SkillFoxx

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

  • 1 ★ on the repository
  • Last commit
Skill

Broad access

Why this level

  • The Direct skill supports add, update, delete, suspend, resume and moderate methods, so it can change ad campaigns directly
All reasons and checks
Russian stack

bobidk91-ops/yandex-direct-openclaw-skillAuthor:bobidk91-ops

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/openclaw-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

Broad accessThe tool can change data, run commands or handle secrets.

  • The Direct skill supports add, update, delete, suspend, resume and moderate methods, so it can change ad campaigns directly

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

What it does

The repository holds three separate SKILL.md files with YAML frontmatter: yandex_direct for API v5 and v501 methods (add, update, get, delete, suspend, resume, moderate, reports), yandex_metrika for stat reports, counter and goal management, and the Logs API, and yandex_wordstat for top queries, demand dynamics, regions and associations. Each skill documents its own host and auth type (Bearer for Direct and Wordstat, OAuth for Metrica) and explicitly forbids printing the token to logs or replies. Direct also ships materials for applying for API access.

Who it is for. For marketers and developers who want an agent's direct access to three Yandex ad APIs without a separate MCP server for each.

Good fit when

  • You want access to Direct, Metrica and Wordstat all from one skill set
  • You are fine calling JSON API methods directly without an MCP wrapper

Not a fit when

  • You want a ready-made MCP server rather than an API reference for the agent to call directly
  • You are not using OpenClaw and your agent does not support the SKILL.md format

Example request

Get the top queries for a phrase via Wordstat and compare them with Metrica's impression dynamics for the month

Limitations

The repository has no README, only the SKILL.md files themselves. The project is maintained by one author, with 1 star. The Direct API application materials target a specific application form; their current relevance should be checked independently.

How to disable. Delete the skill folders from your agent's skills directory and revoke the issued Direct, Metrica and Wordstat tokens.

FAQ

How does Metrica's auth differ from Direct's?

Metrica uses an Authorization: OAuth header and GET requests for stats, while Direct and Wordstat use Bearer auth and POST requests with a JSON body.

Discussion

No questions or reviews yet.

All Yandex Direct tools
Russian stack

A skill and condensed Yandex Metrika API documentation for an agent: reports, Logs API, counter management, OAuth without leaking the token into chat

SkillExtended access16
Russian stack

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

SkillBroad access17
Russian stack

A skill for auditing and running Yandex Direct campaigns via API v5: 55 checks, an A-F grade, ad creation and reports

SkillBroad access64
Russian stack

An Agent Skill for full Yandex Direct audit, optimization and API v5 work: search, the ad network, Unified Performance, strategies and attribution

SkillBroad access1

Yandex Direct skill with CPA optimization

Yandex.Direct Skill для Claude Code

Russian stack

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

SkillBroad access5

Yandex Direct statistics skill

ya-direct-statistics

Russian stack

A Codex skill for building and reading Yandex Direct reports: Report Wizard, the report library, filters, attribution and safe browser workflows

SkillExtended access1

README in short

There is no separate README. Each of the three SKILL.md files has a frontmatter with a description, the required environment variables, and a link to the official docs, plus in the body: token safety rules, the base URL, the auth method, and a table of API methods with quotas where applicable.

README badge

Original SKILL.md

---
name: yandex_direct
description: Call Yandex Direct API v5/v501 JSON methods (add/update/get/delete/suspend/resume/moderate/reports) using an OAuth access token. Use when the user wants to manage campaigns, ads, keywords, bids, or generate reports via Yandex Direct.
metadata: {"openclaw":{"requires":{"env":["YANDEX_DIRECT_TOKEN","YANDEX_DIRECT_LOGIN"]},"primaryEnv":"YANDEX_DIRECT_TOKEN","emoji":"target"}}
homepage: https://yandex.ru/dev/direct/doc/en/concepts/overview
---

# Yandex Direct (API v5 / v501)

## Core idea (covers "all possible calls")

Yandex Direct method calls all share the same HTTP wrapper:

1. Pick a service (the path segment in the URL)
2. Pick a method (string, e.g. add, update, get, delete, suspend, resume, moderate, etc.)
3. Send POST JSON body { "method": "...", "params": { ... } }

## Safety requirements

- Never print or echo YANDEX_DIRECT_TOKEN (or any token/private secrets) into logs, tool output, or final answers.
- Only call Yandex Direct JSON endpoints on api.direct.yandex.com (production) or api-sandbox.direct.yandex.ru (sandbox).

Report a problem