DANG-ai/SKILLER / skilllearnbench/skills/human_authored/travel-planning/travel-planning-workflow
travel-planning-workflow
VerifiedInvoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.9 KB |
SKILL.md
View on GitHub---
name: travel-planning-workflow
description: Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.
---
# Overview
**This skill provides a travel planning workflow. It is important to follow this workflow.**
**IMPORTANT:Do not forget to perform final validation and refinement.**
---
# Travel Planning Workflow
## Step 1: User Preference and Constraint Analysis
Extract the user's requirements and implicit preferences, including: Trip duration, Number of travelers, Budget constraints, Transportation constraints (e.g., no flights), Special requirements (e.g., pet-friendly accommodations), Food preferences (e.g., American, Mediterranean, Chinese, Italian)
**Default assumption:**
If not explicitly specified, each day should include at least one activity (i.e., no empty days).
---
## Step 2: Global Planning and Sequential Scheduling
### 2.1 Global Skeleton Construction
- Select candidate cities based on user constraints and dataset availability
- Construct a preliminary travel route (considering distance and feasibility)
- Allocate the total number of days across selected cities as a draft plan
---
### 2.2 Sequential Day-by-Day Planning
Generate the itinerary in chronological order:
Using the provided tools, and for each day:
- **Assign one attraction per day**, unless the user explicitly indicates that they do not want to go out.
- **Assign meals** based on cuisine preferences
- **Assign accommodation** (must satisfy constraints such as pet-friendly)
---
### 2.3 Iterative Adjustment and Backtracking
During planning, continuously validate feasibility. For example:
- If a city does not have enough attractions → reduce its allocated days
- If all cities combined still lack sufficient attractions → reselect cities
- If constraints are violated (budget, accomodations, etc.) → adjust previous steps
This step introduces a **feedback loop**, allowing the system to revise earlier decisions.
---
## Step 3: Important!! Final Validation and Refinement
Before returning the final itinerary, the agent must perform an explicit final validation pass. The validation should check:
- **All user constraints must be satisfied**, including transportation constraints (e.g., no flights), special requirements (e.g., pet-friendly accommodations, which should be explicitly reflected using keywords such as pet or animal), and food preferences (e.g., American, Mediterranean, Chinese, and Italian cuisines).
- **Each day includes at least one attraction, including both the first day and last day** (unless the user explicitly indicates that they do not want to go out.)
- **Travel transitions between cities are feasible**
- **The itinerary format is complete and consistent**, with no missing or contradictory information.
**Please refine the itinerary if any violations or inconsistencies are detected**
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |