Yandex Metrika Assistant skill
An OpenClaw agent skill: a reference for the Yandex Metrika API and rules for picking the right report, Logs call and OAuth token
- 0 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The OAuth token can carry write scopes (expense import, CRM orders) depending on what was granted
- The skill drafts curl commands that the agent executes on the user's behalf
russkih75-ctrl/yandex-metrika-assistant
A similar tool with a larger community: Yandex Metrika Assistant, 16 ★ on the repository
Install
- Works in
- Services
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/russkih75-ctrl-yandex-metrika-assistantDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The OAuth token can carry write scopes (expense import, CRM orders) depending on what was granted
- The skill drafts curl commands that the agent executes on the user's behalf
This is third-party code. Review the repository files before installing.
What it does
SKILL.md tells the OpenClaw agent how to answer questions about Yandex Metrika: not to confuse the ym:s: and ym:pv: namespaces, to read the token only from the plugin config or an environment variable, and never print it in chat. The docs folder mirrors the official API sections: Stat reports, Logs export, expense and CRM import, counter and goal management, getting an OAuth token. A separate file maps common user phrasing like traffic sources or period comparison to concrete request parameters.
Who it is for. For site owners and marketers on OpenClaw who want to ask an agent about Metrika data in plain language.
Good fit when
- Your agent runs on OpenClaw and needs a reference for Metrika endpoints
- You need a mapping from plain user phrasing to Stat API and Logs API parameters
- You need a Russian walkthrough for getting an OAuth token
Not a fit when
- Your agent is not OpenClaw: SKILL.md targets its manifest format and {baseDir} paths
- You need a ready MCP server with callable tools rather than a text skill
Example request
Show daily visits for the last month and a traffic sources summaryLimitations
The skill does not call the API itself, only guides the agent to the right requests and curl examples: the agent must be able to make HTTP calls. The SKILL.md format and plugin config target OpenClaw; other agents would need adaptation. The OAuth token needs metrika:read scope, plus metrika:write for data import.
How to disable. Disable the yandex-metrika-assistant plugin in OpenClaw or remove the skill folder from skills.
FAQ
Do I need a separate OAuth token?
Yes, a Yandex token with metrika:read scope obtained via oauth.yandex.ru; a Russian walkthrough is in docs/INSTRUCTION-GET-TOKEN-RU.md.
Does it work with Claude Code or Cursor?
The skill targets OpenClaw's SKILL.md format and plugin manifest; other agents would need their own adaptation.
Discussion
No questions or reviews yet.
Related
All Yandex Metrica toolsA skill and condensed Yandex Metrika API documentation for an agent: reports, Logs API, counter management, OAuth without leaking the token into chat
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 Claude Code skill for Yandex Metrica built on bash scripts over curl: preset reports, goals, counters and raw log exports
Yandex Metrika Core: shared client for skills
Yandex Metrika Core
A shared PHP OAuth and API client for Yandex Metrika that the author's separate OpenCode skills are built on
Yandex Metrica MCP
yandex-metrica-mcp
Read-only MCP server for Yandex Metrica: reports, period comparison, goals and raw log export with browser login
Yandex Metrika skill plugin wrapper
claude-skill-yandex-metrika
A Claude Code plugin bundling a Yandex Metrika skill: traffic, conversions, UTM, search engines and Direct costs, with caching
README in short
The README presents the repository as an OpenClaw skill plus a condensed reference for the official Metrika API: OAuth, quotas, reports, Logs, import, management. It shows a table matching OpenClaw's manifest requirements, a quick-start diagram and a table of user-question to agent-action scenarios. Author Andrey Ruskikh offers support via Telegram and Instagram.
README badge
Original SKILL.md
---
name: yandex-metrika-assistant
description: "OpenClaw + Яндекс.Метрика API, stat/Logs/management, OAuth, presets, UTM, цели, CSV, квоты; плагин yandex-metrika-assistant. Автор: Андрей Русских (wordprais.ru)."
homepage: "https://github.com/russkih75-ctrl/yandex-metrika-assistant"
---
# Яндекс.Метрика API, заточка под OpenClaw
Автор навыка: Андрей Русских, сайт wordprais.ru (WordPress), Telegram @wordprais, Instagram.
Плагин: yandex-metrika-assistant (openclaw.plugin.json в этой папке).
Цель: ноль сюрпризов, сначала конфиг и секреты, потом правильный endpoint, без выдуманных метрик и без утечки токена.
## Онбординг человека (порядок ответов агента)
Если токена еще нет (пользователь только ставит навык или не настроил ключ):
1. Сначала дай ссылку и краткое резюме установки: {baseDir}/docs/INSTALL-FOR-HUMANS-RU.md.
2. Обязательно перечисли, какие галочки в приложении Яндекс OAuth нужны для Метрики.
3. Укажи каналы поддержки автора.
4. Затем, получение токена: {baseDir}/docs/INSTRUCTION-GET-TOKEN-RU.md.
5. Напомни: ключ хранить в oauthToken плагина или в YANDEX_METRIKA_OAUTH_TOKEN, не в чате.