agentleFS
khadinakbarlabskhadinakbarlabs/vibelocal/skills/local-keyword-research/SKILL.md

local-keyword-research

Skill0 starsChanged 36 days agoMITView on GitHub

Build a local service keyword map, find city and near-me query opportunities, map intent to real branch pages, or choose keywords for Google Maps rank checks. Use observed SERP questions and related queries without inventing volume or difficulty.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read WORKFLOW.md and ACTORS.md.

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Local service keyword map

Read WORKFLOW.md and ACTORS.md. Reuse actual services, public service areas and the user's goal. Start with a useful local draft without paid data: service × locality × intent, distinguishing emergency, appointment, price/eligibility and information needs where those services are real.

Select a small representative serp sample only if search evidence is needed and its plan is approved. Preserve country, language, query, result page, timestamp and source URL. Related searches and People Also Ask are observed ideas. This Actor does not provide search volume, CPC or difficulty; leave these unknown. A city phrase is query wording, not precise device geolocation. Use the separate Maps grid workflow for location-based rank positions.

Produce a deduplicated map: keyword, intent, actual service, branch/service area, source/observed date, proposed existing page or justified new page, and validation method. Prioritize service fit, purchase intent, the owner's capacity and observed content gaps; label these qualitative judgments. Avoid duplicate city pages with swapped names, unsupported service claims, fake offices and keyword-stuffed business names.

Choose 1–3 baseline ranking queries and a small content improvement the owner can review. Do not turn all ideas into a paid ranking run automatically. If the user supplies Search Console or keyword-tool exports, keep their metrics and definitions separate from this scraper's observations.

Deliver the usable keyword/page map, assumptions and next action. Route a location-page implementation to location-page-seo; a request only for rankings goes to maps-rank-tracking.

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.