SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillslinkfox-seerfar-ozon-keyword-mining

linkfox-seerfar-ozon-keyword-mining

Marketing & growth

View repository

Updated 10-15 17:34

About this skill

Seerfar Ozon Keyword Mining

This skill mines Ozon marketplace keywords around a seed keyword in the Seerfar analytics database and filters the discovered terms by rich performance metrics — search volume, 30-day growth, product/seller/competitor counts, average price, relevancy, title density, cart-add conversion, and more. Each mined keyword carries a full market profile (market space, return/cancellation rate, top products, Chinese translation), making it the starting point for Ozon keyword expansion, long-tail discovery, and seed-term opportunity analysis.

Core Concepts

Seed-driven, not market-browse: unlike a market keyword search, this endpoint requires a keyword (the seed) and returns terms related to that seed, each enriched with market metrics. You expand outward from a term you already have in mind.

Relevancy is the mining signal: relevancy scores how closely a mined term relates to the seed (the seed term itself returns at relevancy: 100, related terms rank lower); titleDensity reflects how densely the term appears in product titles. Both are populated on every row — sort by relevancy DESC to keep expansions on-topic.

Platform coverage: each keyword record carries a platform field (0 = Ozon, 1 = Wildberries). The dataset is Ozon-centric; Wildberries rows appear where available. There is no input to restrict the platform — filter client-side if needed.

Match mode: matchType controls how the seed keyword (and includeKeywords) are matched — 0 exact, 1 fuzzy. Choose fuzzy to broaden the expansion, exact to stay tight.

No date or category selectors: this endpoint does not accept searchDate or categories. If you need month-over-month or category-scoped browsing, use the market keyword search skill instead.

Parameters

Parameter Type Required Description
keyword string yes Seed keyword; mining expands around it (maxLength 1000).
page object yes Pagination {page, pageSize, orders[]}. page from 1 (default 1), pageSize default 20. orders[] = {field, direction} with direction DESC/ASC.
matchType integer no Keyword match mode: 0 exact, 1 fuzzy.
includeKeywords array no Terms that must appear (max 1000); narrows the expansion.
excludeKeywords array no Terms to exclude (max 1000); removes irrelevant expansions.
wordCount {min,max} no Keyword word/char count range.
searchVolume {min,max} no Monthly search volume range.
searchChange30 {min,max} no 30-day search change range.
productViews {min,max} no Product view range.
products {min,max} no Product count range.
sellers {min,max} no Seller count range.
price {min,max} no Average price range.
marketSpace {min,max} no Market space range.
conversionSharing {min,max} no Conversion concentration range.
relevancy {min,max} no Relevancy-to-seed range.
uniqQueriesWCa {min,max} no Cart-add count range.
ca {min,max} no Cart-add conversion rate range.
titleDensity {min,max} no Title density range.
adRivalCount {min,max} no Ad competitor count range.
uId string no User ID.
memberId string no Member ID (data attribution).

All range filters are {min, max} objects; supply either or both bounds. keyword and page are both required.

How to call

  • API endpoint：POST /seerfar/ozon/keywordMining(for full parameters/response/error codes see references/api.md）
  • Python script：python scripts/seerfar_ozon_keyword_mining.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/empty results, do not automatically switch keywords, turn pages, or change zip codes to probe continuously; if you need to continue searching, first explain to the user that additional consumption will be incurred.

Output strategy (script default behavior)：

  • Alwayswrite the full response to <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-seerfar-ozon-keyword-mining-<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 suggestions: first look at the summary to judge whether it is sufficient; when specific fields are needed, prefer to use jqorConvertFrom-Json to extract on demand from the saved json file, avoiding putting the entire JSON into the context.

