AgentShekelAgentShekel/agentic-workflow/skills/yandex-webmaster-guide/SKILL.md

yandex-webmaster-guide

Skill4 starsChanged 29 days agoMITView on GitHub

[TOOL] Yandex Webmaster API v4 client (indexing status, search queries from SERP, crawl errors, backlinks, sitemaps, site diagnostics, SQI history). Preloaded by marketing-seo-specialist agent.

Reads credentials

In this repository48 other files it gives its agents.
- skills/dev-methodology/references/agents.mdAGENTS.md
- skills/skill-authoring/references/agents.mdAGENTS.md
- acceptance-protocolSkill
- agency-intakeSkill
- ai-visibility-methodologySkill
- banner-design-guideSkill
- benchmark-researchSkill
- brand-methodologySkill
- code-reviewingSkill
- code-writingSkill
- codex-bridgeSkill
- deploy-pipelineSkill
- design-assets-guideSkill
- design-system-methodologySkill
- design-task-decompositionSkill
- dev-methodologySkill
- docs-pipelineSkill
- documentation-writingSkill
- engagement-contractSkill
- engagement-protocolSkill
- feature-researchSkill
- human-voiceSkill
- infrastructure-setupSkill
- marketing-task-decompositionSkill
- post-deploy-qaSkill
- pre-deploy-qaSkill
- presentation-designSkill
- project-planningSkill
- prompt-engineeringSkill
- security-auditingSkill
- semantic-drift-methodologySkill
- seo-auditingSkill
- skill-authoringSkill
- skill-test-designSkill
- skill-testingSkill
- system-optimization-protocolSkill
- task-decompositionSkill
- tech-spec-planningSkill
- testing-methodologySkill
- ui-styling-guideSkill
- ui-ux-methodologySkill
- user-spec-planningSkill
- validation-pipelineSkill
- yandex-analytics-methodologySkill
- yandex-direct-guideSkill
- yandex-metrika-guideSkill
- yandex-search-guideSkill
- yandex-wordstat-guideSkill

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Check API connection, show user_id, list hosts.
line 30
Very specific:
Use common.sh functions directly:
line 211
Very specific:
Run bash scripts/quota.sh to verify
line 226

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

yandex-webmaster

Informational skill — website SEO health and search performance via Yandex Webmaster API v4.

Config

Requires YANDEX_WEBMASTER_TOKEN in config/.env (synced from yandex-analytics-methodology unified config). Optionally set YANDEX_WEBMASTER_HOST for a default host. Token setup and OAuth registration details in config/README.md.

Workflow

Check connection: bash scripts/quota.sh — verifies token, gets user_id
List hosts: bash scripts/hosts.sh — shows all registered sites
Run report using appropriate script with --host parameter
Interpret results — the API returns raw JSON; parse and present key metrics

Scripts

quota.sh

Check API connection, show user_id, list hosts.

bash scripts/quota.sh

hosts.sh

List all sites registered in Yandex Webmaster with their verification status.

bash scripts/hosts.sh

search_queries.sh

Popular search queries from Yandex SERP for a specific site.

bash scripts/search_queries.sh --host https://example.com:443 --from 2025-01-01 --to 2025-01-31 --limit 20 --order TOTAL_CLICKS

Param	Required	Default	Description
`--host`	yes	—	Host URL (e.g., `https://example.com:443`)
`--from`	no	30 days ago	Start date (YYYY-MM-DD)
`--to`	no	today	End date (YYYY-MM-DD)
`--limit`	no	20	Max rows
`--order`	no	TOTAL_CLICKS	Sort by: `TOTAL_SHOWS` or `TOTAL_CLICKS`
`--indicator`	no	TOTAL_SHOWS,TOTAL_CLICKS,AVG_SHOW_POSITION,AVG_CLICK_POSITION	Query indicators

indexing.sh

Indexing stats: summary, history, or indexed page samples.

bash scripts/indexing.sh --host https://example.com:443 --type summary
bash scripts/indexing.sh --host https://example.com:443 --type history --from 2025-01-01
bash scripts/indexing.sh --host https://example.com:443 --type samples --limit 20

Param	Required	Default	Description
`--host`	yes	—	Host URL
`--type`	no	summary	`summary`, `history`, or `samples`
`--from`	no	30 days ago	Start date (for history)
`--to`	no	today	End date (for history)
`--limit`	no	100	Max rows (for samples)

diagnostics.sh

Site diagnostics — problems found by Yandex crawler.

bash scripts/diagnostics.sh --host https://example.com:443

Param	Required	Default	Description
`--host`	yes	—	Host URL

links.sh

External backlinks or broken internal links.

bash scripts/links.sh --host https://example.com:443 --type external
bash scripts/links.sh --host https://example.com:443 --type internal-broken
bash scripts/links.sh --host https://example.com:443 --type external-history --from 2025-01-01

