Eight calculation skills for WB and Ozon sellers

mikhail-marketplace-skills

A SKILL.md bundle of calculation skills for marketplace sellers: ads, finance, unit economics, warehouses, a profit report, posts and certificate checks

  • 0 ★ on the repository
  • Last commit
  • MIT
Skill

Minimal access

Why this level

  • Only calculates from figures and files the user provides, no access to platform accounts
All reasons and checks
Russian stack

ganzhamihail-jpg/mikhail-marketplace-skills

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/mikhail-marketplace-skills

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • Only calculates from figures and files the user provides, no access to platform accounts

This is third-party code. Review the repository files before installing.

What it does

Eight skills cover specific seller tasks: a Wildberries ad audit with ad-cost ratio and bid analysis, financial report reconciliation and a profit bridge, per-SKU unit economics with a break-even price and maximum ad-cost ratio, warehouse restocking and rebalancing, a weekly management profit report, Telegram post generation, lessons and exercises for training managers, and certificate and document-binding validation. Each skill takes numbers directly in the request (price, commission, logistics, cost) and calculates from them, rather than inventing missing metrics or platform rates.

Who it is for. For Wildberries and Ozon sellers who want quick calculations from their own numbers instead of manual Excel formulas.

Good fit when

  • You need to quickly compute unit economics, break-even price or maximum ad-cost ratio from your own figures
  • You need a weekly profit report or a WB ad campaign breakdown
  • You need a batch certificate check or a Telegram post for customers

Not a fit when

  • You need automatic data pulled from a seller cabinet: the skills work with numbers you supply yourself
  • You need Seller API integration: this bundle has none
  • The SkillKit installer doesn't fit: it needs Node.js 18 and npx

Example request

Use unit-economics: price 1990 rubles, commission 24%, logistics 145 rubles, cost 620 rubles, ads 180 rubles, tax 6%

Limitations

None of the skills connect to a marketplace Seller API: every calculation runs on numbers and files the user supplies in the request. Installation is built around SkillKit (npx skillkit) or manual copying, and the skill explicitly asks to verify current rates and platform requirements against primary sources rather than trust its own memory.

How to disable. Delete the relevant folder from skills/ in your agent's skills directory, or reinstall the bundle via npx skillkit@latest install without the unwanted skills.

FAQ

Do the skills pull data from a WB or Ozon cabinet themselves?

No, every calculation uses figures you supply in the request, the skills have no Seller API access.

Can I install just one skill?

Yes, npx skillkit@latest install supports a --skill flag with the names of the skills you need instead of the whole bundle.

Discussion

No questions or reviews yet.

Russian stack

A large library of 169 skills for marketing, marketplaces, analytics, operations and legal tasks, including dedicated Wildberries and Ozon skills

SkillMinimal access1Repository stars
Russian stack

An OpenClaw skill that tracks orders, prices and stock on Ozon, Wildberries and Yandex Market from one interface

SkillBroad access10Repository stars
Russian stack

An Agent Skill for Claude Code and Codex that writes a Russian listing title and description from product photos and keyword screenshots, per WB and OZON rules

SkillExtended access1Repository stars

README in short

The README lists the eight skills in a table, describes the layout (SKILL.md plus agents/openai.yaml per skill), installation via SkillKit as a whole set, by selected skills, or locally during development, gives test prompts for each skill, and states safety principles: never invent metrics, verify rates against primary sources, keep tokens out of the repository, and dry-run before a bulk upload.

README badge

Report a problem