Resolve authentication and compute issues

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

Usage Examples

1. Expand around a seed term (sort by search volume)

{"keyword": "платье", "page": {"page": 1, "pageSize": 10, "orders": [{"field": "searchVolume", "direction": "DESC"}]}}

2. Blue-ocean expansions — high volume, few sellers

{"keyword": "телефон", "page": {"page": 1, "pageSize": 20, "orders": [{"field": "searchVolume", "direction": "DESC"}]}, "searchVolume": {"min": 10000}, "sellers": {"max": 50}}

3. Keep expansions on-topic with relevancy + title density

{"keyword": "наушники", "page": {"page": 1, "pageSize": 20, "orders": [{"field": "relevancy", "direction": "DESC"}]}, "relevancy": {"min": 50}}

4. Narrow with include / exclude lists

{"keyword": "часы", "page": {"page": 1, "pageSize": 20}, "includeKeywords": ["женские"], "excludeKeywords": ["ремень"], "matchType": 1}

How to Build Queries

  1. Always lead with the seed keyword: it is required and defines the expansion center. Pass it in Russian for Ozon.
  2. Lead with page.orders: sort by the metric you care about (searchVolume DESC for popularity, relevancy DESC for on-topic, sellers ASC for low competition).
  3. Stack range filters to find opportunities: combine a high searchVolume floor with a low sellers ceiling to surface blue-ocean expansions; add relevancy / titleDensity bounds to keep them relevant to the seed.
  4. Use includeKeywords / excludeKeywords to steer the expansion: force in must-have modifiers and strip noise without running a second query.

Display Rules

  1. Present data only: show mined-keyword metrics in a clear table without subjective advice.
  2. Lead with keyword columns: query / queryCn (Chinese translation), then searchVolume, count30GrowthRate, productCount, sellers, avgPrice; show relevancy to convey closeness to the seed (the seed term itself is 100).
  3. Russian keywords: preserve the original query; the queryCn field provides a Chinese translation when available.
  4. Platform tag: when both Ozon and Wildberries rows are present, show platform (0/1) so the user can distinguish them.
  5. Large result sets: when total is large, show the top rows and remind the user they can persist the full response via the large-response pattern below, or page further with page.page.
  6. Error handling: when code is not 200 (or errcode is not 200), explain the reason from msg / errmsg and suggest adjusting the seed keyword or filters.

Important Limitations

  • keyword + page required: a payload missing either is rejected.
  • No date selector: there is no searchDate; you cannot pick a data month here. Use the market keyword search skill for month-scoped data.
  • No category selector: categories is not accepted as input; each returned keyword carries a categories ID array you can group or filter client-side.
  • dimension / categoryInfos not returned: both are defined in the schema and appear as columns, but real data[*] rows do not populate them on this endpoint. (categoryInfos IS populated on the sibling market-keyword-search endpoint — don't assume parity.)
  • Nested fields: products[*] (Top products) is structured and decision-useful — see references/api.md for sub-fields. (categoryInfos[*] is documented there for schema completeness but is not returned on this endpoint; dimension / columns are opaque or partially populated.)

User Expression & Scenario Quick Reference

Applicable — seed-driven Ozon keyword expansion:

User Says Scenario
"mine Ozon related words around the XX word" Seed-keyword expansion
"Ozon long-tail keyword mining / expand the long tail of a word" Long-tail mining around a seed
"blue-ocean expansion words for an Ozon word, low competition and high search" Blue-ocean expansion (high volume, few sellers)
"what words related to XX are there on Ozon, highly relevant ones" Relevancy-ranked expansion
"expand a certain Ozon word, but exclude/must include certain words" Include/exclude steered expansion

Not applicable — Needs beyond seed-driven keyword mining:

  • Browse/rank the whole market's hot keywords without a seed → use the Seerfar Ozon market keyword search skill.
  • A specific SKU's price/sales/stock → use a product-level Seerfar Ozon data source.
  • A specific seller's catalog → use a seller/shop-level Seerfar Ozon data source.
  • Month-over-month or category-scoped keyword browsing → use the market keyword search skill (supports searchDate / categories).

Boundary judgment: if the user wants to expand outward from a seed term and rank the related terms by market metrics, start here. If they want to browse the whole market of keywords (no seed) or scope by month/category, route to the market keyword search skill.

Compute consumption rules

Consumes 23 compute.

Users pay fees due to compute consumption. Please fully assess: when this skill needs to be called frequently, or the user's expectation of compute consumption is insufficient, be sure to remind the user and let the user decide 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, set LinkFox Skills.