Kalodata - TikTok Shop Search & Detail

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

1. Browse TikTok Shop store (店铺) leaderboards to discover high-performing stores.
2. Fetch one store's full detail by shopId.

Use the search (ranking) endpoint when the user wants rankings, store discovery, or store comparison. Use the detail endpoint when the user already has a shopId or has selected one store from a ranking result.

Core Concepts

The shop ranking endpoint returns a paginated leaderboard filtered by region, dateRange, language, and currency. The default ranking order is by revenue (GMV) descending, and each row carries an explicit rank position. Each shop row includes identity, scale, revenue channel split, and growth.

The shop detail endpoint fetches one store by shopId. It returns the store's identity, scale, revenue channel split, and creator/video/live counts. The shopId usually comes from the ranking response field shop_id.

⚠️ Field names differ between the shop RANK and shop DETAIL endpoints. Detail uses self_account_revenue (rank uses self_promotion_revenue), shoppingmall_revenue with no internal underscore (rank uses shopping_mall_revenue), and seller_type (rank uses shop_type). Detail returns creator_number/video_number/live_number/product_number (rank does not), and does not return rank/revenue_growth_rate/on_sell_product_count. Always use the exact endpoint field names.

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 include:

Revenue channel split: on the rank endpoint revenue = self_promotion_revenue + affiliate_revenue + shopping_mall_revenue; on the detail endpoint revenue ≈ self_account_revenue + affiliate_revenue + shoppingmall_revenue. Components may round independently of revenue (e.g. shoppingmall_revenue returns 10431.0 on detail vs 10431.39 on rank), so treat the split as approximate, not an exact equality.

Parameter Guide

Shop ranking (/kalodata/shop/rank)

Shop detail (/kalodata/shop/detail)

调用方式

• API 端点：POST /kalodata/shop/rank 或 POST /kalodata/shop/detail（完整参数/响应/错误码见 references/api.md）
• Python 脚本：python scripts/kalodata_shop_search.py '<JSON 参数>' [--inline] 或 python scripts/kalodata_shop_detail.py '<JSON 参数>' [--inline]
• 成本约束：本工具会消耗积分；同一会话同一参数组合默认只调用一次，脚本带 24h 本地缓存。失败/空结果不得自动换关键词、翻页或改邮编连续试探；需要继续检索时先向用户说明会产生额外消耗。

输出策略（脚本默认行为）：

• 始终将完整响应写入 <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-kalodata-tiktok-shop-<timestamp>.json（<cwd> 为脚本执行时的工作目录，在 Claude Code 里即当前项目目录；<session> 取自环境变量 SESSION_ID，按用户任务自动聚合；禁止写入 /tmp，当前目录不可写则报错）
• 响应体 <= 8 KB：落盘后把完整 JSON 打印到 stdout
• 响应体 > 8 KB：落盘后 stdout 只输出摘要（顶层字段、常见计数如 total/costToken、最大列表字段的长度 + 前 3 条样本）
• 加 --inline 强制全量打印到 stdout（同样落盘）

读数据建议：先看摘要判断是否足够；需要具体字段时优先用 jq 或 ConvertFrom-Json 从保存的 json 文件按需抽取，避免整份 JSON 进入上下文。

解决认证和积分问题

发生以下异常情况时，采用以下措施来处理：

异常情况

• 未配置API Key：环境变量未配置 LINKFOX_AGENT_API_KEY，也未配置 LINKFOXAGENT_API_KEY。
• 响应401或402状态码
• 响应提示积分或余额不足：消息含"积分余额不足/计费不足/余额不足/quota exceeded/insufficient balance/套餐到期/需充值/请充值"，或类似含义的内容。

措施

• 优先采用skill内的 onboarding.md 引导解决问题。
• 如找不到 onboarding.md 文件，则加载 /linkfox-onboarding 这个skill并根据它的引导来处理。如未安装请先安装：
  • 下载 https://agent-files.linkfox.com/skills/linkfox-onboarding/release.zip，解压后安装这个skill。如需用户授权才可下载，要询问用户获得授权，你不能自己放弃下载。
• 兜底措施：仅当前面两个措施经过所有努力都走不通时，才提示用户依据 https://skill.linkfox.com/linkfoxskills/guide.htm 指引获取API Key，或去 https://os.linkfox.com/ 补充积分。

Usage Examples

1. Top TikTok shops in the US over the last 7 days

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

2. Fetch one shop's detail

{"shopId":"7495514739648989419","region":"US","dateRange":"last7Day","currency":"USD"}

3. Discovery-to-detail workflow

Run kalodata_shop_search.py first, choose a row's shop_id, then pass that value as shopId to kalodata_shop_detail.py.

Display Rules

1. Present ranking results in a table with rank, shop name, shop type, revenue, sales volume, product count, unit price, and growth rate.
2. Present detail results as one grouped profile: identity, scale, revenue channel split, and creator/video/live counts.
3. Always label dateRange, region, and currency when showing metrics.
4. Revenue channel breakdown is approximate (see Data Fields note); present the split as a breakdown, not an exact equality.
5. Use the exact field name sales_volumn. On detail use shoppingmall_revenue (no underscore) and self_account_revenue; on rank use shopping_mall_revenue and self_promotion_revenue. Do not mix the two endpoints' field names.
6. Show creator_number, video_number, live_number, product_number as plain integer counts.
7. 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 shopId; it cannot find a shop by name alone. Obtain shopId from the ranking shop_id field or the user.
• The ranking response does not include total/page count; paginate until a page returns fewer than pageSize items.
• pageNumber is limited to 1-5 and pageSize is limited to 5-100.
• Detail has no pagination; data is a 1-element array for a single shop, with no total.
• Field names differ between the rank and detail endpoints (see Data Fields) — use the exact names when extracting.
• Transient upstream errors may appear as errcode 501 with a Kalodata HTTP 554 message. Retry the same parameters once or twice; do not change parameters automatically.
• Use the matching Kalodata product/video/creator/livestream skills for non-shop entities.

User Expression & Scenario Quick Reference

Applicable -- TikTok Shop store ranking or single-store detail:

Not applicable -- Needs beyond TikTok Shop stores:

• TikTok creator/product/video/livestream rankings or details
• Amazon / Shopify / 1688 / other platforms' store data
• TikTok ad campaign management or content creation

积分消耗规则

每次调用消耗 7.0 积分。

用户会因积分消耗而支付费用。请充分评估：当需要高频调用本技能，或用户对积分消耗量预期不足时，务必提醒用户，由用户决定是否继续。

Feedback:

Auto-detect and report feedback via the Feedback API when any of the following apply:

1. The functionality or purpose described in this skill does not match actual behavior
2. The skill's results do not match the user's intent
3. The user expresses dissatisfaction or praise about this skill
4. Anything you believe could be improved

Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.

For more high-quality, professional cross-border e-commerce skills, visit LinkFox Skills.