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

seo-research

Skill0 starsChanged 47 days agoMITView on GitHub

Find what local customers actually search for, using real keyword data from the DataForSEO MCP server, and map those searches to pages on the site. Use for "what should my pages target", "what do people search for", "plan blog posts", or before writing new pages.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. hyperfx-ai/marketing-skills★ 112same name
    2. oegeyilmaz9/seo-aeo-geo-ultimate★ 6same name
    3. mrieck/seoblog-claude-plugin★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 2

    Distinctive

    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. Distinctive:

    Keep it to 5 calls or fewer per run unless the owner says otherwise.

    line 18
  2. Very specific:

    Read content/business.json: the seo.market (e.g.

    line 25
  3. Very specific:

    Write docs/seo/keywords.md with a table: keyword, monthly searches, which existing page should target it (or "new post"), and why.

    line 35
  4. Distinctive:

    When writing, use the keyword naturally in the title, the first paragraph, and one heading.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 3 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 research with real data

An agent without data gives confident, made-up SEO advice. This skill only uses numbers that come back from DataForSEO, and it says so when data is missing.

Cost guardrails (read first)

DataForSEO bills per API call; the calls in this skill cost cents each. Before running:

  1. Tell the owner which calls you're about to make and roughly what they cost. Keyword suggestions and search-volume lookups are typically a few cents per call; check https://dataforseo.com/pricing for current rates.
  2. Keep it to 5 calls or fewer per run unless the owner says otherwise.
  3. The MCP server always calls the live API (there's no sandbox switch), so for a practice run keep it to one or two calls. That's cents. Check the account balance in the DataForSEO dashboard if the owner wants to see it.

Steps

  1. Read content/business.json: the seo.market (e.g. "Virginia,United States"), seo.language, and seo.seedKeywords, plus what the business sells.
  2. Using the DataForSEO MCP tools (the repo's .mcp.json enables only the keyword-research modules):
    • dataforseo_labs_google_keyword_ideas or dataforseo_labs_google_keyword_suggestions for 2–3 seed keywords in the market's location.
    • kw_data_google_ads_search_volume for the most relevant 20–40 candidates.
  3. Filter hard. Keep searches a real customer of this business would type, with local or purchase intent. Drop national brands, jobs ("bakery jobs"), and recipes, unless the owner wants recipe content.
  4. Write docs/seo/keywords.md with a table: keyword, monthly searches, which existing page should target it (or "new post"), and why. Add the date and the data source.
  5. Propose, don't publish: suggest up to 3 concrete changes (a title or description rewrite, a new section, or a new journal post) and wait for the owner to pick.
  6. When writing, use the keyword naturally in the title, the first paragraph, and one heading. Never stuff keywords or invent facts to fit a keyword.

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