linkfox-ai/linkfox-skills

linkfox-sif-keyword-summary

在给定关键词下拆解所有竞品 ASIN 的流量来源——自然搜索、SP 广告、SB 品牌广告、SBV 视频广告、SP 推荐、AC/ER/TR 等推荐位,支持按 ASIN 过滤、指定日期区间及新进流量词等筛选。当用户提到关键词流量来源、该关键词下哪些竞品在抢流量、自然流量与付费流量占比、SP广告曝光、品牌广告占比、SP推荐位、推荐位广告/非广告拆分、搜索展示分析、Amazon's Choice或编辑推荐曝光、关键词竞争格局、ASIN流量构成、keyword traffic, traffic structure an…

Vedi sorgente

Come usare

  1. Copia il comando e controlla il pacchetto prima di installarlo nel tuo ambiente agente.
  2. Controlla strumenti, credenziali e ambienti richiesti nel documento originale.
  3. Descrivi input e risultato desiderato; confronta l’output con le fonti.
npx skills add https://github.com/linkfox-ai/linkfox-skills --skill linkfox-sif-keyword-summary

Prima di iniziare

  • L’installazione non include abbonamenti, quote API o accesso ai file.
  • Stelle e installazioni indicano attività, non un test indipendente di qualità o sicurezza.
Documento Skill originale

Contenuto dal repository con titoli, esempi, codice, tabelle, link e immagini preservati.

SIF Keyword Traffic Source Summary

This skill guides you on how to query and analyze keyword traffic source data for Amazon products, helping sellers understand the traffic structure behind keywords — including organic search, Sponsored Products (SP) ads, brand ads, video ads, and various Amazon recommendation placements.

Core Concepts

The SIF Keyword Summary tool returns, for one given keyword, the list of ASINs appearing under that keyword along with their per-keyword traffic exposure breakdown and their product-level cross-channel traffic mix. It answers: Who is taking traffic under this keyword, and through which channels?

Traffic channels analyzed:

  • Natural Search — organic search result positions
  • SP Ads (Sponsored Products) — paid product ad placements (regular slot)
  • Brand Ads (SB) — top and bottom brand ad placements on the search results page
  • Video Ads (SBV) — Sponsored Brands Video placements
  • SP Recommendation slots — Trending now / Seen on social media / Customers frequently viewed / 4 stars and above
  • Amazon's Choice (AC) — Amazon's Choice badge recommendations
  • Editorial Recommendations (ER) — editorial/curated recommendation placements
  • Top Rated (TR) — high-rating recommendation placements

Two score families (important — do not mix):

  1. Product-level fields (no prefix, e.g. naturalSearchExposureScore): the ASIN's overall exposure across all keywords.
  2. Keyword-level fields (keyword… prefix, e.g. keywordNaturalExposureScore): the ASIN's exposure on just this one queried keyword.

Parameter Guide

Required Parameter

ParameterTypeDescription
searchKeywordstringThe search keyword to analyze. Translate to the target marketplace's language when applicable. Max 1000 characters.

Optional Parameters

ParameterTypeDefaultDescription
countrystringUSMarketplace code (13 supported — see list below).
asinsstring(none)Comma-separated ASIN filter; if omitted, returns all ASINs appearing under the keyword. Max 1000 chars.
conditionstring(none)Filter by a specific traffic source. Only one value per request. See Condition Filters below.
last7dbooleantrueUse the latest 7 days. When false, the API uses startDate/endDate.
startDatestring—yyyy-MM-dd. Takes effect when last7d=false; if omitted, the system's latest integral week is used.
endDatestring—yyyy-MM-dd, paired with startDate.
sortBystring(default)Sort field. See sortBy section below.
pageNuminteger1Page number for pagination.
pageSizeinteger100Results per page. Min 10, max 100.
descbooleantrueSort in descending order.

Supported Marketplaces

13 marketplaces: US (United States), UK (United Kingdom), DE (Germany), CA (Canada), JP (Japan), FR (France), ES (Spain), IT (Italy), MX (Mexico), AU (Australia), AE (United Arab Emirates), BR (Brazil), SA (Saudi Arabia).

Default marketplace is US. Codes outside this list will be rejected by the API pattern.

Condition Filters

Each request can include at most one condition filter. Flag-style:

ValueMeaning
nfPositionNatural search traffic keywords
isSpAdSP ad keywords
isVedioAdVideo ad keywords
isBrandAdBrand ad keywords
isPPCAdPPC ad keywords (all paid ad types)
isSearchRecommendSearch recommendation keywords
acAdSP recommendation (Trending now / Customers frequently viewed / etc.)

