Kalodata - TikTok Product Search & Detail

This skill supports a two-step TikTok Shop product workflow via the Kalodata data source:

1. Browse TikTok Shop product leaderboards to discover top-ranked and best-selling products.
2. Fetch one product's full detail by productId.

Use the ranking endpoint when the user wants best-seller rankings, hot products, or product discovery. Use the detail endpoint when the user already has a productId or has selected one product from a ranking result.

Core Concepts

The product ranking endpoint returns a paginated leaderboard filtered by region, dateRange, currency, language, and optional sortField. Each product row includes identity, price, sales volume, revenue (split across video, live, and showcase channels), revenue growth rate, commission rate, and launch date. Results are paginated with pageNumber (1-5) and pageSize (5-100).

The product detail endpoint fetches one TikTok Shop product by productId. It returns the product's price range, sales, revenue (with channel split), commission rate, launch date, review count, category hierarchy, owning shop, and associated video/live/creator counts. The productId usually comes from the ranking response field product_id.

Both endpoints may reflect a statistical delay (T+1). See references/api.md for full request and response details.

Data Fields

Ranking rows include:

Detail rows additionally include:

Detail revenue channel split: revenue = videorevenue + liverevenue + shoppingmallrevenue.

Parameter Guide

Product ranking (/kalodata/product/rank)

Product detail (/kalodata/product/detail)

How to Call

• API Endpoints: POST /kalodata/product/rank or POST /kalodata/product/detail (see references/api.md for full parameters/response/error codes)
• Python Scripts: python scripts/productdetail.py '<JSON parameters>' [--inline] or python scripts/productdetail.py '<JSON parameters>' [--inline]
• Cost constraint: This tool consumes credits; the same parameter combination in the same session is called only once by default, with 24h local caching in the script. On failure/empty results, do not automatically retry with different keywords, pagination, or filter changes; inform the user before making additional queries.

Output strategy (default script behavior):

• Always write the full response to <cwd>/nexscope/<YYYY-MM-DD>/<session>/data/nexscope-kalodata-tiktok-product-<timestamp>.json (<cwd> is the working directory at script execution time, i.e., the current project directory in Claude Code; <session> is taken from the SESSION_ID environment variable, auto-grouped by user task; do not write to /tmp, error if the current directory is not writable)
• Response body <= 8 KB: print the full JSON to stdout after writing to disk
• Response body > 8 KB: stdout only outputs a summary (top-level fields, common counts like total/costToken, length of the largest list field + first 3 samples)
• Add --inline to force full output to stdout (still writes to disk)

Data reading tip: Check the summary first to see if sufficient; for specific fields, prefer using jq or ConvertFrom-Json to extract from the saved JSON file on demand, avoiding loading the entire JSON into context.

Authentication

Set NEXSCOPEAPIKEY. Visit https://www.nexscope.ai/help/skills-external-access?co-from=skillNS to manage credits.

Usage Examples

1. Browse top TikTok products in the US (last 7 days)

{"region":"US","dateRange":"last7Day","pageSize":20,"pageNumber":1,"currency":"USD"}

2. Fetch one product's detail

{"productId":"1729508370969629931","region":"US","dateRange":"last7Day","currency":"USD"}

3. Discovery-to-detail workflow

Run product_detail.py first, choose a row's product_id, then pass that value as productId to product_detail.py.

Display Rules

1. Present ranking results in a table with product name, product ID, price, sales volume, revenue (with channel split), growth rate, commission rate, and launch date.
2. Present detail results as one grouped profile: identity, price range, sales, revenue (channel split), commission, category hierarchy, owning shop, and associated video/live/creator counts.
3. Always label dateRange, region, and currency when showing monetary metrics.
4. Use the exact field name sales_volumn.
5. commission_rate is a direct percentage (25.0 = 25%), not basis points -- show with a % sign.
6. revenuegrowthrate is a percentage -- show with a % sign.
7. Revenue channel split: ranking revenue = videorevenue + liverevenue + showcaserevenue; detail revenue = videorevenue + liverevenue + shoppingmall_revenue. Present the split when useful.
8. Preserve ranking order unless the user explicitly requests a supported sortField.

Important Limitations

• Ranking is not keyword search; it browses leaderboards by region and time window.
• Detail requires productId; it cannot find a product by name alone. Obtain productId from the ranking product_id first.
• The ranking response does not include total or page count; result count is data.length.
• pageNumber is limited to 1-5 and pageSize is limited to 5-100.
• A valid-but-empty request (e.g. an unsupported region) may return errcode 200 with no data field and still be billed.
• Transient upstream errors may appear as errcode 501 with a Kalodata HTTP 5xx message (e.g. 522/554). Retry the same parameters once or twice; do not change parameters automatically.
• Use the matching Kalodata video/creator/shop/livestream skills for non-product entities.

User Expression & Scenario Quick Reference

Applicable -- TikTok product ranking or product detail lookup:

Not applicable -- Needs beyond TikTok products:

• TikTok video / creator / shop / livestream rankings or details
• Keyword-based product search
• Amazon / Shopify / 1688 product research (use the platform-specific skills)
• TikTok advertising / ad campaign management or content creation