Token导航 LogoToken导航

Agent Skill · 研究检索

travel-map-generator(旅行地图生成器)

travel-map-generator 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

travel-map-generator 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为操作浏览器;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 33,646。

总安装 2,327周安装 96GitHub Stars 公开资料未说明下载 760核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:travel-map-generator(旅行地图生成器)
来源仓库:https://github.com/kensonh/travel-map-generator
安装命令:
openclaw skills install travel-map-generator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install travel-map-generator

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

生成吉卜力风格手绘地图PNG,附带卡通景点插图与路线标注。适合喜欢艺术化表达与视觉记录的用户。使用方式:输入目的地与兴趣点自动生成定制地图。需注意图像版权与商用许可问题。travel-map-generator 属于研究检索类 Skill,可作为该场景下的辅助能力补充。安装前请确认是否生成临时文件或缓存数据。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install travel-map-generator;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

travel-map-generator 怎么安装?

在终端执行 openclaw skills install travel-map-generator。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

travel-map-generator 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

travel-map-generator 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

travel-map-generator 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

travel-map-generator 用的人多吗?

公开数据是累计安装 2,327 次,近一周安装 96 次,下载 760 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

travel-map-generator 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
travel-map-generator

旅行地图生成器 · 本页

2,327—操作浏览器MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
travel-map-generator-skill
description
>-
license
MIT
metadata
author
Qoder Community
version
1.1.0
created
2026-04-02
last_reviewed
2026-04-02
review_interval_days
90
dependencies
type
python-package
install
pip3 install Pillow
schema_expectations
expected_keys

/travel-map-generator — Ghibli Style Travel Map Generator

You are an expert travel map illustrator. Your job is to generate beautiful, hand-drawn style travel itinerary maps in Studio Ghibli / Hayao Miyazaki aesthetic.

Trigger

User invokes /travel-map-generator followed by their input:

/travel-map-generator Create a Ghibli-style map of Tokyo
/travel-map-generator I'm going to Paris, make me a cute illustrated map
/travel-map-generator Draw a travel map for Rome with Colosseum, Vatican, Trevi Fountain

Or activate naturally:

Make me a travel map for Kyoto
Generate a cartoon itinerary map
I need a hand-drawn map of my trip

Generate a single illustrated PNG travel map in Studio Ghibli / Miyazaki style. The map shows a destination city with cartoon POI icons at real coordinates, connected by a hand-drawn numbered route.

Quick Start

Follow the seven-phase workflow below in order. Do not skip phases. Each phase specifies which tools to use and what outputs to produce.

Prerequisites: Run the dependency installer first:

python3 SKILL_DIR/scripts/install_deps.py

Phase 1: Setup & Input Gathering

Goal: Extract travel info from conversation and prepare the workspace.

  1. Parse the conversation to identify:

- Destination city (required) - Specific attractions/POIs the user mentioned (optional) - Visit order if the user specified a sequence (optional)

  1. If the city is ambiguous (e.g., "Springfield"), ask the user to clarify.
  2. Create a temporary workspace:
   mkdir -p /tmp/travel-map-CITY_SLUG

Use a URL-safe slug of the city name (e.g., tokyo, new-york).

Output: City name, list of POI names (may be empty), visit order (may be null).


Phase 2: POI Discovery (if needed)

Goal: Find top attractions if the user didn't specify any.

Skip this phase if the user already named specific attractions.

  1. Use the WebSearch tool to find popular attractions:
   Query: "top attractions things to do in {CITY}"
  1. Extract 5-8 popular attractions from the search results.
  1. Present the discovered attractions to the user and confirm before proceeding.

Output: Final list of POI names (typically 3-10, ideally 5).


Phase 3: Coordinate Collection

Goal: Get the latitude/longitude of each POI.

Use WebSearch to find coordinates for each POI:

Query: "{POI_NAME} {CITY} coordinates latitude longitude"

Or use the Task tool with browser-agent:

  1. Navigate to https://www.google.com/maps/search/{POI_NAME}+{CITY}
  2. Extract coordinates from the URL format @{lat},{lng},{zoom}z

Collect all POI data into a structured list:

[
  {"name": "POI Name", "lat": 35.6586, "lng": 139.7454},
  ...
]

Important: Record coordinates with at least 4 decimal places for accuracy.

Output: List of POIs with name, lat, lng.


Phase 4: Map Background Generation

Goal: Generate a map background covering all POIs.

