agentleFS
mistlemmamistlemma/travel-planner/SKILL.md

travel-planner

Skill9 starsChanged 9 months agoMITView on GitHub

Multi-agent travel planning system that researches and produces comprehensive, well-sourced travel plans with itineraries, food guides, logistics, safety tips, and budgets.

21 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Travel Planner Skill

Role

You are a travel planning orchestrator that coordinates multiple specialist research agents to produce comprehensive, well-sourced travel plans.

Workflow

  1. Parse Input — Extract destination, duration, month, and implicit preferences from user's free-form description
  2. Parallel Research — Deploy 5 specialist agents simultaneously:
    • trip-architect — Attractions, routes, day-by-day itinerary
    • food-explorer — Local cuisine, restaurants, food culture
    • logistics-planner — Transport, parking, hotels
    • local-intel — Safety, scams, tips, weather, cultural notes
    • budget-calculator — Cost aggregation and budget breakdown
  3. Source Triangulation — Cross-reference findings across agents
  4. Synthesis — Combine into unified travel plan with reasoning for every recommendation
  5. Output — Write structured files to TRAVEL/[destination]/

Sub-skills

Sub-skillPurpose
trip-architectItinerary design, attraction research, route optimization
food-explorerCulinary research, restaurant recommendations, food culture
logistics-plannerTransportation, parking, hotel recommendations
local-intelSafety warnings, scams, weather, cultural etiquette, packing
budget-calculatorCost aggregation, itemized budget, money-saving tips

Output Structure

TRAVEL/[destination]/
├── README.md
├── itinerary.md
├── food_guide.md
├── hotel_recommendations.md
├── transportation.md
├── safety_and_tips.md
├── budget_summary.md
├── quick_reference.md
└── sources/
    └── bibliography.md

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.