agentleFS
AgentShekelAgentShekel/agentic-workflow/skills/seo-auditing/SKILL.md

seo-auditing

Skill4 starsChanged 29 days agoMITView on GitHub

[METHODOLOGY] Comprehensive SEO audit process orchestrating Yandex data sources (Webmaster, Metrika, Wordstat, Search) into a unified report with recommendations. Preloaded by marketing-seo-specialist agent.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run skills in parallel where possible.

    line 56
  2. Distinctive:

    If a skill is not configured (missing token), skip that section and note it in the report

    line 200
  3. Distinctive:

    If API returns errors, log them and continue with available data

    line 201
  4. Distinctive:

    Always produce a report even if some data sources are unavailable

    line 202
  5. Distinctive:

    Run data collection scripts in parallel using Agent tool where possible

    line 206
  6. Distinctive:

    Look for gaps: high-demand queries (Wordstat) where site has no positions (Search)

    line 209
  7. Distinctive:

    Check if top Metrika pages are properly indexed (Webmaster)

    line 210

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

seo-audit

Procedural skill — comprehensive SEO audit orchestrating all Yandex analytics skills into a unified report.

Prerequisites

At least some of these skills must be configured:

  • yandex-webmaster — indexing, crawl errors, search queries, SQI
  • yandex-metrika — traffic, behavior, conversions
  • yandex-wordstat — search demand, semantics
  • yandex-search — SERP positions, competitors

Path resolution

Orchestrator calls scripts from dependency skills. Paths resolve via $SKILLS_ROOT (default: ~/.claude/skills). Override with:

export SKILLS_ROOT="/custom/path/to/skills"

Makes the skill portable across plugin layouts, custom install locations, and future restructuring.

Workflow

Phase 1: Discovery

  1. ASK user:
    Для какого сайта делаем SEO-аудит?
    URL сайта и основная тематика/что продаёт?
  2. ASK about scope:
    Какие направления аудита нужны?
    - Полный аудит (все направления)
    - Только техническое SEO (индексация, ошибки)
    - Только поисковая видимость (запросы, позиции)
    - Только трафик и поведение
  3. ASK about competitors (if relevant):
    Есть конкуренты для сравнения? (URL или названия)

Phase 2: Data Collection

Run skills in parallel where possible. Check which skills are configured before attempting.

# Set once at the start of Phase 2 — all subsequent calls use $SKILLS_ROOT
SKILLS_ROOT="${SKILLS_ROOT:-$HOME/.claude/skills}"

2.1 Technical SEO (yandex-webmaster)

# Connection check
bash "$SKILLS_ROOT"/yandex-webmaster/scripts/quota.sh

# Site summary
bash "$SKILLS_ROOT"/yandex-webmaster/scripts/indexing.sh --host $SITE --type summary

# Crawl diagnostics
bash "$SKILLS_ROOT"/yandex-webmaster/scripts/diagnostics.sh --host $SITE

# Sitemaps status
bash "$SKILLS_ROOT"/yandex-webmaster/scripts/sitemaps.sh --host $SITE

# Broken internal links
bash "$SKILLS_ROOT"/yandex-webmaster/scripts/links.sh --host $SITE --type internal-broken

# External links
bash "$SKILLS_ROOT"/yandex-webmaster/scripts/links.sh --host $SITE --type external

# SQI history
bash "$SKILLS_ROOT"/yandex-webmaster/scripts/sqi.sh --host $SITE --from $THREE_MONTHS_AGO

# Indexing history
bash "$SKILLS_ROOT"/yandex-webmaster/scripts/indexing.sh --host $SITE --type history --from $THREE_MONTHS_AGO

2.2 Search Visibility (yandex-webmaster + yandex-search)

# Top search queries from Webmaster
bash "$SKILLS_ROOT"/yandex-webmaster/scripts/search_queries.sh --host $SITE --limit 50 --order TOTAL_CLICKS

# Check positions for top queries
bash "$SKILLS_ROOT"/yandex-search/scripts/positions.sh --domain $DOMAIN --queries top_queries.txt --region $REGION --csv positions.csv

# Competitor analysis for key queries
bash "$SKILLS_ROOT"/yandex-search/scripts/competitors.sh --query "$KEY_QUERY" --region $REGION

