# Long Horizon Itinerary Sequencing

> Use this when the user wants planning data about multi-day schedules, several cities, or chains of decisions that must stay consistent from one day to the next. Trigger it for requests like 'make week-long itinerary tasks', 'give me travel plans that span multiple stops', 'create schedule planning data where each day depends on the last one', or 'make long plans where an early routing choice affects later days.'

- Skill: `dingxingdi/long-horizon-itinerary-sequencing-2` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add dingxingdi/long-horizon-itinerary-sequencing-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/dingxingdi/long-horizon-itinerary-sequencing-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: dingxingdi (https://skillmd.com/u/dingxingdi)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/dingxingdi/long-horizon-itinerary-sequencing-2

---


# Skill: long-horizon-itinerary-sequencing
## 1. Capability Definition & Real Case
* **Professional Definition**: The ability to transform a multi-day objective into an ordered itinerary whose daily decisions remain coherent across time, location transitions, and interdependent travel logistics.
* **Dimension Hierarchy**: Open-World Real-World Planning->Information-Grounded Plan Construction->long-horizon-itinerary-sequencing
### Real Case
**[Case 1]**
* **Initial Environment**: A trip-planning environment supports 3-day, 5-day, and 7-day travel requests. For longer requests, the agent may need to visit two or three cities, account for inter-city connectivity, and distribute meals, attractions, lodging, and transportation across each day.
* **Real Question**: Develop a week-long travel itinerary for a group of six visiting three different cities in Texas, while maintaining a coherent day-by-day route and legal transitions between cities.
* **Real Trajectory**: Choose the first reachable city from the origin. Reserve daily structure around arrival and departure times. Insert inter-city transfers only on days where transport exists and downstream accommodations remain valid. Continue until the itinerary closes with a feasible return leg instead of ending mid-trip in the wrong city.
* **Real Answer**: A correct answer is a full multi-day itinerary with ordered city transitions, daily local activities that occur in the correct city, and a feasible final return segment.
* **Why this demonstrates the capability**: This case tests long-horizon sequencing because local day plans cannot be chosen independently. The planner must manage dependencies across time, including where the traveler wakes up, where they can eat or sightsee that day, and how one transfer constrains the next day’s options. It therefore probes persistent temporal coherence rather than one-shot recommendation quality.

## Pipeline Execution Instructions
To synthesize data for this capability, you must strictly follow a 3-phase pipeline. **Do not hallucinate steps.** Read the corresponding reference file for each phase sequentially:

1. **Phase 1: Environment Exploration**
   Read the exploration guidelines to discover raw knowledge seeds:
   `references/EXPLORATION.md`

2. **Phase 2: Trajectory Selection**
   Once Phase 1 is complete, read the selection criteria to evaluate the trajectory:
   `references/SELECTION.md`

3. **Phase 3: Data Synthesis**
   Once a trajectory passes Phase 2, read the synthesis instructions to generate the final data:
   `references/SYNTHESIS.md`