Opengis All logo

Opengis All

Community
znlgis
opengis-all

Use when navigating end-to-end GIS workflows — GDAL CLI/API (ogr2ogr, gdalwarp, gdal_calc.py), qgis_process and PyQGIS analysis, GeoServer REST publishing, and OpenLayers/CesiumJS visualization. One-stop index covering the complete open-source GIS data pipeline.

Overview

Publisherznlgis
Repositoryopengis-skills
Skill nameopengis-all
Stars
76
Forks
12
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by znlgis on GitHub. Read the source before you install it.

Installation

Install the Opengis All AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/znlgis/opengis-skills/tree/main/gis/opengis-all
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/znlgis/opengis-skills.git /tmp/opengis-skills
mkdir -p .claude/skills
cp -r /tmp/opengis-skills/gis/opengis-all .claude/skills/opengis-all
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Opengis All in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Opengis All on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Opengis All is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

涵盖工具与项目:

概述

本文件将五个独立的 GIS 技能模块整合为一个端到端的 GIS 数据处理流程,涵盖以下阶段:

text
┌──────────────┐    ┌──────────────┐    ┌──────────────┐    ┌──────────────┐
│  阶段一       │    │  阶段二       │    │  阶段三       │    │  阶段四       │
│  数据获取     │ →  │  数据处理     │ →  │  空间分析     │ →  │  服务发布     │
│  与生成       │    │  与转换       │    │              │    │              │
│              │    │              │    │              │    │              │
│ · 读取各类    │    │ · 格式转换    │    │ · 缓冲区分析  │    │ · 创建工作空间 │
│   矢量/栅格  │    │ · 坐标系转换  │    │ · 叠加分析    │    │ · 上传数据    │
│ · 创建新数据  │    │ · 裁剪/合并   │    │ · 栅格计算    │    │ · 发布图层    │
│ · 查询元数据  │    │ · 元数据编辑  │    │ · DEM分析     │    │ · 配置样式    │
│              │    │              │    │ · 统计分析    │    │ · 图层组/缓存 │
└──────────────┘    └──────────────┘    └──────────────┘    └──────────────┘

工具映射:
  阶段一:GDAL CLI (ogrinfo/gdalinfo) · GDAL API · PyQGIS
  阶段二:GDAL CLI (ogr2ogr/gdalwarp/gdal_translate) · GDAL API · qgis_process · PyQGIS
  阶段三:qgis_process · PyQGIS · GDAL CLI (gdal_calc/gdal_contour) · GDAL API
  阶段四:GeoServer REST API

环境准备

GDAL(命令行 + API)

bash
# Linux (Debian/Ubuntu)
apt-get update && apt-get install gdal-bin python3-gdal libgdal-dev

# macOS
brew install gdal

# Conda(推荐,自动处理 C 库依赖)
conda install -c conda-forge gdal

# Docker
docker run -it osgeo/gdal:latest bash

# 验证
gdalinfo --version
ogrinfo --version
python3 -c "from osgeo import gdal; print(gdal.VersionInfo())"

QGIS(qgis_process + PyQGIS)

bash
# 安装 QGIS 3.44 LTR 或 4.x(qgis_process 从 3.16 开始可用)
# Ubuntu
apt-get install qgis qgis-plugin-grass

# 验证
qgis_process --version

# Headless 服务器环境(无窗口系统)
export QT_QPA_PLATFORM=offscreen

GeoServer

bash
# Docker 方式(推荐)
docker run -d -p 8080:8080 docker.osgeo.org/geoserver:3.0.2

# 验证
curl -u admin:geoserver "http://localhost:8080/geoserver/rest/about/version.json"

默认认证: 用户名 admin,密码 geoserver(HTTP Basic Auth)


阶段一(数据获取与信息查询)、阶段二(数据处理与转换)、阶段三(空间分析)的完整操作手册见 reference/data-stages.md

核心 API 与命令速查

阶段工具入口
数据获取/元数据GDAL CLIogrinfo -json(矢量)、gdalinfo -json(栅格)
格式转换GDAL CLIogr2ogr(矢量)、gdal_translate(栅格)
坐标统一GDAL CLIogr2ogr -t_srs / gdalwarp -t_srs
空间分析qgis_process / PyQGISqgis_process run <alg> --json / processing.run(...)
栅格波段运算GDAL CLIgdal_calc.py(NumPy 语法)
编程集成GDAL API / PyQGISosgeo.ogr/osgeo.gdal、QgsApplication + QgisInterface
服务发布GeoServer REST APIHTTP + JSON(工作空间 → 数据存储 → 图层 → 样式)