Period-count filters (.total full / .in new-in):

ValueMeaning
totalPeriod.inNewly-entered traffic keywords this period
nfKeywordCnt.total / nfKeywordCnt.inKeywords with (new) organic exposure
adKeywordCnt.total / adKeywordCnt.inKeywords with (new) ad exposure
allSpKeywordCnt.total / allSpKeywordCnt.in(New) SP-ad keywords (regular + recommendation)
spKeywordCnt.total / spKeywordCnt.in(New) SP regular keywords
recSpKeywordCnt.total / recSpKeywordCnt.in(New) SP recommendation keywords
allSbKeywordCnt.total / allSbKeywordCnt.in(New) SB-ad keywords
sbKeywordCnt.total / sbKeywordCnt.in(New) SB regular keywords
sbvKeywordCnt.total / sbvKeywordCnt.in(New) SBV keywords

sortBy

Leave empty for system default. Valid values:

totalKeywordNum (total keyword count), naturalKeywordNum, brandKeywordNum, vedioKeywordNum, acKeywordNum, erKeywordNum, trKeywordNum, sumScore (total exposure across all keywords), totalNfScore, totalSpSocre (note spelling), totalBrandScore, totalVedioScore, totalAcScore, totalTrScore, totalErScore.

调用方式

  • API 端点:POST /sif/keywordSummary(完整参数/响应/错误码见 references/api.md)
  • Python 脚本:python scripts/sif_keyword_traffic.py '<JSON 参数>' [--inline]
  • 成本约束:本工具会消耗算力;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-sif-keyword-summary-<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。

解决认证和算力问题

发生以下异常情况时,采用 references/onboarding.md 引导解决问题:

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
  • 响应提示算力或余额不足:消息含"算力余额不足/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。

Usage Examples

1. Basic keyword traffic overview Query the traffic source breakdown for a keyword in the US marketplace:

searchKeyword: "wireless charger", country: "US"

2. Filter for organic search traffic only See only ASINs that appear in natural search results for a keyword:

searchKeyword: "wireless charger", country: "US", condition: "nfPosition"

3. Analyze SP ad competition Find which ASINs are running SP ads for a keyword:

searchKeyword: "wireless charger", country: "US", condition: "isSpAd"

4. SP recommendation slots Find ASINs surfacing in SP recommendation slots (Trending now, Customers frequently viewed, etc.):

searchKeyword: "wireless charger", country: "US", condition: "acAd"

5. Keyword analysis for a non-US marketplace Analyze traffic sources in the Japan marketplace (use the local language keyword):

searchKeyword: "ワイヤレス充電器", country: "JP"

6. Focus on specific competitor ASINs Limit results to a small set of competing ASINs:

searchKeyword: "wireless charger", country: "US", asins: "B01NBNDC1T,B09VLJJPL6"

7. Custom date range

searchKeyword: "wireless charger", country: "US", last7d: false, startDate: "2026-04-05", endDate: "2026-04-11"

8. Rank ASINs by their overall SP exposure

searchKeyword: "wireless charger", country: "US", sortBy: "totalSpSocre", desc: true

9. Newly-entered traffic keywords this period

searchKeyword: "wireless charger", country: "US", condition: "totalPeriod.in"

Display Rules

  1. Present data clearly: Show query results in well-structured tables. Group data by traffic channel exposure ratios for easy comparison.
  2. Distinguish product-level vs keyword-level scores: Do not mix naturalSearchExposureScore (product-wide) with keywordNaturalExposureScore (this keyword only). Label columns so users know which scope they are reading.
  3. Highlight key ratios: When displaying results, emphasize the natural search exposure ratio vs. paid ad exposure ratio to help users quickly assess the organic-to-paid balance.
  4. Translate field names: Present field names in user-friendly language rather than raw API field names (e.g., "Natural Search Exposure Ratio" instead of "naturalSearchExposureRatio").
  5. Volume notice: When results are large (high total count), show core data and remind users they can paginate to see more results.
  6. Period annotation: When comparing exposure/counts, label the resolved window — default last7d; or startDate ~ endDate if a custom range was set. Also surface dataPeriodStartDate on each row.
  7. Error handling: When a query fails, explain the reason based on the msg field and suggest adjusting query parameters (e.g., checking keyword spelling or marketplace code).
  8. Percentage formatting: Display exposure ratios as percentages (e.g., 0.45 as "45%") for readability.
  9. Traffic source summary: When presenting a single ASIN's data, provide a brief traffic composition summary (e.g., "This product gets 60% of its exposure from organic search, 25% from SP ads, and 15% from brand ads"); prefer keyword-level fields when the user asks specifically about this keyword.

