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

yandex-metrika-guide

Skill4 starsChanged 29 days agoMITView on GitHub

[TOOL] Yandex Metrika API client (traffic overview, sources, devices, conversions, popular pages, audience geography, demographics). Preloaded by marketing-web-analyst and marketing-ppc-specialist agents.

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-search-guideSkill
- yandex-webmaster-guideSkill
- yandex-wordstat-guideSkill

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
All scripts accept --counter ID to specify the Metrika counter.
line 30
Distinctive:
Check API connection and counter info.
line 33
Very specific:
Use common.sh functions directly:
line 204
Very specific:
Run bash scripts/quota.sh --counter THEIR_COUNTER to verify
line 219

≈ “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-metrika

Informational skill — website traffic and user behavior analytics via Yandex Metrika API.

Config

Requires YANDEX_METRIKA_TOKEN in config/.env (synced from yandex-analytics-methodology unified config). Token setup and OAuth details in config/README.md.

Counter ID is per-project — pass it via --counter flag on every script call. Alternatively, set YANDEX_METRIKA_COUNTER in config/.env as a default for a single site.

Workflow

Check connection: bash scripts/quota.sh --counter 12345678
Run report using appropriate script
Interpret results — the API returns raw JSON; parse and present key metrics

Scripts

All scripts accept --counter ID to specify the Metrika counter. If not passed, falls back to YANDEX_METRIKA_COUNTER from config/.env.

quota.sh

Check API connection and counter info.

bash scripts/quota.sh --counter 12345678

overview.sh

Traffic overview: visits, pageviews, users, bounce rate, avg duration.

bash scripts/overview.sh --counter 12345678 --from 2025-01-01 --to 2025-01-31

Param	Required	Default	Description
`--counter`	yes*	from .env	Metrika counter ID
`--from`	no	30 days ago	Start date (YYYY-MM-DD)
`--to`	no	today	End date (YYYY-MM-DD)

sources.sh

Traffic sources: search engines, referrals, direct, social.

bash scripts/sources.sh --counter 12345678 --from 2025-01-01 --to 2025-01-31 --limit 10

Param	Required	Default	Description
`--counter`	yes*	from .env	Metrika counter ID
`--from`	no	30 days ago	Start date
`--to`	no	today	End date
`--limit`	no	10	Max rows per report

pages.sh

Popular pages: pageviews and users by URL.

bash scripts/pages.sh --counter 12345678 --from 2025-01-01 --limit 20

# Filter by URL substring
bash scripts/pages.sh --counter 12345678 --url "/price/"

Param	Required	Default	Description
`--counter`	yes*	from .env	Metrika counter ID
`--from`	no	30 days ago	Start date
`--to`	no	today	End date
`--limit`	no	20	Max rows
`--url`	no	-	Filter pages by URL substring

devices.sh

Device, browser, and OS statistics.

bash scripts/devices.sh --counter 12345678 --type device
bash scripts/devices.sh --counter 12345678 --type browser
bash scripts/devices.sh --counter 12345678 --type os

Param	Required	Default	Description
`--counter`	yes*	from .env	Metrika counter ID
`--from`	no	30 days ago	Start date
`--to`	no	today	End date
`--type`	no	device	`device`, `browser`, or `os`

goals.sh

Configured goals and conversion statistics.

# List goals only
bash scripts/goals.sh --counter 12345678 --list

# Goals with conversion stats
bash scripts/goals.sh --counter 12345678 --from 2025-01-01

Param	Required	Default	Description
`--counter`	yes*	from .env	Metrika counter ID
`--from`	no	30 days ago	Start date
`--to`	no	today	End date
`--list`	no	false	Only list goals, skip stats

visitors.sh

Visitor demographics and geography.

bash scripts/visitors.sh --counter 12345678 --type geo
bash scripts/visitors.sh --counter 12345678 --type age
bash scripts/visitors.sh --counter 12345678 --type gender

Param	Required	Default	Description
`--counter`	yes*	from .env	Metrika counter ID
`--from`	no	30 days ago	Start date
`--to`	no	today	End date
`--type`	no	geo	`geo`, `age`, or `gender`

* --counter is required unless YANDEX_METRIKA_COUNTER is set in config/.env

API Reference

Stat API (reports)

Base: https://api-metrika.yandex.net/stat/v1/data
Auth: Authorization: OAuth <token>
Key params: id (counter), preset (report type), date1/date2, metrics, dimensions, filters, sort, limit

Presets (most useful)

Preset	Description
`sources_summary`	Traffic by source type
`sources_search_engines`	Search engine breakdown
`sources_sites`	Referral sites
`tech_platforms`	Devices (desktop/mobile/tablet)
`tech_browsers`	Browser stats
`tech_os`	OS stats
`geo_country`	Geography by country
`age_gender`	Age and gender
`conversion_rate`	Goal conversions

Custom metrics (ym:s:*)

Metric	Description
`ym:s:visits`	Visits
`ym:s:pageviews`	Page views
`ym:s:users`	Unique users
`ym:s:bounceRate`	Bounce rate
`ym:s:avgVisitDurationSeconds`	Avg visit duration

Custom dimensions (ym:s:*)

Dimension	Description
`ym:s:TrafficSource`	Traffic source
`ym:s:regionCity`	City
`ym:s:gender`	Gender
`ym:s:ageInterval`	Age group
`ym:s:deviceCategory`	Device type

Page-level metrics (ym:pv:*)

Metric/Dimension	Description
`ym:pv:pageviews`	Page views
`ym:pv:users`	Users
`ym:pv:URLPath`	Page URL

Management API

Base: https://api-metrika.yandex.net/management/v1/counter/{id}/
Endpoints: goals, filters, operations, grants

Common use cases

"How's the site doing?"

bash scripts/overview.sh --counter 12345678
bash scripts/sources.sh --counter 12345678
bash scripts/devices.sh --counter 12345678

"Which pages get the most traffic?"

bash scripts/pages.sh --counter 12345678 --limit 30

"Are goals converting?"

bash scripts/goals.sh --counter 12345678

"Who visits the site?"

bash scripts/visitors.sh --counter 12345678 --type geo
bash scripts/visitors.sh --counter 12345678 --type age

Custom query (advanced)

Use common.sh functions directly:

source scripts/common.sh
load_config
YANDEX_METRIKA_COUNTER=12345678

# Custom metrics + dimensions
metrika_custom "ym:s:visits,ym:s:bounceRate" "ym:s:TrafficSource" "date1=2025-01-01&date2=2025-01-31&limit=10"

Sharing

To share this skill with colleagues:

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

Limits

API rate limit: ~5 requests/second
Daily limit depends on token type
Data availability: ~5 min delay for real-time, historical data available fully

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