direct-eda

direct-eda is a skill for Claude Code from nikolaymokh-dev/yandex-direct-mcp. It costs 106 tokens per session (2,163 once invoked), scanned A, a copy of direct-eda, MIT.

An exploratory analysis guide for Yandex Direct advertising reports. Yandex Direct is an online advertising platform, and exploratory analysis means examining data to find trends, differences, and unusual results.

In plain words
What is it for?
Use it to analyse campaigns by time, device, location, gender, or age; compare campaigns, keywords, or ads; find top and weak performers; and assess measures such as click-through rate, conversion rate, and cost per acquisition.
Why use it?
It helps choose the right report, fields, filters, and breakdowns instead of querying advertising data blindly.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the yandex-direct plugin — 3 skills, 1 hook, 1 MCP server shipped together

Good fit Use it to analyse campaigns by time, device, location, gender, or age; compare campaigns, keywords, or ads; find top and weak performers; and assess measures such as click-through rate, conversion rate, and cost per acquisition.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nikolaymokh-dev/yandex-direct-mcp/direct-eda
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add nikolaymokh-dev/yandex-direct-mcp --skill direct-eda
Clone the repo
git clone --depth 1 https://github.com/nikolaymokh-dev/yandex-direct-mcp

Made for: Claude Code.

Or install yandex-direct, the plugin that ships this one along with the rest of its 3 skills, 1 hook, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for direct-eda

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikolaymokh-dev/yandex-direct-mcp/direct-eda/github.svg)](https://agentmods.dev/skills/nikolaymokh-dev/yandex-direct-mcp/direct-eda)
Your own site
<a href="https://agentmods.dev/skills/nikolaymokh-dev/yandex-direct-mcp/direct-eda"><img src="https://agentmods.dev/badge/skills/nikolaymokh-dev/yandex-direct-mcp/direct-eda/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for direct-eda

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikolaymokh-dev/yandex-direct-mcp/direct-eda"><img src="https://agentmods.dev/badge/skills/nikolaymokh-dev/yandex-direct-mcp/direct-eda.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,163 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.02163
Opus 5 $0.00053 $0.01081
Sonnet 5 $0.00021 $0.00433
Haiku 4.5 $0.00011 $0.00216

Measured 10d ago against content hash 090f0697254e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

direct-eda scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to direct-eda — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/direct-eda/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Разведочный анализ статистики Яндекс.Директ (EDA)

Скилл для исследования статистики кампаний через отчётные MCP-инструменты плагина. Не вводит новых API-методов — это композиция reports_get / reports_custom / reports_list_types (+ v4goals_get_stat_goals для целей) с правильным выбором разреза, метрик и подачи выводов.

С чего начинать

  1. Авторизация. Сначала auth_status(). Если valid: falseauth_login(). Без авторизации отчёты вернут ошибку.
  2. Выбор инструмента:
    • reports_get(date_from, date_to) — быстрый снимок по кампаниям за короткое окно (по умолчанию ~8 дней, дефолтные поля). Для ответа «как там кампании».
    • reports_custom(field_names=…) — всё остальное: произвольные поля, разрезы по времени/срезам, фильтры, сортировка, цели, пагинация, выгрузка в файл.
    • reports_list_types() — если не уверен, какой report_type подходит.
  3. Сомневаешься в полях/фильтрах — dry_run=True. Reports API отвергает неверные enum'ы опаковым error_code=8000; локальный dry-run экономит раунд-трип и показывает итоговый request_body.

Типовые рецепты EDA

report_type по умолчанию = CUSTOM_REPORT (самый широкий набор измерений). Деньги по умолчанию в рублях (не микро). field_names — регистрозависимый enum.

Вопрос Как получить
Общий снимок по кампаниям reports_get() (или reports_custom с CampaignName,Impressions,Clicks,Cost,Conversions,Ctr,AvgCpc)
Динамика по месяцам/неделям/дням field_names="Month,Cost,Clicks,Conversions,…", order_by=["Month:ASC"] (или Week/Date)
Топ-N кампаний по расходу/конверсиям field_names="CampaignName,Cost,Clicks,Conversions,CostPerConversion", order_by=["Cost:DESC"], page_limit=N
Топ-N ключевых фраз report_type="CRITERIA_PERFORMANCE_REPORT", field_names="CampaignName,Criterion,Clicks,Cost,Ctr,Conversions", order_by=["Cost:DESC"], page_limit=N
Разрез по устройствам field_names="Device,Cost,Clicks,Ctr,Conversions,CostPerConversion"
Разрез по площадкам (Поиск/Сети) field_names="AdNetworkType,Cost,Clicks,Ctr,Conversions"
Пол / возраст field_names="Gender,Age,Impressions,Clicks,Ctr,Conversions"
География field_names="LocationOfPresenceName,Cost,Clicks,Conversions" (или TargetingLocationName)
Поисковые запросы (для минус-слов / новых ключей) report_type="SEARCH_QUERY_PERFORMANCE_REPORT", field_names="Query,Impressions,Clicks,Ctr,Cost,Conversions", order_by=["Cost:DESC"]
Конверсии по целям Метрики задай goal_ids="123,456" → в выводе появятся Conversions_<goal>_<attr> и CostPerConversion_<goal>_<attr>. ID целей: v4goals_get_stat_goals(campaign_ids=…)
Итоги по всему аккаунту report_type="ACCOUNT_PERFORMANCE_REPORT"

Read the full file on GitHub · 117 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 117 lines · 106 tokens per session scan A 090f0697254e

Subscribe to this mod's changes

direct-eda is a skill published in the GitHub repository nikolaymokh-dev/yandex-direct-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 106 tokens to every session and 2,163 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to direct-eda, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories