← Back to Skills Marketplace
yandex-metrika-assistant
by
Artur Horosheff
· GitHub ↗
· v1.0.0
· MIT-0
154
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install yandex-metrika-assistant
Description
OpenClaw + Яндекс.Метрика API — stat/Logs/management, OAuth, presets, UTM, цели, CSV, квоты; плагин yandex-metrika-assistant.
Usage Guidance
This skill appears to do exactly what it says: call Yandex.Metrika APIs and help with OAuth and report generation. Before installing: (1) confirm you only grant the OAuth scopes you actually need (if you only need read access avoid requesting metrika:write), (2) store the access token in OpenClaw secrets or YANDEX_METRIKA_OAUTH_TOKEN rather than pasting it in chat, (3) review the referenced GitHub repo (scripts like the OAuth exchange) if you plan to run them, and (4) remember the implicit flow (response_type=token) returns tokens in the browser URL fragment — for server integrations prefer the authorization-code flow with refresh tokens/secret. If you want further assurance, check the upstream GitHub repo history and the optional scripts mentioned in docs before running any of them.
Capability Analysis
Type: OpenClaw Skill
Name: yandex-metrika-assistant
Version: 1.0.0
The yandex-metrika-assistant bundle is a legitimate tool designed to help an AI agent interact with the Yandex Metrika API. The SKILL.md and documentation files (such as docs/INSTRUCTION-GET-TOKEN-RU.md and docs/OPENCLAW-AGENT.md) contain clear, defensive instructions that prioritize security, specifically directing the agent to use environment variables for OAuth tokens and explicitly forbidding the agent from echoing sensitive credentials in chat responses. No evidence of data exfiltration, malicious command execution, or harmful prompt injection was found; the provided PowerShell and curl examples are transparent and aligned with the stated purpose of fetching analytics data.
Capability Assessment
Purpose & Capability
Name/description (Yandex.Metrika assistant) match the content: docs describe management, reports, Logs API, imports and OAuth; the only sensitive thing is an OAuth token which the plugin schema exposes as an optional config field. Nothing in the package requests unrelated services or credentials.
Instruction Scope
SKILL.md is detailed and instructs the agent to only use the token from plugin config, YANDEX_METRIKA_OAUTH_TOKEN, or a one‑time user-provided token, and explicitly forbids echoing or committing tokens. All example API endpoints are the official api-metrika.yandex.net. Minor note: the docs recommend the implicit OAuth flow (response_type=token) which exposes tokens in the browser fragment — acceptable for client flows but less ideal for long‑lived server use; the docs do mention the authorization‑code flow for server scenarios.
Install Mechanism
Instruction-only skill: no install spec, no downloads or binaries. All files are docs and openclaw plugin metadata; no executable code is included in the package to write/execute on host.
Credentials
No required env vars declared by registry metadata. The plugin exposes an optional oauthToken and optional oauthClientId/defaultCounterId in its configSchema — proportional for a metrics integration. The SKILL.md consistently limits where tokens come from and discourages pasting tokens into chat or repos.
Persistence & Privilege
always:false and no requests to modify other skills or system settings. The plugin expects to store its own oauthToken in its config (normal). Autonomous invocation is allowed by platform default but is not combined with other red flags here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install yandex-metrika-assistant - After installation, invoke the skill by name or use
/yandex-metrika-assistant - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the Yandex.Metrika Assistant skill for OpenClaw:
- Provides step-by-step user onboarding for connecting the Yandex.Metrika API via OAuth.
- Details strict token handling and secure workflows (never expose or echo actual tokens).
- Outlines plugin usage patterns: default counter selection, API endpoints, and user guidance.
- Includes quick PowerShell (Windows) examples for typical API tasks (counters, visits, reports).
- Covers common user intents, troubleshooting quotas, and how responses should be formatted for end users.
Metadata
Frequently Asked Questions
What is yandex-metrika-assistant?
OpenClaw + Яндекс.Метрика API — stat/Logs/management, OAuth, presets, UTM, цели, CSV, квоты; плагин yandex-metrika-assistant. It is an AI Agent Skill for Claude Code / OpenClaw, with 154 downloads so far.
How do I install yandex-metrika-assistant?
Run "/install yandex-metrika-assistant" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is yandex-metrika-assistant free?
Yes, yandex-metrika-assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does yandex-metrika-assistant support?
yandex-metrika-assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created yandex-metrika-assistant?
It is built and maintained by Artur Horosheff (@horosheff); the current version is v1.0.0.
More Skills