Param	Required	Default	Description
`--host`	yes	—	Host URL
`--type`	no	external	`external`, `external-history`, or `internal-broken`
`--from`	no	30 days ago	Start date (for history)
`--to`	no	today	End date (for history)
`--limit`	no	100	Max rows (for samples)

sitemaps.sh

List sitemaps registered for a site.

bash scripts/sitemaps.sh --host https://example.com:443

Param	Required	Default	Description
`--host`	yes	—	Host URL

recrawl.sh

Submit a URL for recrawling or check recrawl quota.

bash scripts/recrawl.sh --host https://example.com:443 --url https://example.com/page
bash scripts/recrawl.sh --host https://example.com:443 --quota

Param	Required	Default	Description
`--host`	yes	—	Host URL
`--url`	no	—	URL to submit for recrawl
`--quota`	no	false	Show recrawl quota only

sqi.sh

SQI (Site Quality Index) history.

bash scripts/sqi.sh --host https://example.com:443 --from 2025-01-01

Param	Required	Default	Description
`--host`	yes	—	Host URL
`--from`	no	30 days ago	Start date (YYYY-MM-DD)
`--to`	no	today	End date (YYYY-MM-DD)

API Reference

Webmaster API v4

Base: https://api.webmaster.yandex.net/v4
Auth: Authorization: OAuth <token>
First get user_id: GET /user → {"user_id": 12345}
Then all requests use: /user/{user_id}/hosts/...

Host ID format

Yandex Webmaster uses host IDs in format https:example.com:443. Scripts accept normal URLs like https://example.com or https://example.com:443 and convert them automatically.

Key endpoints

Endpoint	Description
`GET /user`	Get user_id
`GET /user/{uid}/hosts`	List all registered sites
`GET /user/{uid}/hosts/{hostId}/summary`	Site indexing summary
`GET /user/{uid}/hosts/{hostId}/search-queries/popular`	Popular search queries
`GET /user/{uid}/hosts/{hostId}/indexing/samples`	Indexed page samples
`GET /user/{uid}/hosts/{hostId}/indexing/history`	Indexing history
`GET /user/{uid}/hosts/{hostId}/links/external/samples`	External backlinks
`GET /user/{uid}/hosts/{hostId}/links/external/history`	External links history
`GET /user/{uid}/hosts/{hostId}/links/internal/samples`	Broken internal links
`GET /user/{uid}/hosts/{hostId}/diagnostics`	Site diagnostics
`GET /user/{uid}/hosts/{hostId}/sitemaps`	Sitemaps
`POST /user/{uid}/hosts/{hostId}/recrawl/queue`	Submit URL for recrawl
`GET /user/{uid}/hosts/{hostId}/recrawl/quota`	Recrawl quota
`GET /user/{uid}/hosts/{hostId}/sqi/history`	SQI history
`GET /user/{uid}/hosts/{hostId}/search-queries/all/history`	All queries stats

Search queries indicators

Indicator	Description
`TOTAL_SHOWS`	Total impressions in search
`TOTAL_CLICKS`	Total clicks from search
`AVG_SHOW_POSITION`	Average position when shown
`AVG_CLICK_POSITION`	Average position when clicked

Common use cases

"How's the site doing in Yandex?"

bash scripts/quota.sh
bash scripts/indexing.sh --host https://example.com:443 --type summary
bash scripts/sqi.sh --host https://example.com:443

"What queries bring traffic from Yandex?"

bash scripts/search_queries.sh --host https://example.com:443 --limit 30 --order TOTAL_CLICKS

"Are there indexing problems?"

bash scripts/diagnostics.sh --host https://example.com:443
bash scripts/indexing.sh --host https://example.com:443 --type samples

"What's the backlink profile?"

bash scripts/links.sh --host https://example.com:443 --type external --limit 50
bash scripts/links.sh --host https://example.com:443 --type external-history

"Are sitemaps working?"

bash scripts/sitemaps.sh --host https://example.com:443

"Force recrawl a page"

bash scripts/recrawl.sh --host https://example.com:443 --quota
bash scripts/recrawl.sh --host https://example.com:443 --url https://example.com/updated-page

Custom query (advanced)

Use common.sh functions directly:

source scripts/common.sh
load_config
USER_ID=$(get_user_id)

# Custom GET request
webmaster_get "/user/${USER_ID}/hosts"

Sharing

To share this skill with colleagues:

Copy the entire yandex-webmaster/ folder to their ~/.claude/skills/
They create their own config/.env with their token
Run bash scripts/quota.sh to verify

Limits

API rate limit: ~5 requests/second
Recrawl quota: limited per day (check via --quota)
Historical data depth varies by endpoint
Host must be verified in Yandex Webmaster to access data

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.

Check your setup, free