各阶段完整示例见 reference/data-stages.md 与 reference/workflow-cheatsheets.md。


阶段三:空间分析(速查)

任务命令入口
缓冲区qgis_process run native:buffer -- INPUT=... DISTANCE=... OUTPUT=...
交集/联合/差集native:intersection / native:union / native:difference
融合native:dissolve -- FIELD=...
空间连接native:joinattributesbylocation -- PREDICATE=0
按属性/位置提取native:extractbyattribute / native:extractbylocation
栅格波段运算gdal_calc.py -A nir.tif -B red.tif --calc="(A-B)/(A+B)"
DEM 分析`gdal_contour -i 10 / qgis_process run gdal:slope
插值成 DEMgdal_grid -a invdist:power=2:zfield=Z
栅格矢量互转gdal_polygonize.py / qgis_process run gdal:rasterize
地图渲染导出PyQGIS QgsMapRendererSequentialJob / QgsLayoutExporter

完整的 3.1-3.10 逐项示例(qgis_process、PyQGIS、GDAL Python API 三种写法)见 reference/data-stages.md。

阶段四(发布 GIS 地图服务)的完整 GeoServer REST 操作见 reference/data-stages.md 端到端工作流示例、内置算法速查、GDAL 命令速查、数据格式与环境变量见 reference/workflow-cheatsheets.md

典型工作流

端到端:Shapefile → 缓冲分析 → GeoServer 发布 → Web 预览

输入 data/roads.shp(EPSG:4326),输出 http://localhost:8080/geoserver/wms 上可用的图层 demo:roads_buffer。

  1. 探索数据:ogrinfo -so -al data/roads.shp 确认要素数与 CRS
  2. 统一格式与坐标系:ogr2ogr -t_srs EPSG:3857 roads_3857.gpkg data/roads.shp
  3. 空间分析:qgis_process run native:buffer -- INPUT=roads_3857.gpkg DISTANCE=500 OUTPUT=roads_buffer.gpkg
  4. 验证结果:ogrinfo -so roads_buffer.gpkg roads_buffer 核对方框与要素数
  5. 发布服务:GeoServer REST 建工作空间 → 上传 GeoPackage → 发布图层
  6. 前端预览:OpenLayers TileWMS 指向 /geoserver/wms,LAYERS: 'demo:roads_buffer'
bash
# 1~4:本地分析与验证
ogrinfo -so -al data/roads.shp
ogr2ogr -t_srs EPSG:3857 roads_3857.gpkg data/roads.shp
QT_QPA_PLATFORM=offscreen qgis_process run native:buffer -- \
  INPUT=roads_3857.gpkg DISTANCE=500 SEGMENTS=8 OUTPUT=roads_buffer.gpkg
ogrinfo -so roads_buffer.gpkg roads_buffer

# 5:发布(GeoServer 3.0.2,默认 admin/geoserver)
BASE=http://localhost:8080/geoserver/rest
curl -u admin:geoserver -X POST "$BASE/workspaces" \
  -H 'Content-Type: application/json' \
  -d '{"workspace":{"name":"demo"}}'

curl -u admin:geoserver -X PUT "$BASE/workspaces/demo/datastores/roads/file.gpkg?configure=all" \
  -H 'Content-Type: application/geopackage+sqlite3' \
  --data-binary @roads_buffer.gpkg

# 6:回读确认图层已发布
curl -u admin:geoserver "$BASE/layers/demo:roads_buffer.json"
js
// 6:OpenLayers 前端预览
import Map from 'ol/Map.js';
import View from 'ol/View.js';
import TileLayer from 'ol/layer/Tile.js';
import TileWMS from 'ol/source/TileWMS.js';

new Map({
  target: 'map',
  layers: [new TileLayer({
    source: new TileWMS({
      url: 'http://localhost:8080/geoserver/wms',
      params: { LAYERS: 'demo:roads_buffer', TILED: true }
    })
  })],
  view: new View({ center: [12968000, 4863000], zoom: 12 })
});

