agentleFS
Sign inStart free
ModernMustardSeedModernMustardSeed/local-growth-crew/skills/presence-audit/SKILL.md

presence-audit

Skill0 starsChanged 34 days agoMITView on GitHub

Run a scored local presence audit on one business (website 45 percent, Google reviews 30 percent, Google Business Profile 25 percent) and return the score, what is working, and ranked fixes. Use when the user names a local business and asks how it looks online or what to fix first.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run the Site Check scan_website tool on the homepage with detail: "summary".

    line 11
  2. Distinctive:

    Read the Google Business Profile as it shows publicly: rating, review count, primary category, hours, phone and address, with the source …

    line 12
  3. Very specific:

    Run the Site Check score_local_presence tool with only the facts you read or the user supplied, plus source_urls.

    line 13
  4. Distinctive:

    If the tools are unavailable, say so and stop.

    line 19
  5. Very specific:

    No em dashes. Never promise rankings, calls or revenue.

    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

Presence audit

Audit the business the user named: $ARGUMENTS

  1. Confirm the business name, city and state, website and trade. Ask for anything missing. If you find the website by search, confirm it is the same business before you scan.
  2. Run the Site Check scan_website tool on the homepage with detail: "summary".
  3. Read the Google Business Profile as it shows publicly: rating, review count, primary category, hours, phone and address, with the source URL. If you cannot read it, ask the user to paste what they see. Never invent a rating or a count.
  4. Run the Site Check score_local_presence tool with only the facts you read or the user supplied, plus source_urls.
  5. Write the report:
    • Overall score, letter grade, and the three pillar scores, with today's date.
    • What is already working.
    • Fixes ranked by impact, each with its evidence and who can do it.
    • Three fixes the owner can do this week without help.
  6. If the tools are unavailable, say so and stop. Do not estimate a score by hand.

No em dashes. Never promise rankings, calls or revenue. For a deeper pass on one pillar, suggest the local-seo, reputation-manager or ai-visibility-auditor agents.

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