Claude Yandex Skills
Five cache-first shell skills for Direct, Metrika, Webmaster, Wordstat and Search API, with Claude choosing which one to run
- 17 ★ on the repository
- Last commit
Broad access
Why this level
- The yandex-direct skill creates and changes real campaigns and bids, spending budget
- The other skills read site and traffic data, but the tokens grant broad account access
Install
- Works in
- Services
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/mkultraaaa-claude-yandex-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The yandex-direct skill creates and changes real campaigns and bids, spending budget
- The other skills read site and traffic data, but the tokens grant broad account access
This is third-party code. Review the repository files before installing.
What it does
The repository bundles five independent Claude Code skills for Yandex services. yandex-direct creates and runs campaigns, bids and ads via API v5. yandex-metrika returns traffic, conversions, funnels, UTM reports and search query data. yandex-webmaster handles indexing, sitemaps, page recrawls and site diagnostics. yandex-wordstat analyzes demand, frequency and seasonality of search terms. yandex-search-api scrapes Yandex search results through the Yandex Cloud Search API v2 in sync and async modes. Each skill is a SKILL.md with triggers, shell scripts on top of curl and jq, endpoint reference docs, and a config folder with an environment variable template. Every script caches repeated requests locally to save context and money on identical calls.
Who it is for. For marketers and SEO specialists who want one skill bundle covering all the main Yandex services at once.
Good fit when
- You want Direct, Metrika, Webmaster, Wordstat and search results together in one skill set
- You care about not wasting extra context on repeated requests: the scripts cache results
- You want ready Russian-language endpoint reference docs for each API
Not a fit when
- You only need one of the five services: a dedicated single-purpose skill is simpler
- Your agent environment lacks bash, curl and jq: the scripts require them directly
Example request
Check Wordstat demand for "нейросеть без vpn" across Russian regionsLimitations
Each service needs its own OAuth token or service account: Direct, Metrika and Webmaster via oauth.yandex.ru, Wordstat via Yandex Direct's access moderation, Search API via a Yandex Cloud service account with a JSON key. You need bash, curl and jq, plus Python 3 for Search API's JWT signing. The skills were written by one author for personal use, with no formal tests or releases.
How to disable. Delete the relevant skill folder (for example yandex-direct) from ~/.claude/skills/ or your project's .claude/skills/.
FAQ
How does Claude pick the right skill?
By matching the request against each skill's SKILL.md description; it triggers automatically without an explicit name.
Where are tokens stored?
Only locally in each skill's config/.env, which is gitignored and never committed.
Discussion
No questions or reviews yet.
Related
All Yandex Direct toolsA Claude Code skill for Yandex Metrica built on bash scripts over curl: preset reports, goals, counters and raw log exports
Yandex Direct skill with CPA optimization
Yandex.Direct Skill для Claude Code
A dependency-free Python skill that builds Direct campaigns from a blueprint, pulls leads from Metrika and optimizes bids toward a target CPA or ROI
Yandex Direct, Metrica and Wordstat skill
openclaw-skills
Three Agent Skills in one repository: calling the Yandex Direct, Metrica and Wordstat APIs directly via JSON
A marketplace of 22 Claude Code plugins: Yandex Direct, Metrika, Webmaster, Wordstat, SEO crawling, publishing and research
End-to-end Yandex Direct audit skill
ya-direct-codex
An Agent Skill for full Yandex Direct audit, optimization and API v5 work: search, the ad network, Unified Performance, strategies and attribution
A skill for auditing and running Yandex Direct campaigns via API v5: 55 checks, an A-F grade, ad creation and reports
README in short
The README lists the five skills in a table with their purpose and scenarios, describes the cache-first approach for saving context, covers installation by cloning into the Claude Code skills directory, getting tokens for each service, example phrases that trigger each skill, a shared skill folder layout (SKILL.md, config, references, scripts), and requirements: bash, curl, jq, Python 3 for Search API. A separate security section covers local-only tokens and gitignored cache and secrets.