- Home
- Skills
- Business & Operations
- Trip Planner
Trip Planner
A skill for planning a long trip (many bases, ferries, bookings and small producers with odd hours) without losing track of where you are each night.
Free
Works with the AI Agents you already use
Trip Planner
Example session with this skill installed
Check the plan in examples/sample-trip/itinerary.md before I book anything.
- Read your context and instructions
- Compiled the trip planner
Summary
Ran the pre-trip audit on the sample Lisbon / Alentejo itinerary (5 nights, 14 to 19 May 2027). The date grid has no errors. Two days carry unverified items and three decisions are still open. Nothing was booked or sent.
Lint output
$ python3 scripts/itinerary_lint.py examples/sample-trip/itinerary.md
ERRORS: none
TO CHECK
16 May: has an unverified or TBD item.
18 May: has an unverified or TBD item.
Open: Confirm Comporta to Lisbon drive time
Open: Book Saturday dinner in Lisbon
Open: Email the winery for Tuesday afternoon hours (local language first)
Fixed now
Nothing needed fixing: every weekday matches its date, there are no gaps or repeated dates, the night count is 5, and each day starts where the previous one ended.
Needs your action
| Item | Date | Why |
|---|---|---|
| Book Saturday dinner in Lisbon | Sat 15 May | Saturday needs a reservation |
| Email the winery about Tuesday afternoon hours | Tue 18 May | Hours not confirmed by the winery; draft in Portuguese with English beside it |
Still unverified
- Lisbon to Comporta drive time (~1h30) is an estimate. Check a route planner close to the date.
- Monday closures in Comporta are likely but not confirmed; dinner on 17 May is planned at the hotel.
Next steps
- Add closing days to the restaurant and producer trackers, then run
closure_check.py --year 2027on the CSV exports. - Approve the winery email draft and send it yourself.
Connects securely to your tools. The creator never sees your data.
About this skill
A skill for planning a long trip (many bases, ferries, bookings and small producers with odd hours) without losing track of where you are each night. It grew out of a real 27-night road trip through Italy: 14 overnight bases, 13 ferry crossings and 26 small wineries, dairies and shops.
It contains no trip data. You bring your own itinerary, trackers and constraints.
What it does
- One record.
itinerary.mdsays where you are each night. When memory, a tracker or a chat disagrees with it, the file wins. - Constraints first. Budget per person, rating floor, dietary limits, blocked time windows and gym needs live in
config.yamland are checked before anything is suggested. - Verify at the source. Booking sites and map listings are leads. Hours and closing days count as facts only when the business confirms them; everything else is marked unconfirmed.
- Local-language search. Small producers post hours in their own language, so the agent searches with configured local terms.
- Bilingual emails. Drafts to businesses in their language with English beside it, formal register, at most three questions. It drafts; it never sends, books or pays.
Tasks
Find and vet hotels, scout restaurants for given nights, research wineries and other producers, write to a business, run a pre-trip audit, and keep an as-traveled log.
Scripts
Three small Python scripts (standard library only, with tests):
itinerary_lint.pychecks weekdays against dates, gaps, repeated dates, the night count, and that each day starts where the last ended.closure_check.pyflags any planned visit on a place's closing day and lists places whose closing day is unknown.name_dedupe.pyfinds places already in a tracker before new ones are added.
Source
MIT licensed. https://github.com/pegahcarter/agent-skills/tree/main/trip-planner
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.
Hours on a business's own site are often stale for the shoulder season; an email reply is the only confirmation that held up. Closing-day checks are only as good as the tracker, and blank cells are reported as unknown. Drive times stay estimates until checked near the date. The scripts read CSV, so export .xlsx or Google Sheets tabs first.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 14 days ago
- Free with an Agensi account
- Software
Python 3
Permissions
Shell runs the three bundled Python scripts. Read and write cover your itinerary, tracker files and config.yaml. Network access is for web searches on hotels, restaurants and producers. It drafts emails but never sends them, and never books or pays.