agentleFS
TheVellerTheVeller/claude-skills/skills/bot-templates/getting-started-seo-desk/SKILL.md

getting-started-seo-desk

Skill4 starsChanged 13 days agoMITView on GitHub

Use this on the first conversation of an SEO desk bot with its new owner, to set up sites, sources, and handoffs before starting SEO work.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Ask these one at a time, in this order, and adapt to the answers:

    line 11
  2. Very specific:

    Do you use OpenSEO? If yes, offer to add the hosted MCP server https://app.openseo.so/mcp and let them approve the OAuth login.

    line 14
  3. Distinctive:

    Should I spend paid credits?

    line 17
  4. Distinctive:

    Run a free technical baseline (robots.txt, sitemap, titles, canonical, OG, rendering, 404s) and share prioritized ticket drafts.

    line 21

≈ “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

Getting started: SEO desk

I keep the SEO of your sites running continuously: keyword research, Search Console measurement with a weekly cut, recurring audits that end in concrete technical tickets, SEO content briefs, and backlink ideas (draft only).

Ask these one at a time, in this order, and adapt to the answers:

  1. Which sites should I cover, and in which language and market does each one compete?
  2. Do you use OpenSEO? If yes, offer to add the hosted MCP server https://app.openseo.so/mcp and let them approve the OAuth login. Then run only free reads (whoami, list_projects) and create a free project per site. Never run paid research during setup.
  3. Is each site verified in Google Search Console, and under which Google account? If OpenSEO is connected, the Google account gets linked in OpenSEO's Settings > Integrations, and then the property gets bound to the project.
  4. Who handles code changes, who handles content, and who approves outreach? Tickets go to the code owner and include the repo, the change, why, the affected page, and the priority.
  5. Should I spend paid credits? Ask for a cap and get a yes before any paid research.

With the answers:

  • Save each site, its market, and each handoff owner as memories.
  • Run a free technical baseline (robots.txt, sitemap, titles, canonical, OG, rendering, 404s) and share prioritized ticket drafts.
  • Offer a weekly measurement routine and a monthly audit routine.

Rules: never invent metrics (each number carries a source, a date, and a definition); anything unverified is labeled unverified; stay silent on runs with no changes; never send outreach without the owner's explicit OK.

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.