agentleFS
awaikawaik/direct-mcp-ai-project/.claude/skills/seo-optimizer/SKILL.md

seo-optimizer

Skill20 starsChanged 3 days agoMITView on GitHub

Проводить SEO/GEO-аудит и оптимизацию страницы или сайта: интент, Wordstat, Вебмастер, метаданные, структура контента, перелинковка и конверсия. Использовать для аудита URL, плана улучшений или проверки видимости в поиске и AI-ответах.

19 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, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 4

    Distinctive

    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
  1. Distinctive:

    Use for SEO audits, GEO/AI-search visibility, question selection and monitoring reports, page optimization, metadata, internal links, and …

    line 8
  2. Very specific:

    Use Wordstat for demand when needed.

    line 15
  3. Very specific:

    Use Yandex Webmaster if site access is available.

    line 16
  4. Very specific:

    Read references/audit-checklist.md before producing the final priority list.

    line 21
  5. Distinctive:

    Use selected-project notes and rules for attributed business terms.

    line 26
  6. Distinctive:

    When moving from an audit to drafting page copy, briefly retain the unfinished checks from the audit.

    line 28
  7. Distinctive:

    Do not invent rankings or traffic numbers.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 15 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 Optimizer

Use for SEO audits, GEO/AI-search visibility, question selection and monitoring reports, page optimization, metadata, internal links, and content improvement plans.

For GEO monitoring, question selection, report analysis or comparison, read references/geo-monitoring.md. Use the shared lidfly_geo_* tools for sites on any platform.

Workflow

  1. Clarify target page, region, business goal, and priority queries.
  2. Use Wordstat for demand when needed; no client_login or connection_id.
  3. Use Yandex Webmaster if site access is available; start with webmaster_get_hosts.
  4. Inspect page content and search intent.
  5. Produce prioritized fixes: technical blockers, intent gaps, title/meta/H1, headings, content, internal links, conversion elements.
  6. Return the audit in the requested format. Save to Workspace only when requested and with resolved workspace_project_id; do not require Workspace for a response or local artifact.

Read references/audit-checklist.md before producing the final priority list. If the page content cannot be opened through an available browser, connector, or supplied file, ask for the text/HTML and do not pretend to have inspected the page.

Rules

  • Separate verified data from hypotheses.
  • Use selected-project notes and rules for attributed business terms; do not ask again for facts already supplied there. Name conflicts with website content and the source of each claim.
  • If page_details_available: false or a page has details: null, give a text audit: distinguish findings checked through text/available Webmaster data from checks requiring a browser or manual inspection (forms, header/footer, mobile layout, canonical/robots). Missing details do not mean those elements are absent. Do not call read_website_page(part="details") for a page whose details are unavailable.
  • When moving from an audit to drafting page copy, briefly retain the unfinished checks from the audit. Use only services needed for the task; missing visual data does not block useful text recommendations.
  • Do not invent rankings or traffic numbers.
  • For generated page changes, preserve user-provided brand and legal constraints; flag regulated or unsupported claims that require qualified review.

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.