agentleFS
awaikawaik/direct-mcp-ai-project/.agents/skills/serp-monitor/SKILL.md

serp-monitor

Skill20 starsChanged 4 days agoMITView on GitHub

Мониторить запросы, CTR и средние позиции сайта в Яндексе через данные Вебмастера; при наличии отдельного SERP-инструмента делать точечные снимки выдачи и конкурентов. Использовать для динамики позиций, сниппетов и поисковых запросов.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use for checking a site's Yandex queries, CTR, average positions, snippets, and movement over time.

    line 8
  2. Very specific:

    Use $yandex-webmaster: start with webmaster_get_hosts, select the exact host_id, then read webmaster_get_popular_queries, …

    line 13
  3. Distinctive:

    Treat Webmaster positions as aggregated search-performance data, not a point-in-time rank checker.

    line 14
  4. Distinctive:

    Do not claim stable ranking from one snapshot or average position.

    line 23
  5. Distinctive:

    Do not infer advertising blocks from Yandex XML/Webmaster organic data.

    line 24
  6. Distinctive:

    Do not mix organic and paid positions.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

SERP Monitor

Use for checking a site's Yandex queries, CTR, average positions, snippets, and movement over time.

Workflow

  1. Clarify target domain, queries, period, comparison period, and region when the source supports it.
  2. Use $yandex-webmaster: start with webmaster_get_hosts, select the exact host_id, then read webmaster_get_popular_queries, webmaster_get_queries_history, webmaster_get_query_history, or webmaster_query_analytics as appropriate.
  3. Treat Webmaster positions as aggregated search-performance data, not a point-in-time rank checker.
  4. For an exact current SERP or competitor snapshot, use only a separately available SERP connector/tool whose schema you can inspect. If none exists, state that the exact snapshot is unavailable; do not reconstruct it from memory or ordinary browser personalization.
  5. Record source, period/date, query, domain, URL, position metric, CTR, clicks/impressions, and any source limitations.
  6. Compare against prior verified data only when available.
  7. Save reports to Workspace through call_write_tool only when the user requests that destination and after resolving workspace_project_id. Otherwise return the report or use the requested available artifact tool.

Rules

  • Mark exact SERP snapshots as point-in-time and Webmaster metrics as period aggregates.
  • Do not claim stable ranking from one snapshot or average position.
  • Do not infer advertising blocks from Yandex XML/Webmaster organic data.
  • Do not mix organic and paid positions.

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.