← 返回
未分类

透过桌面去旅游

This skill should be used when the user asks to identify, find, or look up the shooting location of their current desktop wallpaper/background image. It covers requests such as "Where was my wallpaper taken?", "Find the location in my desktop background", "查看我的桌面背景是在哪里拍的", "介绍一下我的壁纸拍摄地", and similar queries that involve reading the desktop wallpaper and geolocating the scene. Trigger phrases: wallpaper location, desktop background location, where was my wallpaper photo taken, identify wallpaper
>足不出户,每条通过电脑桌面了解全世界的旅游景点
哏儿都老码
未分类 community v1.0.1 2 版本 100000 Key: 无需
★ 1
Stars
📥 46
下载
💾 0
安装
2
版本
#latest

概述

Desktop Wallpaper Location Identifier

Identify the real-world shooting location of the user's current desktop wallpaper and

provide a rich introduction to that location.

Workflow

Follow these steps in order:

Step 1 — Get the wallpaper file path

Run the bundled script to obtain the absolute path of the current wallpaper:

python scripts/get_wallpaper_path.py
  • On Windows: reads from the registry key HKCU\Control Panel\Desktop\WallPaper;

falls back to the TranscodedWallpaper cache file for theme-based wallpapers.

  • On macOS: uses osascript to query System Events.
  • On Linux: tries gsettings (GNOME) then xfconf-query (XFCE).

If the script outputs an ERROR: line, report the problem to the user and stop.

Step 2 — Read the wallpaper image

Use the Read tool with the path returned by the script to load the image into

context. WorkBuddy is multimodal and can directly interpret the visual content.

If the path points to a file without a standard image extension (e.g. the Windows

TranscodedWallpaper cache has no extension), still pass it to Read—it is a

valid JPEG/PNG image and will be processed correctly.

Step 3 — Analyse the image

Carefully examine the image and identify:

  1. Scene type — natural landscape, urban skyline, architectural monument,

national park, etc.

  1. Visual clues — distinctive landforms, building styles, signage text, flags,

vegetation, water bodies, sky color/weather, and any other identifiable features.

  1. Candidate locations — list the top 1–3 candidate real-world locations with

reasoning for each.

Step 4 — Confirm the most likely location

Select the single most probable shooting location. State clearly:

  • Country / Region
  • Specific site name (e.g. "Torres del Paine National Park, Patagonia, Chile")
  • Confidence level (High / Medium / Low) and the key visual evidence that

supports the identification.

If the wallpaper is a digital illustration, abstract art, or a clearly synthetic

image with no identifiable real location, inform the user and stop here.

Step 5 — Introduce the location

Write a compelling, informative introduction to the identified location covering:

| Section | Content |

|---------|---------|

| 概况 / Overview | Location, country, administrative region, coordinates (approximate) |

| 自然地理 / Geography | Terrain, climate, notable natural features |

| 历史文化 / History & Culture | Historical background, cultural significance, famous events |

| 旅游亮点 / Travel Highlights | Best viewpoints, must-see attractions, nearby places of interest |

| 最佳旅行时间 / Best Time to Visit | Season recommendation and reason |

| 实用信息 / Practical Info | How to get there, tips for visitors |

Write in the same language the user used (default: Chinese). Use headings and

bullet points for readability. Aim for 400–800 words total.

Step 6 — Offer follow-up

End with a short prompt asking if the user wants to know more, e.g.:

> "如需了解更多关于该地点的信息(如签证要求、住宿推荐、摄影技巧等),欢迎继续提问!"

Important Notes

  • Privacy: The wallpaper path is read locally and never uploaded anywhere.

Only the image content (pixels) is analysed by the model within this session.

  • Low-confidence cases: When confidence is Medium or Low, present multiple

candidate locations and explain the ambiguity rather than guessing wrongly.

  • No internet access needed: Location identification is done entirely by the

model's visual understanding—no reverse image search or external API is required.

If the model is uncertain, say so honestly.

  • Non-photographic wallpapers: For paintings, illustrations, or computer-

generated art, skip geolocation and instead describe the artwork and its style.

版本历史

共 2 个版本

  • v1.0.1 使skill脚本功能更精准 当前
    2026-05-29 10:48 安全 安全
  • v1.0.0 Initial release
    2026-05-28 15:07 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

life-service

Caldav Calendar

asleep123
使用 vdirsyncer + khal 同步并查询 CalDAV 日历(iCloud、Google、Fastmail、Nextcloud 等)。适用于 Linux。
★ 244 📥 30,653
life-service

Weather

steipete
获取当前天气和预报(无需API密钥)
★ 455 📥 228,830
life-service

Sonoscli

steipete
控制Sonos音箱(发现/状态/播放/音量/分组)
★ 56 📥 85,164