By Rimagination
Google Earth Engine and geemap workflow bundle with bilingual 5,000+ dataset discovery, EasyGEE, GeoMaster, GEE Growth Diary, and a local MCP server.
Build, debug, and run Google Earth Engine Python and geemap workflows. Use for Earth Engine/geemap authorization, authentication, Cloud project setup, quotas, notebooks, browser map previews, Python scripts, 5,000+ official/community GEE dataset discovery, bilingual dataset selection by id/theme/task, dataset recommendation/comparison/verification, geospatial export, Sentinel/Landsat/MODIS/VIIRS/SAR/population collections, interactive maps, JavaScript-to-Python migration, local GIS integration, or OpenGeo/opengeos patterns such as GeoAgent, GeoLibre, leafmap, anymap, GEE agents, and catalog-driven assistants. Prefer this skill for reproducible GEE/geemap setup, notebooks, batch exports, map-first AI workflows, and auth/quota/project troubleshooting.
Secondary source-index and article-derived idea skill for the 153-article "GEE" WeChat album by GEEer成长日记. Use only when the user explicitly asks about that article collection, wants Chinese GEE cookbook inspiration, or needs source/title recall from the album. Do not use as the authority for current Earth Engine dataset ids, QA masks, scale factors, exports, or API behavior; use EasyGEE official-doc-grounded references first.
Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), vector and raster data operations, spatial statistics, point cloud processing, network analysis, cloud-native workflows (STAC, COG, Planetary Computer), and 8 programming languages (Python, R, Julia, JavaScript, C++, Java, Go, Rust) with 500+ code examples. Use for remote sensing workflows, GIS analysis, spatial ML, Earth observation data processing, terrain analysis, hydrological modeling, marine spatial analysis, atmospheric science, and any geospatial computation task.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
EasyGEE 把 Google Earth Engine、geemap、GeoMaster 方法知识和本地浏览器地图工作台打包成一个可复用插件。它的目标不是复刻 GEE 网页控制台,而是让 Agent 用一句自然语言完成数据查找、授权引导、配额检查、地图预览和本地/云端地理空间分析编排。
easygee/
├── .codex-plugin/ # Codex 插件元数据
├── .claude-plugin/ # Claude 插件元数据
├── assets/ # EasyGEE 图标与 logo
├── commands/ # Claude-style 命令入口
├── hooks/ # Hook 配置与轻量脚本
├── scripts/ # EasyGEE MCP server 启动入口
├── skills/
│ ├── easygee/ # GEE / geemap / 地图控制台工作流
│ ├── geomaster/ # 本地 GIS 与遥感方法知识
│ └── gee-growth-diary/ # GEEer成长日记蒸馏方法库
└── adapters/ # Codex、Claude、Zcode、Qoder 适配说明
给 Agent 的一句话安装:
帮我安装这个插件:[Rimagination/easygee](https://github.com/Rimagination/easygee)
Agent 看到这句话后应完成四件事:克隆或更新仓库、写入个人 marketplace、校验插件、在可用时执行 codex plugin add easygee@local-plugins。
在 Windows 上也可以直接运行这一行:
powershell -NoProfile -ExecutionPolicy Bypass -Command '$p=Join-Path $HOME "plugins\easygee"; if(Test-Path $p){ git -C $p pull --ff-only } else { gh repo clone Rimagination/easygee $p }; & (Join-Path $p "scripts\install-easygee.ps1")'
默认安装位置是:
%USERPROFILE%\plugins\easygee
安装脚本会把插件路径加入本地 marketplace。Codex 会从这里发现 EasyGEE:
C:\Users\Liang\.agents\plugins\marketplace.json
安装脚本也会校验插件结构;手动校验命令是:
python C:\Users\Liang\.codex\skills\.system\plugin-creator\scripts\validate_plugin.py C:\Users\Liang\plugins\easygee
直接用自然语言告诉 Agent 你要做什么。下面这些例子覆盖了最常见的日常用法:
帮我授权 geemap 到 example-ee-project-123456
打开 EasyGEE 地图,我想先看看北京朝阳公园附近,然后手动画一个 AOI
我想做北京朝阳公园 2024 年夏季 NDVI,帮我选择合适的 GEE 数据集并解释为什么
在 5000 多个数据集中查找 DEM,只看未弃用的官方产品,并比较前三个
我要评估山区洪水风险;我还没选数据,请按灾情、地形、降雨和暴露角色推荐一组数据
比较 COPERNICUS/DEM/GLO30_2024_1 和 USGS/SRTMGL1_003,并在写代码前核验最终 ID
把 Sentinel-2 真彩色和 NDVI 叠加到地图上,我想在浏览器里检查云和植被情况
查看我的 Earth Engine 项目配额、用量层级和剩余额度
帮我把当前 AOI 的 NDVI 结果导出到 Google Drive,并告诉我导出参数是否合理
我有一个本地 GeoJSON,帮我判断应该用 GEE 处理还是本地 GIS 处理,并生成可运行脚本
EasyGEE 默认把浏览器和凭据当作用户私有空间。Agent 可以生成授权计划、启动本地工具、查询安全摘要,但不能要求用户把 OAuth URL、验证码、token、credential 文件、service account key 或短期 access token 粘贴到聊天、日志、文档或提交里。
GeoMaster 以 skill snapshot 形式内置在插件中,而不是嵌套 git 仓库。这样插件保持自包含、轻量、离线可用,也避免把依赖目录、历史仓库状态或未知远端同步进插件包。
EasyGEE 参考并蒸馏了许多开放资料和项目经验。特别感谢:
npx claudepluginhub rimagination/easygeeGeoAI-powered skills for Claude Code: inspect geospatial files, download satellite imagery, search STAC catalogs, fetch Overture Maps data, process rasters, run AI object detection, and search session logs.
Geospatial SQL skill for BigQuery and Snowflake. Discovers Overture Maps and warehouse schemas, writes cost-safe SQL with mandatory dry-run, validates results, and optionally renders an interactive map.
MCP server for rendering GeoJSON vector layers into map images with basemaps
AI-powered 3D globe control for Claude Code — load tilesets, fly to locations, style layers, and query spatial data with natural language
Benchmark and optimize Zarr chunking strategies for multi-dimensional scientific datasets on cloud object stores (S3, GCS)
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses