本文へ移動
cccskills
無料GitHub で公開

ecommerce.tiktok-video-analytics

Search TikTok e-commerce trending promotional video leaderboards via Kalodata and query detailed data for specific videos. Supports viewing high-ranking/high-view/hot-selling promotional videos by region, currency, language, and date range, and using videoId to retrieve views, likes, comments, shares, revenue, GPM, and advertising metrics. Trigger when users mention TikTok video search, TikTok video ranking, TikTok viral video chart, TikTok video detail, video analytics, kalodata video search/detail. Even if the user does not explicitly mention "kalodata", trigger this skill whenever their need involves viewing TikTok trending promotional video leaderboards or detailed sales and engagement data for a specific TikTok video.

インストール方法を見る

含まれるファイル(5)

  • SKILL.md9.2 KB
  • manifest.json259 B
  • references/api.md9.8 KB
  • scripts/video_detail.py6.5 KB
  • scripts/video_rank.py6.5 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Kalodata - TikTok Video Search & Detail

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

  1. Browse TikTok Shop video leaderboards to discover high-performing shoppable videos.
  2. Fetch one video's full performance detail by videoId.

Use the search endpoint when the user wants rankings, hot videos, viral videos, or video discovery. Use the detail endpoint when the user already has a videoId or has selected one video from a ranking result.

Core Concepts

The video ranking endpoint returns a paginated leaderboard filtered by region, dateRange, language, currency, and optional sortField. Each video row includes identity, engagement, revenue, ad-performance, and creator fields. Results are paginated with pageNumber (1-5) and pageSize (5-100).

The video detail endpoint fetches one shoppable TikTok video by videoId. It returns the video's engagement metrics, monetization metrics, advertising metrics, creator identity, region, duration, and linked product count. The videoId usually comes from the ranking response field video_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:

FieldDescription
video_idVideo unique ID; pass this as videoId for detail lookup
video_titleVideo title / caption
viewsVideo view count
digg_count / comment_count / share_countLikes, comments, and shares
revenueTotal GMV in the requested currency
revenue_growth_rateRevenue growth rate (%)
ad / ad_view_ratio / ad_revenue_ratio / ads_roasAd and advertising performance fields
belonged_creator_id / belonged_creator_handleCreator identity
creator_debutCreator debut date

Detail rows additionally include:

FieldDescription
video_regionVideo region; may be empty
sales_volumnSales volume; field is spelled volumn
video_gpmGMV per mille (revenue per 1000 views)
ads_views / ad_cpa / ads_periodAd views, CPA, and ad running period
durationVideo duration in seconds
product_numberNumber of products linked in the video

Parameter Guide

Video ranking (/kalodata/video/rank)

ParameterTypeRequiredDescription
regionstringNoMarket region code, e.g. US
dateRangestringNoTime window, e.g. last7Day, last30Day
pageNumberintegerNoPage number, 1-5
pageSizeintegerNoPage size, 5-100
languagestringNoResponse language, e.g. zh-CN, en-US
currencystringNoCurrency for monetary metrics, e.g. USD
category_idstringNoCategory ID filter
shop_idstringNoShop ID filter
creator_idstringNoCreator ID filter
product_idstringNoProduct ID filter
revenue_rangestringNoGMV range because response field revenue is total GMV; examples: 1-100, >1000, <100
followers_rangestringNoCreator follower range filter
ads_roasnumberNoAdvertising ROAS filter
sortFieldobjectNoGMV sorting specification, e.g. {"field":"revenue","type":"DESC"}

Video detail (/kalodata/video/detail)

ParameterTypeRequiredDescription
videoIdstringYesTikTok video ID from ranking field video_id or a TikTok video URL
regionstringNoMarket region code, e.g. US
dateRangestringNoTime window, e.g. last7Day, last30Day
languagestringNoResponse language, e.g. zh-CN, en-US
currencystringNoCurrency for monetary metrics, e.g. USD

How to Call

  • API Endpoints: POST /kalodata/video/rank or POST /kalodata/video/detail (see references/api.md for full parameters/response/error codes)
  • Python Scripts: python scripts/video_rank.py '<JSON parameters>' [--inline] or python scripts/video_detail.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-video-<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.

Response handling

For the research HTTP response, require a numeric outer code equal to 0 before using data. Nonzero codes are platform failures; display outer msg without interpreting its wording as a retry instruction. Nexscope preserves upstream messages and translates Chinese to English; successful responses may have msg: null. HTTP 200 alone and nested business code / status do not replace the platform check. See references/api.md for response paths and task-specific states.

Authentication

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

Usage Examples

1. Browse top TikTok videos in the US

{"region":"US","dateRange":"last7Day","pageSize":10,"pageNumber":1,"currency":"USD"}

2. Fetch one video's detail

{"videoId":"7659161409279806734","region":"US","dateRange":"last7Day","currency":"USD"}

3. Discovery-to-detail workflow

Run `video_rank.py` first, choose a row's `video_id`, then pass that value as `videoId` to `video_detail.py`.

Display Rules

  1. Present ranking results in a table with title, video ID, views, engagement, revenue, ad indicators, and creator handle.
  2. Present detail results as one grouped profile: identity, engagement, monetization, ads, creator, duration, and linked products.
  3. Always label dateRange, region, and currency when showing metrics.
  4. Use the exact field name sales_volumn.
  5. video_gpm is GMV per mille; do not display it as a percentage.
  6. 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 videoId; it cannot find a video by title alone.
  • The ranking response does not include total/page count; result count is data.length.
  • pageNumber is limited to 1-5 and pageSize is limited to 5-100.
  • Transient upstream errors may appear as a nonzero platform code with an upstream failure message. Retry the same parameters once or twice; do not change parameters automatically.
  • Use the matching Kalodata product/creator/shop/livestream skills for non-video entities.

User Expression & Scenario Quick Reference

Applicable -- TikTok video ranking or video detail lookup:

User SaysScenario
"TikTok video ranking", "TikTok video leaderboard"Video ranking lookup
"TikTok trending videos", "TikTok viral videos"Top or viral video ranking
"TikTok promotional video ranking", "top TikTok videos"Region-specific shoppable video leaderboard
"TikTok video detail", "TikTok promotional video data"Single video detail lookup
"Video views", "video engagement data", "video GPM"Video engagement or monetization metrics
"kalodata video search/detail"Direct data source reference

Not applicable -- Needs beyond TikTok videos:

  • TikTok product / creator / shop / livestream rankings or details
  • Keyword-based video or product search
  • TikTok advertising / ad campaign management
  • Video editing, video download, or content creation

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Query 1688 product bestseller billboard data for sourcing discovery and wholesale product research. Trigger when the user mentions 1688 product rankings, 1688 bestseller lists, wholesale hot products, domestic sourcing rankings, dropshipping product selection, 1688 trending products, bulk purchase popular items, supplier product rankings, 1688 billboard, 1688 bestsellers, sourcing rankings, wholesale hot products, trending product rankings, supplier rankings, 1688 trends. Even if the user does not explicitly mention "1688 billboard", if their need involves discovering hot-selling wholesale products or sourcing opportunities on the 1688 platform, this skill should also be triggered.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Query 1688 public product details through the Nexscope research proxy. Use when the user requests this public marketplace or patent data; do not use for seller-console or store-authorized operations.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Search and analyze products on the Chinese 1688 wholesale platform (Alibaba domestic B2B market) for sourcing, supplier discovery, and product selection. Trigger when the user mentions 1688 product search, finding suppliers on 1688, wholesale product queries, factory sourcing, dropshipping supplier search, 1688 keyword product selection, wholesale price comparison, filtering by sales volume, any product research on the 1688 platform, 1688 search, 1688 product selection, find suppliers, factory lookup, wholesale pricing, supplier search, domestic sourcing, 1688 products. Even if the user does not explicitly say "1688", if their need involves searching for wholesale products, finding domestic suppliers, or sourcing from the domestic Chinese market, this skill should also be triggered.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Perform image-based product search on the 1688 platform. Use an image URL to find visually similar supplier products, returning title, price, minimum order quantity, monthly sales, repurchase rate, trade score, and seller identity. Triggered when users mention 1688 image search, 1688 visual search, find supplier by image, reverse image search 1688, 1688 product sourcing by image, or Alibaba 1688 image search. Even if the user does not explicitly mention "image search," this skill should be triggered whenever a user provides an image URL and wants to find matching or similar products on the 1688 wholesale platform.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Authorize Amazon Ads accounts and inspect safe connection and profile metadata.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

Read and mutate SP, SB, and SD campaigns, ad groups, ads, targeting, and budget rules.

日本語の概要は準備中です。原文の説明を表示しています。

nexscope-ai/nexscope-ecommerce-skills862026年10月9日 更新

nexscope-ai のスキルをすべて見る

このスキルの問題を報告する