maps-rank-tracking
Skill0 starsChanged 35 days agoMITView on GitHub
Check Google Maps positions for local service keywords across a defined grid or area, establish a local ranking baseline, or compare equivalent later snapshots. Keep Maps, Search local-pack and organic measurements separate.
In this repository8 other files it gives its agents.
- citation-auditSkill
- gbp-auditSkill
- local-competitor-analysisSkill
- local-keyword-researchSkill
- local-seo-reportSkill
- location-page-seoSkill
- review-insightsSkill
- vibelocalSkill
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
- Distinctive: line 8
Read WORKFLOW.md, ACTORS.md and METRICS.md.
≈ “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
Maps ranking baseline and comparison
Read WORKFLOW.md, ACTORS.md and METRICS.md. Confirm the branch and reviewed place ID/cid where possible. With only a name/domain, flag weaker matching and have the user verify found rows.
Start with 1–3 high-intent owner-confirmed services and a small grid, normally nine explicit coordinates, or the user's existing grid. Do not invent precise coordinates from a city name. Reuse supplied coordinates or resolve public location anchors with an authorized source. Agree on spacing/radius and label every point. Use exactly one selector per point. Keep language, device, depth and provider mode explicit. Do not change a series' settings silently.
Prepare the maps-ranks input and a live plan; collect only after the user approves its exact scope and costs. One keyword at nine points is nine checks. If the user asks for the Google Search local pack, use a distinct local-pack plan and label its output separately. The Maps tracker calls its field localPackRank for compatibility; it measures Maps result position and does not establish Search three-pack or organic position.
Collect using the confirmed receipt. Preserve missing/failed rows as unknown and valid not-found as null. Inspect match method, result URL and source date before summarizing. Generate the HTML report with report; it contains point cards and an evidence table. Report observed coverage, top-3 share of valid observed checks, found/not-found counts and mean rank among found checks with the denominator.
For a later run, reuse the same identity, keywords, grid and search settings. Use compare --before ... --after ...; do not force incompatible data through the comparison. Changes from/to not-found remain categorical; the helper never invents rank 101. Explain that movement does not establish that an SEO edit caused it.
Deliver the actual snapshot/report paths, one interpretation supported by the observed rows and a specific next action. For an unfinished run, leave its receipt and collection/reconciliation step. Tracking means repeatable snapshots here; no monitor is active unless the user separately authorizes and the host confirms a schedule.
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.