": "2026-01", "date_to": "2026-06", "top": 100, "format": "csv", "estimate": true}. Show me rows, credits and dollars, and wait for my approval before submitting without estimate. Then poll GET /v1/exports/{export_id} until the files are ready and download them.

From the data give me: the ten largest brands by GMV and their share in the most recent month; how each share has moved since the first month; realised price per unit for each against the category average, as an index with the average at 100; and any brand whose share moved more than a third either way. Flag any month whose row count is sharply out of line with its neighbours — that is a collection artefact, not a market move, so say so rather than reporting it as a trend.

Using the catalogue and a free estimate first, export the most recent full month of my category at "top": 500. Compute realised price per unit per brand as GMV divided by units. Bucket brands into price deciles against the category average and report, per decile, how many brands sit there and what share of category GMV they hold together.

Look for a band holding meaningful demand but few competing brands. If there is no such gap, say so explicitly rather than manufacturing one.

Using the catalogue and a free estimate first, export the most recent month of my category at "top": 100. Report the combined share of the top ten brands, the number of brands needed to reach half of category GMV, and the realised price index of the top three against the category average.

Then classify the category: concentrated and premium (leaders hold high share at high price), concentrated and cheap (leaders hold share by undercutting), or fragmented (no brand holds meaningful share). Give the reasoning, not just the label — each implies a different entry cost.

I will give you a list of products, each with our offer price and the Shopee URL of the matching listing. For each row, extract shop_id and item_id from the URL, which ends in -i.{shop_id}.{item_id}. POST to /v1/shopee/get_pc/submit with {"region": "id", "item_id": "...", "shop_id": "..."} to get a task_id, then poll GET /v1/shopee/get_pc/retrieve/{task_id} until it returns a result. Read the current price and divide it by 100000.

Give me a table of every product where the Shopee price is at or below ours, showing our price, the Shopee price and the gap. Also report is_lowest_price_at_shopee for each row — read it from each entry in item.models, because the item-level field comes back null.

Only use get_pc: it runs without manual approval.

Submit POST /v1/shopee/search-items/submit with Shopee search URLs sorted by sales (?page=0&sortBy=sales), several keywords covering my category, up to 50 URLs. Poll the job, download each frame and parse it using the Shopee parsing rules in the skill. Deduplicate by itemid before summing anything.

Compute GMV per listing as units × price, aggregate by shop, and report the twenty largest shops with their share of the total observed, listing count, average realised price and location. Separate official brand stores from resellers where the shop name makes that clear. Tell me how many submitted URLs returned data and how many failed.

Run a Shopee search-items job using my brand name and its common misspellings as keywords, sorted by sales. Parse per the skill's Shopee rules, deduplicate by itemid and aggregate by shop.

I will give you my list of authorised distributors and our price floor. Produce two tables: every shop selling the brand that is not on the list, with observed GMV, listing count and location, sorted by size; and any authorised shop whose realised price sits more than twenty per cent below the floor.

Do not accuse anyone of counterfeiting. Report only what the listing data shows — who is selling, at what price, from where.

Submit POST /v1/shopee/merchant-items/submit with {"urls": ["https://shopee.co.id/shop/<shop_id>"], "max_pages": 5}, up to 50 shop URLs per request, then poll GET /v1/shopee/merchant-items/retrieve/{job_id} until complete. On this endpoint the numeric sold field is 0, so read monthly_sold_count_text, which is exact. The payload repeats items across the shop's category tabs, so deduplicate by itemid first or the total roughly doubles.

Give me the listing count, total observed monthly GMV, the twenty listings carrying most of it, and the price distribution.

Do not compare this shop's total against a market total built from keyword search. The shop is fully enumerated and the market is not, so any share computed that way is a ceiling, not an estimate. If I ask for a share, say that.

Run a Shopee search-items job for my category keywords sorted by newest (?page=0&sortBy=ctime). Save the itemid list. Run it again weekly and compare against the previous week's list.

Each week, report the listings that are new since the last run, grouped by shop, with price and any units already recorded. Highlight any new listing that took meaningful volume immediately — that usually means a launch with paid support behind it.

Submit POST /v1/shopee/variant_sold_v1/submit with {"items": [{"item_id": "...", "shop_id": "...", "country": "id"}]} for the products I give you — one country per request. Poll until complete.

Report sold count per variant, ranked, with each variant's share of the product total. Tell me whether demand concentrates in one or two variants or spreads evenly, because that decides whether the range needs pruning.

For the Lazada product I give you, take the numeric item ID from the product URL (…-i5133872551.html gives 5133872551) — the review endpoints reject product page URLs. Submit POST /v1/lazada/product-reviews with {"requests": [{"url": "https://my.lazada.co.id/pdp/review/getReviewList?itemId=<item_id>"}]} and poll GET /v1/lazada/retrieve/{task_id}. Each call returns five reviews; add &pageNo=2, &pageNo=3 for more. Agree a page budget with me before reading more than a few pages, because every page is billed.

Group the reviews by star rating. Summarise the recurring complaints in the one and two star reviews and the recurring praise in the five star ones, quote a few representative lines verbatim, and say how many reviews you read out of reviewTotal.

Submit POST /v1/tokopedia/search/bulk/submit with {"items": [{"list_type": "search", "keyword": "<keyword>", "product_limit": 60}]} for each of my keywords (up to 50 per request). Poll GET /v1/tokopedia/search/bulk/retrieve/{job_id}, and download each item's download_url promptly and save it — the links expire.

A listing's rank is its position in the products array, counting from 1. Skip any product whose ads.id is filled — that slot is sponsored, not organic. Match my listings by id or shop.id and record rank per keyword per run, then show me who climbed past us since the last run.