Trip Planner logo

Trip Planner

Community
borski
trip-planner

Full trip planning orchestration. Combines flight search, hotel search, and points optimization into one cost analysis. Use when the user says "plan a trip" or wants the complete picture for a destination.

Overview

Publisherborski
Repositorytravel-hacking-toolkit
Skill nametrip-planner
Stars
690
Forks
75
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by borski on GitHub. Read the source before you install it.

Installation

Install the Trip Planner AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/borski/travel-hacking-toolkit/tree/main/plugins/travel-hacking-toolkit/skills/trip-planner
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/borski/travel-hacking-toolkit.git /tmp/travel-hacking-toolkit
mkdir -p .claude/skills
cp -r /tmp/travel-hacking-toolkit/plugins/travel-hacking-toolkit/skills/trip-planner .claude/skills/trip-planner
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Trip Planner in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Trip Planner on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Trip Planner is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Companion reference skills. Load these for deeper context:

  • flight-search-strategy — full search workflow and source priority
  • lessons-learned — Seats.aero workflow and common failure modes (load before any award search)
  • points-valuations — CPP rules, opportunity cost
  • partner-awards — reachability through alliance + bilateral partnerships
  • award-sweet-spots — flag legendary redemptions
  • booking-guidance — booking flow + phone numbers + the "hold before transfer" rule
  • transfer-bonuses — live current transfer bonuses (weekly refresh) before recommending any transfer
  • stopovers — per-program stopover rules; can turn a one-trip plan into a multi-city itinerary at no extra mileage cost
  • award-holds — per-program hold rules; affects transfer timing decisions
  • round-the-world — when the trip request implies 3+ stops or multiple regions, RTW products may be cheaper than separate awards
  • status-match — when a user mentions wanting status or asks about elite tier shortcuts; covers free direct matches, paid concierge fees, and once-per-lifetime warnings

Trip Planner

"Plan a trip to Paris Aug 11-15" answered with one complete cost breakdown.

Orchestrates compare-flights, compare-hotels, transfer-partners, and trip-calculator into a unified trip analysis. Shows total trip cost in cash vs every available points strategy.

This is an orchestration skill. It tells the agent which skills to invoke and how to combine their outputs.

When to Use

  • "Plan a trip to Paris Aug 11-15"
  • "What's the cheapest way to do SFO to Tokyo for a week in September?"
  • "How much would a trip to Stockholm cost in points vs cash?"
  • Any request that involves both flights AND accommodation

When NOT to Use

  • Flight-only comparison (use compare-flights)
  • Hotel-only comparison (use compare-hotels)
  • Award calendar (use award-calendar)
  • "Should I use points?" without a specific trip (use trip-calculator)

Workflow

Step 1: Parse Trip Parameters

Extract from the user's request:

ParameterExampleRequired
OriginSFOYes
DestinationParis / CDGYes
Departure date2026-08-11Yes
Return date2026-08-15Yes (assume one-way if not given)
Travelers2 adultsDefault: 1
Cabin classBusinessDefault: Economy
PreferencesFHR hotels, nonstop flightsOptional

If anything is ambiguous, ask. Don't guess dates or travelers.

Step 2: Run Searches in Parallel

Launch ALL searches simultaneously. Don't wait for one to finish before starting another.

PARALLEL:
  1. compare-flights: origin → destination, departure date, cabin
  2. compare-flights: destination → origin, return date, cabin (if round-trip)
  3. compare-hotels: destination, checkin = departure, checkout = return

Each of these internally runs their own parallel sub-searches (Duffel, Ignav, seats.aero, Chase, Amex, SerpAPI, Trivago, LiteAPI, Airbnb, etc).

Step 3: Combine into Trip Cost Matrix

Build a table showing total trip cost for each strategy.

For each booking strategy, calculate total = outbound + return + hotel:

StrategyOutboundReturnHotel (4 nights)TotalPoints UsedCash Out of Pocket
All cash$4,200$3,800$1,200$9,2000$9,200
Flights: award, Hotel: cash$120 tax$95 tax$1,200$1,415110,000 UR$1,415
Flights: award, Hotel: FHR$120 tax$95 tax$8,284 (paid via points)$8,499110,000 UR + 828,400 MR$215
Flights: Chase portal, Hotel: Edit———varies540,000 UR$0
Flights: award, Hotel: Airbnb$120 tax$95 tax$780$995110,000 UR$995

Step 4: Calculate Value Scores

For each strategy, compute:

Points value = (all-cash total - cash out of pocket) / total points used × 100

This tells you the CPP you're getting across the whole trip, not just one component.

