google-maps-travel-planning
Skill480 starsChanged 48 days agoMITView on GitHub
Build evidence-backed day trips, multi-day itineraries, and efficient stop sequences with Google Maps data through the standalone CLI. Use when the desired output is a practical travel plan, not merely a route or list of places.
- Reads credentials
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- mcp-google-map-projectSkill
- google-maps-local-seoSkill
- google-mapsSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Read ../_shared/content-attribution.md before presenting reviews, photos, or Google-generated summaries.
- Very specific: line 20
Read references/travel-planning.md before designing the itinerary.
- Very specific: line 21
Use maps_search_places to find candidate anchors, then group nearby anchors into one-direction daily arcs.
- Very specific: line 22
Use maps_search_along_route for meals and breaks between anchors.
- Distinctive: line 24
Check weather and air quality when they affect the plan.
- Distinctive: line 25
When useful, produce a numbered static map after the stop order is final.
- Distinctive: line 40
Do not infer that a venue is accessible, open, safe, or suitable when the API response does not establish it.
- Distinctive: line 41
Do not silently substitute web estimates for unavailable Google Maps results.
≈ “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
Google Maps Travel Planning
Build a time-ordered itinerary whose geography, travel times, opening constraints, and along-route stops have been checked. Use the standalone CLI; no MCP connection is required.
Before calling the CLI
- On the first call in a session, or after an execution failure, read
../_shared/setup-and-diagnostics.mdand run the non-billable local preflight. - The user must supply
GOOGLE_MAPS_API_KEY. Never expose its value. - Read
../_shared/content-attribution.mdbefore presenting reviews, photos, or Google-generated summaries.
Workflow
- Establish destination, dates or duration, fixed anchors, mobility constraints, pace, and relevant preferences. Ask only for omissions that materially change the itinerary.
- Read
references/travel-planning.mdbefore designing the itinerary. - Use
maps_search_placesto find candidate anchors, then group nearby anchors into one-direction daily arcs. - Use
maps_search_along_routefor meals and breaks between anchors. Usemaps_place_detailsfor hours, ratings, and source metadata. - Validate every day with
maps_plan_routeormaps_directions. Do not present estimated timing as validated timing. - Check weather and air quality when they affect the plan. Respect regional weather limitations described in the reference.
- When useful, produce a numbered static map after the stop order is final.
- Present a day-by-day schedule with travel time, visit duration, reservations or opening-hour caveats, and clearly marked fallbacks.
CLI
npx -y @cablate/mcp-google-map exec <tool> '<json_params>'For exact tool parameters, read ../google-maps/references/tools-api.md only for the tools selected by the plan.
Boundaries
- A request for only A-to-B directions or a simple multi-stop ordering belongs to
google-maps. - A request to assess business visibility or local search rankings belongs to
google-maps-local-seo. - Do not infer that a venue is accessible, open, safe, or suitable when the API response does not establish it.
- Do not silently substitute web estimates for unavailable Google Maps results; identify the alternate source.
References
references/travel-planning.md: required methodology, timing budgets, geographic arcs, and anti-patterns.../google-maps/references/tools-api.md: exact parameters and response shapes for selected tools.../_shared/setup-and-diagnostics.md: first-run and failure recovery.../_shared/content-attribution.md: Places presentation requirements.
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.

