agentleFS
Sign inStart free
empowerment-aiempowerment-ai/agent-site-kit/skills/seo-checkup/SKILL.md

seo-checkup

Skill0 starsChanged 47 days agoMITView on GitHub

Monthly (or weekly) read-only website checkup. Confirms the site builds, spot-checks pages and redirects, pulls real ranking and keyword data from DataForSEO, and sends the owner a short report with up to 3 suggested improvements. Designed to run on a schedule (Hermes cron) and never publishes anything on its own.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Very specific:

    Search volume (kw_data_google_ads_search_volume) for the keywords listed in docs/seo/keywords.md, if it exists.

    line 22
  2. Distinctive:

    If the site is new and ranks for nothing yet, say so plainly.

    line 26
  3. Very specific:

    Commit only the docs/seo/ report files, and only through npm run care:propose if the owner wants them kept in the repo.

    line 35
  4. Distinctive:

    Never invent numbers. If a DataForSEO call fails or returns nothing, say "no data this month" rather than guessing.

    line 38

≈ “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

SEO checkup (scheduled, read-only)

This skill reports and suggests. It never publishes. If the owner replies to the report with "do #2", hand off to the site-care skill, which previews and waits for a yes.

Steps

  1. git checkout main && git pull, then npm run check. If the check fails, lead the report with that (someone edited something by hand) and stop.
  2. Is the site up? Fetch the live home page and 2–3 other pages from the URL in content/business.json. Note anything that isn't a 200.
  3. Redirects still work? For each entry in content/redirects.json, request the old URL without following redirects and confirm a 301/308 pointing at the right page.
  4. Search data (DataForSEO MCP, about 2–4 calls, pennies):
    • Keywords the domain currently ranks for (dataforseo_labs_google_ranked_keywords for the site's domain in the market from business.json), if it's live on a real domain.
    • Search volume (kw_data_google_ads_search_volume) for the keywords listed in docs/seo/keywords.md, if it exists. Compare with last month's file in docs/seo/history/ if there is one, then save this month's results as docs/seo/history/YYYY-MM.md. If the site is new and ranks for nothing yet, say so plainly. That's normal for the first few months.
  5. Write the report for a non-technical owner, 8 lines or fewer:
    • one line on site health (up, fast, redirects fine)
    • what moved in search, with real numbers only
    • up to 3 suggestions, numbered, each one sentence with the reason (e.g. "1. Add a 'holiday pre-order' section to the menu page. 390 people a month search 'holiday bread pre-order' near you.")
    • "Reply with a number and I'll prepare a preview."
  6. Commit only the docs/seo/ report files, and only through npm run care:propose if the owner wants them kept in the repo. Otherwise leave them uncommitted.

Never invent numbers. If a DataForSEO call fails or returns nothing, say "no data this month" rather than guessing.

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