Data-driven Wildberries card audit

Audit WB Product Cards

An evidence-based Wildberries card audit skill: live search results, direct competitors, reviews and a measurement plan instead of generic advice

Skill

Low risk

We rate an entry low when it mostly gives the agent instructions and reference material.

Why this level

  • It only reads public search results and prepares recommendations, it does not change the card
All reasons and checks
Russian stack

anvio13/wb-card-audit-skill

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/audit-wb-product-cards

Detects the agents on your machine, checks the risk and pins the version.

Other ways to install

Run in a terminal in the project folder

npx skills add anvio13/wb-card-audit-skill --skill audit-wb-product-cards -a claude-code -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Run in a terminal in the project folder

npx skills add anvio13/wb-card-audit-skill --skill audit-wb-product-cards -a cursor -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Run in a terminal in the project folder

npx skills add anvio13/wb-card-audit-skill --skill audit-wb-product-cards -a github-copilot -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Run in a terminal in the project folder

npx skills add anvio13/wb-card-audit-skill --skill audit-wb-product-cards -a codex -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Run in a terminal in the project folder

npx skills add anvio13/wb-card-audit-skill --skill audit-wb-product-cards -a gemini-cli -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Run in a terminal in the project folder

npx skills add anvio13/wb-card-audit-skill --skill audit-wb-product-cards -a cline -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Run in a terminal in the project folder

npx skills add anvio13/wb-card-audit-skill --skill audit-wb-product-cards -a roo -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

A fork of Roo Code, same .roo folders.

Run in a terminal in the project folder

npx skills add anvio13/wb-card-audit-skill --skill audit-wb-product-cards -a opencode -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

You will need: Node.js

Checked against the repository on Sep 25, 2026, commit 9725c11.

Text for your agent

Copy the audit-wb-product-cards folder into your agent's skills directory, for Codex the default is ~/.codex/skills/audit-wb-product-cards/, then call the skill explicitly with $audit-wb-product-cards.

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

What it does

The skill audits a Wildberries card in a fixed order: it builds a query map, captures the live top-20 search results and tries to locate the card down to the top-100, and picks at least five direct competitors, kept separate from adjacent and premium ones, before writing any recommendations. Recommendations are blocked by an anti-hallucination gate until queries, search results and competitors are collected. The report splits problems into visibility, offer, content risk and operations, separately flags what already works and should not change without a test, turns recent reviews into purchase reasons, defects and objections, and on request produces new copy, attributes and a first-image scenario. It ends by suggesting a controlled experiment checked at 14 and 21-28 days, changing one variable at a time.

Who it is for. For Wildberries sellers and SEO specialists who want a card audit grounded in real search data, not a generic checklist.

Good fit when

  • You want to understand why a card is losing position against real competitors
  • You want a fix plan with priority, risk and a way to measure the result
  • You want customer reviews turned into concrete themes and objections

Not a fit when

  • You have no access to the live Wildberries storefront: without it the skill honestly lowers confidence instead of inventing data
  • You need the card actually changed: the skill only prepares recommendations and copy

Example request

Use audit-wb-product-cards to audit the card at https://www.wildberries.ru/catalog/156678435/detail.aspx for the Moscow region

Limitations

A full audit needs access to the live Wildberries storefront, and region, login state, ads, personalization, stock and delivery can all change the results shown. Without seller-dashboard data the skill can only estimate conversion risk, not actual conversion. No license is stated.

How to disable. Remove the audit-wb-product-cards folder from your agent's skills directory.

Security check

  • It only reads public search results and prepares recommendations, it does not change the card

README in short

The README compares a plain prompt with the skill in a table, lists nine features such as anti-hallucination gates and protecting what already works, gives an example request, the file structure, install by copying into the Codex skills directory, and an honest limitations section about depending on the live storefront.

SKILL.md

---
name: audit-wb-product-cards
description: Аудитирует карточки Wildberries через живую выдачу и прямых конкурентов. Использовать для проверки SEO, контента, характеристик, позиций и конверсионных рисков конкретных карточек WB.
---

# Аудит карточек Wildberries

## Результат

Проводит доказательный аудит одной или нескольких карточек Wildberries и показывает: как карточка представлена сейчас, по каким запросам и на каких позициях она находится, с какими прямыми конкурентами ее реально сравнивает покупатель, где подтвержденные разрывы в цене, предложении, SEO и контенте, что сохранить, исправить, проверить и не менять без теста, как измерить эффект изменений.

Порядок: карточка, запросы, выдача, прямые конкуренты, сравнение, отзывы, диагноз, рекомендации, эксперимент. Рекомендации не формируются до завершения конкурентного анализа.

## Обязательные ограничения

- Всегда фиксировать дату, регион, валюту, сортировку, состояние авторизации и способ получения данных.
- Не называть единичный снимок выдачи постоянной позицией.
- Не выдавать рекламную позицию за органическую.

FAQ

Can the skill give recommendations without real search data?

No, an anti-hallucination gate blocks recommendations until queries, live search results and at least five direct competitors are collected.

Does the skill change the card itself?

No, it prepares copy, attributes and a fix plan; the user or another tool applies them.

Official

Official DataLens (Yandex) skills for Claude Code, Codex and OpenCode: SDK, HTML reports and RLS resolution

SkillMedium riskRussian stackNo VPN needed12Repository stars
Editors’ pick

A Yandex Metrika MCP server generated from the API spec: 108 methods, 10 tools declared by default, transparent filters and response metadata

MCP serverMedium riskRussian stackNo VPN needed2Repository stars
Official

An open MCP server and agent skill set for SEO: keyword research, competitors, backlinks and site audits powered by DataForSEO

MCP serverMedium risk21.5KRepository stars

A Claude Code plugin for SEO audits: technical SEO, E-E-A-T, schema, local and AI search via parallel subagents

PluginHigh risk17.9KRepository stars
Foxx AIData-driven Wildberries card audit

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.