SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillslinkfox-junglescout-keyword-by-keyword

linkfox-junglescout-keyword-by-keyword

Marketing & growth

View repository

Updated 10-15 09:26

About this skill

Jungle Scout — Expand keyword information by keyword (Keyword by Keyword)

This skill expands a seed keyword into a list of related keywords with search volume, trends, PPC bids, ranking difficulty, and other competitive metrics via the Jungle Scout data source, covering 10 Amazon marketplaces.

Core Concepts

The Jungle Scout Keyword by Keyword tool is one of the core tools for Amazon keyword research. Starting from aseed keyword, it mines a large number of related keywords and their competition metrics. Main use cases include:

  • Keyword expansion/discovery: Enter a core term to get hundreds of related keywords and expand your listing keyword library
  • Long-tail keyword mining: Use minWordCount to filter long-tail keywords of 3+ words and discover low-competition, high-conversion opportunities
  • PPC bid research: View exact/broad match PPC bids and Sponsored Brands bids to plan your advertising budget
  • Competition assessment: Use easeOfRankingScore and organicProductCount to determine keyword ranking difficulty
  • Trend analysis: View monthly trends and quarter-over-quarter trend percentage changes to identify growing keywords

Data Fields

Output Fields (keywordInfoList)

Field API Name Description Example
Keyword name Keyword name yoga mat thick
Marketplace country Marketplace code us
Exact search volume monthlySearchVolumeExact Average monthly exact match search volume 45000
Broad search volume monthlySearchVolumeBroad Average monthly broad match search volume 120000
Monthly trend monthlyTrend Month-over-month percentage change in search volume 15.3
Quarterly trend quarterlyTrend Quarter-over-quarter percentage change in search volume -5.2
Main category dominantCategory The category with the highest share in search results Sports & Outdoors
Relevance score relevancyScore Relevance score with the seed keyword 856
Ranking difficulty easeOfRankingScore Ranking ease score (higher means easier) 3
Organic product count organicProductCount Number of organically ranked products in search results 342
Advertised product count sponsoredProductCount Number of advertised products in search results 28
PPC exact bid ppcBidExact Suggested exact match PPC bid (USD) 1.25
PPC broad bid ppcBidBroad Suggested broad match PPC bid (USD) 0.89
Sponsored Brands bid spBrandAdBid Suggested Sponsored Brand ad bid (USD) 2.50
Recommended promotion recommendedPromotions Recommended promotion giveaway quantity 150
Tokens consumed costToken Number of tokens consumed by this call 1

Supported Marketplaces

10 Amazon marketplaces: us (default), uk, de, in, ca, fr, it, es, mx, jp. When the user does not specify a marketplace, use us.

Marketplace marketplace value Description
United States us Amazon.com
United Kingdom uk Amazon.co.uk
Germany de Amazon.de
India in Amazon.in
Canada ca Amazon.ca
France fr Amazon.fr
Italy it Amazon.it
Spain es Amazon.es
Mexico mx Amazon.com.mx
Japan jp Amazon.co.jp

How to call

  • API endpoint：POST /tool-jungle-scout/keywords/by-keyword(For full parameters/responses/error codes, see references/api.md）
  • Python script：python scripts/junglescout_keyword_by_keyword.py '<JSON 参数>' [--inline]
  • Cost constraints: This tool consumes compute; by default, the same parameter combination in the same session is called only once, and the script has a 24h local cache. On failure or empty results, do not automatically try different keywords, paginate, or change the zip code for continuous probing; if further retrieval is needed, first explain to the user that additional consumption will be incurred.

Output strategy (default script behavior)：

  • Alwayswrite the full response to <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-junglescout-keyword-by-keyword-<timestamp>.json（<cwd> is the working directory when the script is executed, which in Claude Code is the current project directory;<session> is taken from the environment variable SESSION_ID, automatically aggregated according to the user task;writing to /tmp is prohibited, and if the current directory is not writable, report an error)
  • Response body ≤ 8 KB: after writing to disk, print the full JSON to stdout
  • Response body > 8 KB: after writing to disk, stdout outputs only a summary (top-level fields, common counts such as total/costToken, the length of the largest list field + the first 3 samples)
  • Add --inline to force full printing to stdout (also written to disk)

Data reading recommendations: first look at the summary to determine whether it is sufficient; when specific fields are needed, prefer to use jqorConvertFrom-Json to extract on demand from the saved json file, avoiding bringing the entire JSON into the context.

Resolve authentication and compute issues

When the following abnormal situations occur, use references/onboarding.md to guide resolution:

Abnormal situations

  • API Key not configured: the environment variable is not configured LINKFOX_AGENT_API_KEY, and LINKFOXAGENT_API_KEY。
  • Response 401 or 402 status code
  • Response indicates insufficient compute or balance: the message contains "insufficient compute balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge", or content with a similar meaning.