2.3 Traffic & Behavior (yandex-metrika)

# Traffic overview (last 30 days vs previous 30 days)
bash "$SKILLS_ROOT"/yandex-metrika/scripts/overview.sh --from $CURRENT_START --to $CURRENT_END
bash "$SKILLS_ROOT"/yandex-metrika/scripts/overview.sh --from $PREV_START --to $PREV_END

# Traffic sources
bash "$SKILLS_ROOT"/yandex-metrika/scripts/sources.sh --from $CURRENT_START --to $CURRENT_END

# Top pages
bash "$SKILLS_ROOT"/yandex-metrika/scripts/pages.sh --limit 30

# Devices
bash "$SKILLS_ROOT"/yandex-metrika/scripts/devices.sh --type device

# Goals/conversions
bash "$SKILLS_ROOT"/yandex-metrika/scripts/goals.sh

2.4 Search Demand (yandex-wordstat)

# Core queries demand
bash "$SKILLS_ROOT"/yandex-wordstat/scripts/top_requests.sh --phrase "$CORE_QUERY" --regions $REGION --limit 100

# Demand dynamics (seasonality)
bash "$SKILLS_ROOT"/yandex-wordstat/scripts/dynamics.sh --phrase "$CORE_QUERY" --period monthly --from-date $YEAR_AGO

Phase 3: Analysis & Report

Structure the report as follows:

# SEO-аудит: [site.ru]
Дата: [date]
Период анализа: [period]

## Резюме
[3-5 ключевых выводов с приоритетами: критично / важно / рекомендация]

## 1. Техническое SEO
### Индексация
- Страниц в индексе: X
- Динамика: рост/падение за 3 мес
- SQI: текущий и тренд

### Ошибки краулинга
- [список проблем с приоритетами]

### Сайтмапы
- Статус сайтмапов

### Внутренние ссылки
- Битые ссылки: количество, примеры

### Внешние ссылки
- Количество, динамика

## 2. Поисковая видимость
### Топ запросов (по кликам)
| Запрос | Показы | Клики | Позиция |
|--------|--------|-------|---------|
| ...    | ...    | ...   | ...     |

### Позиции по ключевым запросам
| Запрос | Позиция | URL | Конкуренты в топ-3 |
|--------|---------|-----|---------------------|
| ...    | ...     | ... | ...                 |

## 3. Трафик и поведение
### Общие метрики
| Метрика | Текущий период | Предыдущий | Изменение |
|---------|---------------|------------|-----------|
| Визиты  | ...           | ...        | +/-X%     |

### Источники трафика
### Топ страниц
### Устройства
### Конверсии

## 4. Поисковый спрос
### Объём спроса по ядру
### Сезонность
### Упущенные запросы

## 5. Рекомендации
### Критично (исправить немедленно)
1. ...

### Важно (исправить в ближайший месяц)
1. ...

### Рекомендации (улучшения)
1. ...

Error Handling

  • If a skill is not configured (missing token), skip that section and note it in the report
  • If API returns errors, log them and continue with available data
  • Always produce a report even if some data sources are unavailable

Tips

  • Run data collection scripts in parallel using Agent tool where possible
  • Compare metrics period-over-period for trend analysis
  • Cross-reference data: Webmaster queries vs Metrika landing pages vs Wordstat demand
  • Look for gaps: high-demand queries (Wordstat) where site has no positions (Search)
  • Check if top Metrika pages are properly indexed (Webmaster)

Example Session

User: Сделай SEO-аудит для example.com

Claude: Для какого региона и что продаёт сайт?

User: Москва, продаём строительные материалы

Claude: [Запускает сбор данных из всех доступных скиллов]
        [Параллельно: Webmaster + Metrika + Wordstat + Search]

        === SEO-аудит: example.com ===

        Резюме:
        🔴 КРИТИЧНО: 340 страниц выпало из индекса за последний месяц
        🟡 ВАЖНО: Bounce rate 78% на мобильных (desktop: 45%)
        🟢 РЕКОМЕНДАЦИЯ: Не покрыты запросы "купить кирпич оптом" (2400 показов/мес)

        [Полный отчёт по разделам...]

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.