Example:

"Flights: award + Hotel: Airbnb"
All-cash equivalent: $9,200
Cash out of pocket: $995
Points saved: $9,200 - $995 = $8,205
Points used: 110,000 UR
Trip CPP: $8,205 / 110,000 × 100 = 7.5 cpp

Step 5: Present the Trip Plan

Trip: SFO → Paris, Aug 11-15, 2 adults, Business Class

✈️ Outbound: SFO → CDG, Aug 11

OptionSourcePrice/PointsCurrency
Cash (lowest)Duffel$4,200—
Flying Blueseats.aero55,000 + $120 taxChase UR (1:1)
Chase Portal Boostchase-travel180,000Chase UR

✈️ Return: CDG → SFO, Aug 15

OptionSourcePrice/PointsCurrency
Cash (lowest)Duffel$3,800—
Aeroplanseats.aero70,000 + $200 taxChase UR (1:1)

🏨 Hotels: Paris, Aug 11-15 (4 nights)

OptionSourcePer NightTotalPointsBenefits
SO/ Paris [EDIT]Chase$639$2,555127,756 URBreakfast, $100 credit
Le Bristol [FHR]Amex$1,849$8,284828,400 MR$100 credit, breakfast, upgrade
Marriott ChampsSerpAPI$289$1,156——
Airbnb: Marais 2BRAirbnb$195$780—Kitchen

💰 Trip Total by Strategy

#StrategyTotal CashPointsCPPRating
1Award flights (FB+AC) + Airbnb$1,115125,000 UR6.5⭐ Best value
2Award flights + Chase Edit hotel$2,870252,756 UR2.5Good convenience
3All cash$8,1360—Baseline
4Chase portal flights + Edit hotel$0487,756 UR1.7Most points
5Award flights + FHR hotel$8,599125,000 UR + 828,400 MRMixedLuxury

🎯 Recommendation:

Award flights via Flying Blue (out) + Aeroplan (return) = 125,000 Chase UR for $8,000 worth of business class flights. That's 6.4 cpp. Excellent.

For the hotel: Chase Edit SO/ Paris gives breakfast + $100 credit for $2,555 (or 127,756 UR at 2.0 cpp via boost). The Airbnb is cheapest at $780 but no breakfast or hotel amenities.

Best overall: Award flights + Airbnb if you want max savings. Award flights + Chase Edit if you want the hotel experience with benefits.

Step 6: Source Status

Always report which sources succeeded and which failed:

✅ Duffel: 45 outbound, 38 return
✅ Ignav: 40 outbound, 35 return
✅ Seats.aero: 12 award options outbound, 8 return
✅ Chase Travel: 300 outbound flights, 21 hotels
✅ Amex Travel: 292 outbound flights, 17 hotels
✅ SerpAPI: 25 hotels
✅ Trivago: 30 hotels
✅ LiteAPI: 22 hotels
✅ Airbnb: 18 listings
✅ Google Flights: 52 outbound
⏭️ Southwest: skipped (no SFO-CDG service)

Error Handling

NEVER fail silently. If any sub-search fails, note it and continue with what you have.

If flights fail but hotels succeed (or vice versa), present what you have and note the gap:

❌ Seats.aero: API timeout. Award flight pricing unavailable.
    Trip totals shown are cash-only and portal-only. Retry seats.aero for award options.

If ALL sources fail for one component, say so:

❌ All hotel sources failed. Cannot calculate trip total. Fix hotel search, then rerun.

Limitations

  • Round-trip cash prices from Duffel/Ignav may be cheaper than two one-ways. Note when this is the case.
  • Award pricing is one-way. The combined outbound + return award cost is the correct comparison against a round-trip cash fare.
  • Hotel pricing may vary between portal and direct booking. Note significant differences.
  • Chase portal pricing is dynamic Points Boost (~1.5-2.0 cpp on select bookings, not a guaranteed floor). The historical static 1.5x multiplier is gone. Pull the actual quote.
  • Trip totals are estimates. Taxes, fees, and exchange rates can change actual booking costs.

Frequently asked questions

What does the Trip Planner AI skill do?

Full trip planning orchestration. Combines flight search, hotel search, and points optimization into one cost analysis. Use when the user says "plan a trip" or wants the complete picture for a destination.

Why use Trip Planner on TypingMind?

Because you install it once and use it with any model. Trip Planner is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Trip Planner in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/borski/travel-hacking-toolkit/tree/main/plugins/travel-hacking-toolkit/skills/trip-planner. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Trip Planner?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Trip Planner?

As many as you like. As long as a model supports skills, you can use Trip Planner with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Trip Planner AI skill free?

Yes. It is published on GitHub by borski under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