local-seo-report
Skill0 starsChanged 36 days agoMITView on GitHub
Build a private local SEO client or owner report from Google Business Profile findings, Maps rank snapshots, competitors, reviews, citations and location-page evidence. Show coverage, comparable trends and a prioritized action plan with sources.
In this repository8 other files it gives its agents.
- citation-auditSkill
- gbp-auditSkill
- local-competitor-analysisSkill
- local-keyword-researchSkill
- location-page-seoSkill
- maps-rank-trackingSkill
- review-insightsSkill
- vibelocalSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Read WORKFLOW.md and METRICS.md.
- Distinctive: line 16
When owner-provided GBP/Search Console/conversion exports exist, add their actual definitions, periods and source.
≈ “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.
Files
Local SEO report and next actions
Read WORKFLOW.md and METRICS.md. Reuse collected/imported snapshots and the current owner context. Do not start fresh paid collection merely to fill a report. For unfamiliar imports, use import to bound and label raw JSON arrays; ask for total coverage only if needed and unknown.
Use report --snapshot ... for one or more supported snapshots to create a self-contained HTML report with escaped data, no remote assets and no tracking. Review its source badges, coverage counts, timestamps and collection warnings. Fixtures remain clearly fictional; imports remain unverified imports. The report's point cards summarize a grid without pretending to be a geographic map. Open the actual output when the host supports file preview.
Add a companion owner summary in Markdown: confirmed branch and period, decision-ready findings, what is unknown, and up to five actions. Each action needs priority reason, source/date, concrete deliverable, owner, approval needed and verification date. Distinguish factual corrections from proposed content experiments. Generic advice without evidence is a recommendation, not an observed defect.
For trends, use compare only with complete, equivalent Maps snapshots. Label newly found/no longer found separately from numeric movement. Show metric denominators, requested versus observed coverage and sample limits. Missing or failed data remains unknown. Public rank/profile data does not establish calls, bookings, revenue or private account performance.
When owner-provided GBP/Search Console/conversion exports exist, add their actual definitions, periods and source. Avoid mixing platform metrics or attributing a change to one edit without supporting evidence. Give a concise interpretation plus one next decision, rather than a fabricated ROI claim.
Review names, hidden addresses, reviewer text and customer information before sharing. The helper removes reviewer identity fields but cannot guarantee that free text contains no personal information. Deliver real artifact paths and the current evidence state. Sending the report, publishing changes or activating repeat collection requires separate approved scope.
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
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.