验收:curl -u admin:geoserver .../layers/demo:roads_buffer.json 返回 200 且含 "enabled": true;前端地图能看到缓冲区图形。任一步失败都不要继续后续阶段——先修当前阶段的产物。


常用环境变量

变量说明示例
QT_QPA_PLATFORMQt 平台插件(Headless 必需)offscreen
GDAL_DATAGDAL 数据文件目录/usr/share/gdal/
PROJ_LIBPROJ 数据文件目录/usr/share/proj/
GDAL_NUM_THREADSGDAL 处理线程数ALL_CPUS
GDAL_CACHEMAX块缓存大小(MB)512
CPL_DEBUG调试日志级别ON

常见问题

问题解决
无显示器服务器上 qgis_process 崩溃设置 QT_QPA_PLATFORM=offscreen
GeoServer 上传 Shapefile 失败打包为 ZIP,且 ZIP 根目录须含 .shp、.shx、.dbf、.prj
分析结果坐标错位全链路统一 CRS:ogr2ogr -t_srs / gdalwarp -t_srs / qgis_process run native:reprojectlayer
找不到 gdal_calc.py安装 GDAL Python 绑定(python3-gdal 或 conda 的 gdal),或改用 qgis_process run gdal:rastercalculator
大栅格/大矢量导致内存不足先裁剪或分块(gdal_translate -srcwin/-outsize),并调大 GDAL_CACHEMAX、启用 GDAL_NUM_THREADS
GeoServer REST 返回 401/403检查 HTTP Basic Auth(默认 admin/geoserver)与用户权限
PyQGIS 导入 qgis.core 失败需在 QGIS 自带 Python 环境运行,或正确配置 PYTHONPATH/QGIS_PREFIX_PATH

AI 使用建议

  • 本技能的组织:主文件给高频用法,完整参数表与高级示例在 reference/data-stages.md、reference/workflow-cheatsheets.md,需要时再展开;示例工程与生成的数据写到工作目录,不要改动技能目录本身。
  • 执行环境:命令在终端 / shell 中执行(Windows 用 PowerShell)。示例是 Linux/bash 写法,按平台改写 apt、/tmp、export 与反引号;Windows 路径加引号。
  • 先探测工具链:gdalinfo --version、qgis_process --version、python3 -c "from osgeo import gdal; print(gdal.VersionInfo())"、curl -u admin:geoserver "http://localhost:8080/geoserver/rest/about/version.json";缺哪个阶段就加载相邻技能(如 gis/gdal、gis/qgis-process)。
  • 分阶段交付:每阶段产物落盘到工作区(GeoPackage/COG/GeoJSON),下一阶段只读取产物;先用 ogrinfo -so、gdalinfo -json 看摘要,不要把大文件或大段输出贴进上下文。
  • 验证:转换后重新打开结果核对 CRS、范围、要素数;发布后用 curl 回读 REST 资源或 GetCapabilities;无显示器环境设置 QT_QPA_PLATFORM=offscreen;qgis_process 参数先用 qgis_process help <id> --json 确认。
  • 安全:gdal_edit.py、覆盖输出、GeoServer ?recurse=true 删除均不可逆;先备份并确认路径,安装 GDAL/QGIS、启动服务或使用数据库凭据前先征得用户同意。

相关技能

参考资源

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Opengis All AI skill do?

Use when navigating end-to-end GIS workflows — GDAL CLI/API (ogr2ogr, gdalwarp, gdal_calc.py), qgis_process and PyQGIS analysis, GeoServer REST publishing, and OpenLayers/CesiumJS visualization. One-stop index covering the complete open-source GIS data pipeline.

Why use Opengis All on TypingMind?

Because you install it once and use it with any model. Opengis All is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Opengis All in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/znlgis/opengis-skills/tree/main/gis/opengis-all. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Opengis All?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Opengis All?

As many as you like. As long as a model supports skills, you can use Opengis All with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Opengis All AI skill free?

Yes. It is published on GitHub by znlgis under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