Option A: Use ImageGen (Recommended)

Generate an artistic map background directly:

ImageGen prompt: "A hand-drawn illustrated bird's-eye-view map of {CITY} in Studio Ghibli watercolor style, showing major streets as soft pencil lines, rivers in gentle blue watercolor, parks in soft green, buildings as tiny charming houses, warm parchment background, Miyazaki aesthetic, no text labels, map only"
Size: 1536x1024
Output: /tmp/travel-map-CITY_SLUG/stylized_map.png

Option B: Google Maps Screenshot + Stylization

If you need precise geographic accuracy:

  1. Compute the optimal viewport:
python3 -c "
import sys; sys.path.insert(0, 'SKILL_DIR/scripts')
from utils import compute_viewport
pois = POI_LIST_AS_PYTHON
vp = compute_viewport(pois, 1536, 1024)
print(f\"center_lat={vp['center_lat']}, center_lng={vp['center_lng']}, zoom={vp['zoom']}\")
"
  1. Use Task tool with browser-agent:

- Navigate to https://www.google.com/maps/@{center_lat},{center_lng},{zoom}z - Take screenshot: /tmp/travel-map-CITY_SLUG/map_screenshot.png

  1. Stylize the screenshot:
python3 SKILL_DIR/scripts/stylize_map.py \
  --input /tmp/travel-map-CITY_SLUG/map_screenshot.png \
  --output /tmp/travel-map-CITY_SLUG/stylized_map.png

Output: stylized_map.png + viewport metadata dict.


Phase 5: POI Icon Generation

Goal: Generate cartoon icons for each POI.

For each POI, call the ImageGen tool:

  • Name: poi_{SLUG}.png (e.g., poi_tokyo_tower.png)
  • Prompt:
  A charming Studio Ghibli watercolor illustration of {POI_FULL_NAME} in {CITY},
  Hayao Miyazaki art style, soft warm pastel colors, whimsical and dreamy,
  centered composition, simple clean background in solid pale cream color,
  small cute details, no text or labels, icon sticker style illustration
  • Size: 1024x1024
  • Output path: /tmp/travel-map-CITY_SLUG/poi_{SLUG}.png

Generate all POI icons concurrently. If any look unsatisfactory, regenerate with a more specific prompt.

Output: One poi_*.png per attraction.


Phase 6: Compositing

Goal: Assemble the final illustrated travel map.

  1. Build the configuration JSON file at /tmp/travel-map-CITY_SLUG/config.json:
{
  "city_name": "City Name (Display Title)",
  "viewport": {
    "center_lat": CENTER_LAT,
    "center_lng": CENTER_LNG,
    "zoom": ZOOM,
    "width": 1536,
    "height": 1024
  },
  "pois": [
    {
      "name": "POI Display Name",
      "lat": LAT,
      "lng": LNG,
      "icon_path": "/tmp/travel-map-CITY_SLUG/poi_SLUG.png",
      "order": ORDER_NUMBER_OR_NULL
    }
  ]
}
  • Set "order" to the 1-based visit sequence if the user specified an order
  • Set "order" to null for automatic route optimization
  • Use proper formatting for "city_name" (appears as title banner)
  1. Run the compositing script:
python3 SKILL_DIR/scripts/composite.py \
  --map /tmp/travel-map-CITY_SLUG/stylized_map.png \
  --config /tmp/travel-map-CITY_SLUG/config.json \
  --output /tmp/travel-map-CITY_SLUG/final_map.png
  1. Verify the output by reading the final image.

Output: final_map.png — the complete illustrated travel map.


Phase 7: Delivery

Goal: Present the result to the user.

  1. Copy the final map to the user's working directory:
   cp /tmp/travel-map-CITY_SLUG/final_map.png ./CITY_SLUG_travel_map.png
  1. Show the image to the user using the Read tool.
  1. Summarize what was generated:

- City name - Listed attractions in route order - Route description (user-specified or auto-computed) - Output file path

  1. Offer modifications:

- "Want to add or remove any attractions?" - "Want to change the visit order?" - "Want to adjust the map style?"


Image Prompt Tips

For better ImageGen results with the Ghibli style:

  • Always include "Studio Ghibli", "Hayao Miyazaki", and "watercolor" in the prompt
  • Specify "pale cream background" to make icons easier to composite
  • Use "icon sticker style" to get centered, isolated illustrations
  • Add landmark-specific details (e.g., "red torii gate" for Fushimi Inari)
  • Avoid requesting text or labels in the generated images

Script Reference

ScriptPurposeKey Arguments
install_deps.pyInstall Pillow(none)
utils.pyCoordinate math, sizing, routing(imported by other scripts)
stylize_map.pyMap screenshot → Ghibli style--input, --output
composite.pyFinal map assembly--map, --config, --output

For coordinate mapping math details, see coordinate-mapping.md.

Error Recovery

IssueSolution
Google Maps CAPTCHA/blockAsk user for coordinates manually
POI not foundSkip it, inform user, continue with remaining
Pillow not availableRun pip3 install Pillow manually
Poor stylizationUse ImageGen for map background instead
Icons overlap heavilyThe composite script handles this automatically
ImageGen failsRetry with simplified prompt or different seed

平台分布

OpenClaw

83.26%
按下载量换算633

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills