SkillFoxx

vk-ads-keywords skill

Claude Code skill: collects semantics for VK Ads from real Wordstat via browser, without Direct or paid APIs

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

Extended access

Why this level

  • Measurement runs via scripts in the user’s logged-in Yandex tab; frequent queries may trigger anti-bot protection
  • Competitor brands are added to semantics only with explicit user consent, described as a mandatory rule
All reasons and checks
Russian stack

bratz121/vk-ads-keywords-skillAuthor:bratz121

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/vk-ads-keywords

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

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Measurement runs via scripts in the user’s logged-in Yandex tab; frequent queries may trigger anti-bot protection
  • Competitor brands are added to semantics only with explicit user consent, described as a mandatory rule

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

What it does

Given a single line like “millionaires club, Vladivostok,” the skill generates a brief (audience, city or all Russia, goal, boundaries), searches for similar offers online, selects phrases by categories, and measures real Wordstat frequency. The key method: the entire list is measured with one OR-expression via an internal Wordstat query from a logged-in Chrome tab, not phrase by phrase, supporting up to 22,500 characters in the expression. Each phrase undergoes a double-meaning audit based on actual search results: the skill detects that “French lessons” refers to a TV series, not language courses. It works in Claude Code via the Claude in Chrome extension and in OpenAI Codex, where the agent without a browser provides ready JS for the user to paste into the F12 console.

Who it is for. For marketers preparing VK Ads targeting by keywords who want real frequency data instead of forecasted figures.

Good fit when

  • You need semantics for VK Ads by specific topic and city or all Russia
  • You don’t have access to Yandex Direct or paid word selection services
  • You want to avoid manually analyzing double meanings of phrases; the skill does this automatically based on search results

Not a fit when

  • You need coverage or CPL forecasts rather than Wordstat search demand
  • You cannot log into Yandex in the browser: the agent does not handle captcha or login, only the user can

Example request

Collect semantics for VK Ads: millionaires club, Vladivostok

Limitations

Numbers show the total Wordstat queries over 30 days; VK Ads reach and CPL forecasts do not directly follow. The author notes a practical ratio of about 10,000 VK audience per 15,000 queries without guarantee. Measurement runs from the user’s logged-in tab; the agent does not handle captcha or login. Without a browser agent (regular Codex), the user manually inserts JS into the F12 console and returns results.

How to disable. Delete the ~/.claude/skills/vk-ads-keywords folder or the directory where the Codex copy was cloned.

FAQ

Is Yandex Direct or a paid API required?

No, the skill reads the public page wordstat.yandex.ru through a tab where the user is already logged in.

What if Claude Code has no browser access?

The skill provides ready JS code for the F12 console; the user inserts it manually and returns the results in chat.

Discussion

No questions or reviews yet.

All Yandex Wordstat tools

VK Ads skill for agencies

claude-skill-vk-ads

Russian stack

A Claude Code skill for VK Ads built for agencies: bulk operations, hashed remarketing audiences, ad-marking compliance and Google Sheets reports

SkillBroad access2
Russian stack

A Claude Code skill for the full VK Ads cycle: campaigns, ad groups, banners, statistics, remarketing and lead forms via bash scripts

SkillBroad access2
Russian stack

A Claude Code skill for the full Yandex-focused SEO content cycle, from keywords to AEO, with a Python engine and real Wordstat data

SkillBroad access1
Russian stack

A 10-stage Claude Code pipeline: Wordstat semantics, top-5 competitor analysis, AI cover and illustrations, publishing to WordPress, Dzen and Prisma Blog

SkillExtended access7
Russian stack

Five cache-first shell skills for Direct, Metrika, Webmaster, Wordstat and Search API, with Claude choosing which one to run

SkillBroad access17

README in short

The README details the pipeline: a short brief with defaults, offer research, phrase selection by categories, measurement with one OR-expression, double-meaning audit via search results, and volume expansion in layers to the target. It provides a table of verified runs with phrase and category counts, project file structure, and separate setup instructions for Codex and Claude Code.

README badge

Report a problem