How to Build Queries

Required parameters:marketplace、searchTerms(a single seed keyword string).

Principles for Building API Calls

  1. Site mapping: when the user says "US site" → us, "Japan site" → jp, "Germany site" → de; when unspecified, default to us
  2. Seed keyword: pass in the keyword provided by the user as-is (lowercase English is preferred), only a single keyword is supported
  3. Number of results: the default number returned is limited; if the user needs more results, set needCount
  4. Sort selection: by default sorted by exact search volume descending (-monthly_search_volume_exact), switch the sort field according to user intent
  5. Filtering: make full use of the min/max parameter to narrow the result range and avoid returning irrelevant low-quality keywords

Common Query Scenarios

1. Expand seed keywords — get a list of related keywords

{
  "marketplace": "us",
  "searchTerms": "yoga mat"
}

2. Mine long-tail keywords (3+ words)

{
  "marketplace": "us",
  "searchTerms": "yoga mat",
  "minWordCount": 3,
  "needCount": 50
}

3. Low-competition keyword discovery

{
  "marketplace": "us",
  "searchTerms": "yoga mat",
  "maxOrganicProductCount": 200,
  "minMonthlySearchVolumeExact": 1000,
  "sort": "-ease_of_ranking_score"
}

4. High-search-volume keyword filtering

{
  "marketplace": "us",
  "searchTerms": "yoga mat",
  "minMonthlySearchVolumeExact": 10000,
  "sort": "-monthly_search_volume_exact",
  "needCount": 30
}

5. PPC bid research — sort by broad bid

{
  "marketplace": "us",
  "searchTerms": "yoga mat",
  "minMonthlySearchVolumeExact": 500,
  "sort": "ppc_bid_broad",
  "needCount": 30
}

6. Germany site broad search volume keywords

{
  "marketplace": "de",
  "searchTerms": "yogamatte",
  "minMonthlySearchVolumeBroad": 5000,
  "sort": "-monthly_search_volume_broad"
}

Display Rules

  1. Tables preferred: display the keyword list in a table, with core columns including: keyword, exact search volume, broad search volume, monthly trend, PPC exact bid, ranking difficulty
  2. Trim columns as needed: decide which columns to display according to user intent — PPC research scenarios focus on bid columns, keyword expansion scenarios focus on search volume and trend
  3. Trend annotation: Mark positive values in monthly and quarterly trends with an upward arrow ↑, and negative values with a downward arrow ↓
  4. Ranking difficulty interpretation：easeOfRankingScore 1-3 is difficult, 4-6 is medium, 7-10 is easy
  5. Data insights: Provide a brief summary after the table, such as which category high-search-volume terms are concentrated in, the competitive advantage of long-tail terms, etc.
  6. Error handling: When a query fails, explain the reason based on the error response and suggest adjusting parameters

Important Limitations

  • Single call single keyword：searchTerms Only one seed keyword is accepted; multiple keywords must be split into multiple calls
  • Data period: Search volume is a monthly average estimate, not real-time data
  • Site limitation: Only covers 10 Amazon sites, excluding Australia, the Netherlands, etc.
  • Fixed sort fields: Only predefined sort fields are supported; custom combined sorting is not supported

User Expression & Scenario Quick Reference

Applicable — Keyword expansion and competition analysis:

User Says Scenario
"Help me expand this keyword" Seed keyword expansion
"What related keywords does this term have" Related keyword mining
"Find some long-tail keywords" Long-tail keyword filtering (minWordCount ≥ 3)
"What are the low-competition keywords" Low-competition keywords (ranking difficulty + product count filtering)
"What is the PPC bid for this keyword" PPC bid data query
"Related keywords with high search volume" High-search-volume keyword filtering
"What related keywords are there on the German site" Non-US site keyword expansion
"Help me do keyword research" Comprehensive keyword research

Not applicable — Beyond the scope of keyword expansion:

  • Keyword historical search volume trends (requires the keyword-history tool)
  • ABA search term ranking (requires the ABA tool)
  • Product search or listing analysis
  • Keyword data from non-Amazon platforms
  • ASIN reverse keyword lookup

Boundary judgment: When users say "关键词", "拓词", or "关键词研究", if they want to expand a seed keyword into a list of related keywords with metrics, this skill applies. If they want to see a single keyword's historical search volume trend over time, use the keyword-history skill instead.

Computing power consumption rules

Billed by dynamic rules: computing power consumed = actual pages queried × 63.75.

Important: The service of this skill is calculated dynamically by a multiplier and may consume a large amount of computing power at once. The user must be reminded, and the user decides whether to continue.

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.