Important Limitations

  • Single condition filter: Only one condition value can be used per request. To compare multiple traffic sources, make separate requests.
  • Marketplace coverage: 13 marketplaces only — IN / NL / SE / PL / TR / SG are no longer available.
  • Keyword language: The searchKeyword should be in the language of the target marketplace for best results.
  • Result cap: Each page returns at most 100 records.
  • Scope: This endpoint focuses on per-keyword ASIN traffic; it does not return whole-ASIN metadata, cross-channel keyword counts, or variant aggregation. Use the ASIN traffic-source tool for those.

User Expression & Scenario Quick Reference

Applicable — Traffic source and competition structure analysis for Amazon keywords:

User SaysScenario
"Where does the traffic come from for this keyword"Traffic source breakdown
"How much organic vs paid traffic"Organic/paid ratio analysis
"Who's running SP ads for this keyword"SP ad competition analysis (condition=isSpAd)
"Which products are in SP recommendation slots"SP recommendation lookup (condition=acAd)
"Which products have Amazon's Choice"AC badge analysis (via amazonsChoiceExposureScore)
"Is this keyword dominated by ads"Ad saturation assessment
"Show me the brand ad competition"Brand ad landscape analysis
"Traffic structure for my competitor's keyword"Competitive traffic analysis
"Which products get editorial recommendations"ER placement analysis
"Compare these 2 ASINs on this keyword"ASIN filter via asins="B0A,B0B"
"For the week of March 8, traffic under this keyword"Custom startDate/endDate window
"Newly-entered traffic keywords this period"New-in filter (condition=totalPeriod.in)

Not applicable — Needs beyond keyword traffic source analysis:

  • Historical keyword ranking trends beyond current + custom window (use ABA data tools)
  • Advertising bid/budget optimization
  • Product reviews or listing content
  • Sales volume estimation
  • Full keyword search volume curve over time
  • Whole-ASIN traffic structure across all keywords (use the SIF ASIN traffic-source tool)

算力消耗规则

消耗 9 算力。

用户会因算力消耗而支付费用。请充分评估:当需要高频调用本技能,或用户对算力消耗量预期不足时,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, set [LinkFox Skills](https://skill.linkfox.com/).

Correlati per attività

dallo stesso repository

Altri Skills

Tutti gli Skills
linkfox-ai
Community

linkfox-aigc-imagegen

AI生图工具,根据提示词和参考图生成图片。支持多种模型(BANANA/BANANA2/BANANAPRO/GPT2IMAGE/AIDRAWEDIT/WAN27/SEEDREAM5),可控制分辨率、宽高比、输出数量。用户说"生成图片"、"AI画图"、"AI生图"、"帮我画"、"图片生成"、"image generation"、"generate image"、"画一张图"、"做张图"、"图生图"时触发。

installazioni
1
GitHub Stars
105
Aggiornato
14 set
linkfox-ai
Community

linkfox-aigc-imagegen-cloth

服饰图生成(模特/服装类)。支持单张或套图:白底图(隐形模特)、模特图、种草图、卖点图、A+图、尺码图。单张单类型直接出图;多张多类型自动编排规划。用户上传模特图或服饰图(上装/下装/连衣裙/外套/鞋帽等)并说"做套图""做模特图""做种草图""做卖点图""做A+图""做尺码图""做服饰白底图"时触发。纯图片编辑操作走 linkfox-aigc-imagegen。

installazioni
1
GitHub Stars
105
Aggiornato
14 set
linkfox-ai
Community

linkfox-aigc-videogen

AI生视频工具(首尾帧/单图模式),根据原图和提示词生成视频,支持可选尾帧图控制结束画面。支持模型KLING可灵/WAN万相/SEED豆包/SEEDFAST/HAILUO海螺。用户说"生成视频"、"AI视频"、"图生视频"、"做个视频"、"video generation"、"generate video"、"图片转视频"、"动态视频"时触发。

installazioni
1
GitHub Stars
105
Aggiornato
14 set
linkfox-ai
Community

linkfox-amazon-ads-auth

亚马逊广告(Amazon Ads)店铺授权与管理技能,提供完整的授权流程、已绑定账号与站点的查询、令牌刷新与读取、当前用户广告授权连接解绑等能力。发起授权链接时需要先向用户确认一个账号名称;一次授权即可自动发现并绑定同账号下所有可用站点的广告 profile(每个站点对应一个 profileId)。当用户提到亚马逊广告授权、Amazon Ads 授权、绑定广告账户、解绑广告账户、断开广告连接、取消广告授权、刷新广告令牌、查询 profile 列表、管理已授权广告账户、Amazon Advertising authorization, Ads token refresh, list profiles, ad account management时触发此技能。即使未明确提及"Amazon Ads"或"授权",只要涉及亚马逊广告账号绑定、访问令牌管理或广告 profile 列表查询,也应触发。

installazioni
1
GitHub Stars
105
Aggiornato
14 set