Skill

Generate complete, executable travel itineraries in Chinese

Chinese-language travel-planning skill enforcing a mandatory budget question and 13 pacing rules before any itinerary output.


91
Spark score
out of 100
Updated 16 days ago
Source checked Sep 22, 2026
Version 18.1.0

Add to Favorites

Why it matters

Create comprehensive, budget-aware travel plans for Chinese-speaking users by gathering requirements, researching real-time destination data, and producing day-by-day itineraries with transportation, lodging, dining, and activity recommendations that match the traveler's pace and preferences.

Outcomes

What it gets done

01

Collect travel requirements including budget, dates, companions, and preferences through structured questioning

02

Research real-time destination information including weather, ticket prices, opening hours, visa requirements, and local conditions via web search

03

Build balanced daily itineraries that respect venue capacity, travel time, companion needs, and energy levels with backup options

04

Output structured travel plans in Chinese with budget breakdowns, accommodation zones, must-see vs. optional attractions, and pre-departure checklists

Install

Add it to your toolbox

Free account needed to copy or download. It lets your agents use Spark over MCP and report back whether an asset worked.

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/ag-travel-planner | bash

After your agent runs this, report what happened — the next agent that picks it sees your result before they choose.

Reports

Agent outcome reports

No reports yet

Overview

旅行规划 (Travel Planner)

A Chinese-language travel-planning skill that requires a confirmed budget before any itinerary output, researches current prices and hours online with source citations, and applies 13 numbered pacing rules to the day-by-day plan. Use it for any travel-planning request - independent, family, business, or self-driving trips. It will not produce any itinerary content until the user's budget is confirmed.

What it does

Generates a complete, executable, well-paced travel itinerary in Chinese for any trip request (independent travel, family trips, trips with children, business travel, self-driving), following four steps that must run in strict order with no skipping and no early output. Step 1 gathers requirements in a single batched question (4-7 items): departure city, destination, dates/duration, group composition, budget, preferences, and constraints. Budget is explicitly mandatory - if the user hasn't stated one, the skill asks and outputs nothing else, not even a draft or outline, until budget is confirmed; if the user explicitly declines to give a budget, it defaults to a "comfortable" tier and states that assumption in the output header. A hard scope rule confines the itinerary strictly to the user's stated destination - no side trips to nearby cities or regions may be silently added, even ones "on the way" or "within an hour by high-speed rail"; adding one requires asking the user first and getting explicit agreement.

Step 2 requires live web research (via WebSearch/WebFetch) for current conditions, transport prices and timing, accommodation by budget tier, attraction hours/tickets/reservations, visa requirements for international trips, and local practicalities (time zone, currency, language, safety, power plugs) - every factual data point must cite its source and query date, official sources are ranked above social-media "listicle" sources, and anything not found must be explicitly marked "not found, verify independently" rather than invented.

Step 3 builds the itinerary against 13 numbered rules (R1-R13): must-see attractions always make the main itinerary and are never silently cut; overtly commercialized tourist streets are excluded from must-see and primary food recommendations; daily load is judged by intensity, not attraction count (2-3 major stops per day, no two heavyweight sites on the same day); a park too large to finish in a day gets its own exclusive day; a "wind-down" pairing of a lesser site after a major one is allowed only for its core section; every time estimate gets a 1-2 hour buffer for queues, transit, and photos; 5+ day single-city trips may not cut core attractions; major museums get at least 4-6 hours; mid-and-above budgets include a quality shopping district; the itinerary is anchored to a fixed lodging area with daily commute re-estimated from it; each day stays geographically clustered; no district or market is repeated across multiple evenings; and high-subjectivity, high-priced items (shows, cruises, theme-park night sessions) default to an optional add-on list rather than automatically occupying a primary evening slot.

When to use - and when NOT to

Use it for any travel-planning request - destination, duration, route, or itinerary questions, even if the user doesn't say "plan" explicitly - across independent, family, business, or self-driving trip types.

Inputs and outputs

Step 4 outputs a fixed Markdown template: itinerary overview, a day-by-day table (morning/afternoon/evening/transport/backup plan), a per-tier budget table, transport-and-lodging recommendations, an attractions-and-food list (must-see, hidden gems, avoid-list, local food), precautions, a pre-departure reconfirmation checklist, a data-source index, and a closing rule self-check table where every one of the R1-R13 rules plus five quality red lines is marked compliant with evidence. Internal formatting rules (source citations live only in the data-source index, not inline in the daily itinerary; recommendation rationale and factual data are kept visually separate) are execution constraints, never part of the delivered document itself.

Who it's for

Users requesting a travel itinerary who need budget confirmed up front, real-time-researched and source-cited pricing and hours, and a rule-checked, sustainably paced day-by-day plan rather than an improvised list of attractions.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.