| сайтмапы, переобход, ссылки, фиды, диагностика. Плюс scraping раздела Alice / Share of Voice (нет публичного API). вебмастер индексация, вебмастер запросы, вебмастер переобход, share of voice, sov, алиса, alice efficiency, конкуренты в алисе.
npx skills add https://github.com/artwist-polyakov/polyakov-claude-skills --skill yandex-webmaster
Работа с Yandex Webmaster API v4. Управление сайтами, анализ индексации, поисковые запросы, переобход страниц, ссылки, фиды.
Требуется YANDEX_WEBMASTER_TOKEN в config/.env.
Scope: webmaster:hostinfo + webmaster:verify.
Инструкция: config/README.md.
Для alice.sh (Share of Voice, без публичного API) дополнительно нужен
SESSION_ID — cookie из браузера. Подробности в config/README.md и
references/ALICE_EFFICIENCY.md.
--host <domain> (поиск по кешу hosts.tsv) или --host-id <id> (прямой ID). Первый вызов hosts.sh автоматически кеширует список. bash scripts/hosts.sh
"О каком сайте идёт речь?
Укажите домен или host_id из списка."
Для поиска по кешу:
bash scripts/hosts.sh --search "example"
bash scripts/summary.sh --host example.com
Общий паттерн вызова:
bash scripts/<script>.sh --host <domain> [--action <action>] [params...]
| Script | Description | Key params |
|--------|-------------|------------|
| hosts.sh | Список сайтов | --search "text", --no-cache |
| host_info.sh | Инфо о сайте + владельцы | — |
| add_site.sh | Добавить сайт | --url <url> |
| verify.sh | Верификация сайта | --action get\|start, --method DNS\|HTML_FILE\|META_TAG |
| Script | Description | Key params |
|--------|-------------|------------|
| summary.sh | Сводка: SQI, страницы, проблемы | — |
| sqi_history.sh | История SQI | --date-from, --date-to |
| diagnostics.sh | Проблемы сайта (live) | — |
| Script | Description | Key params |
|--------|-------------|------------|
| popular_queries.sh | Топ запросов | --order-by, --device, --limit |
| queries_history.sh | История запросов | --query-id (опц.), --device |
| query_analytics.sh | Расширенная аналитика (POST) | --text-indicator, --filter-*, --region-ids |
| Script | Description | Key params |
|--------|-------------|------------|
| indexing.sh | История/сэмплы индексации | --action history\|samples |
| important_urls.sh | Важные URL | --action list\|history, --url |
| archive_export.sh | Экспорт всех страниц | --action start\|status, --task-id |
| Script | Description | Key params |
|--------|-------------|------------|
| insearch.sh | Страницы в выдаче | --action history\|samples |
| search_events.sh | Появление/исчезновение | --action history\|samples |
| Script | Description | Key params |
|--------|-------------|------------|
| recrawl.sh | Переобход URL | --action submit\|status\|list\|quota, --url, --task-id |
| Script | Description | Key params |
|--------|-------------|------------|
| internal_links.sh | Битые внутренние ссылки | --action samples\|history, --indicator |
| external_links.sh | Внешние ссылки | --action samples\|history |
| Script | Description | Key params |
|--------|-------------|------------|
| sitemaps.sh | Управление сайтмапами | --action list\|user-list\|info\|add\|recrawl-limit\|recrawl |
| Script | Description | Key params |
|--------|-------------|------------|
| alice.sh | Эффективность в Алисе: SoV timeline, конкуренты, запросы где сайт есть/нет | --action summary\|sov\|competitors\|with-site\|without-site\|fetch, --no-cache |
> ⚠ Нет публичного API — данные парсятся из window._initData HTML-страницы.
> Требует SESSION_ID cookie в config/.env. См. references/ALICE_EFFICIENCY.md.
| Script | Description | Key params |
|--------|-------------|------------|
| feeds.sh | YML-фиды | --action list\|add\|change\|add-status, --type, --region-ids |
| search_export.sh | PRO SERP экспорт | --action dates\|limits\|start\|status |
| regions.sh | Справочник регионов | --filter "москва" |
| Param | Description |
|-------|-------------|
| --host <domain> | Домен/URL сайта (поиск по hosts.tsv) |
| --host-id <id> | Прямой host_id (формат: http:example.com:80) |
| --action <act> | Подкоманда скрипта |
| --date-from | Начало периода YYYY-MM-DD (history: default 90 дней назад) |
| --date-to | Конец периода YYYY-MM-DD |
| --limit N | Число записей |
| --offset N | Смещение |
| --no-cache | Пропустить кеш |
Кеш в cache/:
user_id.txt — ID пользователя (permanent)hosts.json + hosts.tsv — список сайтов (permanent, инвалидируется при add/verify)host_*/queries/*.tsv — результаты запросов (session, hash-keyed)host_*/indexing/*.tsv — данные индексации (session)host_*/insearch/*.tsv — данные о поиске (session)host_*/links/*.tsv — данные о ссылках (session)host_*/alice/init.json — распарсенный alice объект, переиспользуется всеми action'ами alice.sh (refresh: --no-cache или --action fetch)Fetches complete Airbnb listing details for a given numeric listing ID via the internal GraphQL API, returning title, room type, description, amenities, photos, coordinates, city, house rules, highlights, ratings, review count, bedroom configuration, and property overview. Use when user mentions Airbnb listing details, Airbnb property info, Airbnb room details, get Airbnb listing data, Airbnb amenities list, Airbnb house rules, Airbnb property description, Airbnb detail page scraper, Airbnb rooms detail, Airbnb property page data, Airbnb listing info, fetch Airbnb room details, pull Airbnb listing.
Searches Douyin (douyin.com) for videos by keyword and returns structured video data including author info, stats, cover, description, hashtags, and download URL. Supports date range filtering and sorting by relevance, likes, or recency. Use when user mentions Douyin search, scrape Douyin videos, collect TikTok China videos, extract douyin video data, grab douyin results, fetch douyin keyword videos, douyin video list, douyin content mining, search douyin by keyword, douyin likes filter, douyin date filter, douyin video download links, douyin creator info, douyin hashtag extraction, douyin video scraper, douyin KOL research, douyin content analysis.
Fetch full product detail from a Taobao or Tmall product page by itemId, returning title, price, shop info, images, SKU variants, and product attributes. Use when user asks to get product details from Taobao, scrape a Taobao item page, extract product info by item ID, fetch Tmall product data, 抓取淘宝商品详情, 获取淘宝商品信息, 淘宝商品页面采集, 天猫商品详情, 按商品ID获取信息. Also applies to building product databases, price tracking by itemId, and product comparison research.
Fetch customer reviews for a Taobao or Tmall product by itemId, returning reviewer name, date, purchased variant, review text, and photo URLs. Use when user asks to get product reviews from Taobao, scrape Taobao customer feedback, extract buyer reviews by item ID, collect Tmall ratings and comments, 采集淘宝商品评价, 抓取淘宝买家评论, 获取淘宝商品评论, 天猫商品评价抓取, 按商品ID获取评价. Also applies to sentiment analysis of product reviews, building review datasets, and monitoring product rating changes.
TikTok hashtag video scraper: input a hashtag name → output paginated video list with full metadata (author profile, engagement stats, music, video meta, hashtag list). Use when user mentions TikTok hashtag scraping, TikTok tag videos, scrape TikTok by hashtag, extract TikTok hashtag data, TikTok challenge videos, get videos from a TikTok tag, bulk collect TikTok hashtag posts, TikTok video collection by tag, TikTok topic videos, collect TikTok tag data, batch fetch TikTok videos by hashtag, tiktok tag scraper, tiktok challenge scraper. Also applies to competitive research on TikTok trending topics, influencer discovery by hashtag, content monitoring for specific TikTok tags, or any task requiring video lists from a specific TikTok hashtag or challenge.
TikTok user profile video scraper: input a TikTok username → output the user's profile info plus paginated video list with full metadata (engagement stats, music, video meta). Use when user mentions TikTok profile scraping, scrape TikTok user videos, get TikTok creator videos, extract TikTok profile data, TikTok user posts, TikTok account video collection, collect TikTok profile page videos, TikTok creator video list, TikTok creator data, TikTok profile scraper, tiktok user scraper, tiktok creator scraper. Also applies to influencer research, competitor analysis, content archiving for a specific TikTok creator, or extracting all posts from a TikTok account.
TikTok keyword search video scraper: input search keyword → output paginated video list with full metadata (author, engagement stats, music, video meta). Use when user mentions TikTok search scraping, search TikTok by keyword, TikTok search results, extract TikTok search data, scrape TikTok videos by keyword, TikTok keyword videos, TikTok keyword search, TikTok search results collection, find TikTok videos by topic, tiktok search scraper, tiktok keyword scraper. Also applies to market research on TikTok content for specific topics, competitor content monitoring, or discovering videos and creators around a keyword.
Search Xiaohongshu (RedNote / xhs) notes by keyword and return a paginated list with title, author, engagement stats (likes, collects, comments), cover image URL, and xsecToken for detail lookup. Use when user mentions find notes on xiaohongshu, search rednote, search xhs, scrape xiaohongshu search, xiaohongshu keyword search, rednote post search, xhs search results, monitor xiaohongshu topics, KOL content discovery via xiaohongshu, xiaohongshu note list, rednote scrape, xhs data collection, collect xiaohongshu posts, xiaohongshu topic search, xiaohongshu content monitoring, rednote post list, xhs keyword scrape.
Take artwist-polyakov/yandex-webmaster from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.