Agent skill

Antv L7

by antvis in antvis/L7

Comprehensive guide for AntV L7 geospatial visualization library.

MITAuto-check passedData & Analytics

Install Antv L7

skills CLI
$ npx skills add antvis/L7 --skill antv-l7 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install antvis/L7 antv-l7 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/antvis/L7.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/l7 .claude/skills/antv-l7 && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
antv-l7
GitHub stars
4.1k
Token cost
~1.4k tokens
SKILL.md length
202 words
Files
40 (incl. references)
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Comprehensive guide for AntV L7 geospatial visualization library.

  • Works in 5 steps: 场景初始化优先: 始终从创建 Scene 开始 → 数据格式规范: 优先使用 GeoJSON 标准格式 → 性能优先: 大数据量时使用数据过滤和聚合 → …
  • Create interactive maps with WebGL rendering
  • SKILL.md covers Quick Start, Core Workflow, 📚 Reference Documentation and 使用指南, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Antv L7 is an agent skill from antvis/L7. Comprehensive guide for AntV L7 geospatial visualization library. Use when users need to: (1) Create interactive maps with WebGL rendering (2) Visualize geographic data (points, lines, polygons, heatmaps) (3) Build location-based data dashboards (4) Add map layers, interactions, or animations (5) Process and display GeoJSON, CSV, or other spatial data (6) Integrate maps with AMap (GaodeMap), Mapbox, Maplibre, or standalone L7 Map (7) Optimize performance for large-scale geographic datasets

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 44 other files, including reference files (for example `COMPLETENESS_REPORT.md`, `README.md` and `index.md`).

It sits in Data & Analytics, covering Geospatial analysis, 3D graphics and WebGL and Performance optimization. It works with Mapbox and JavaScript. The repository describes itself as: 🌎 Large-scale WebGL-powered Geospatial Data Visualization analysis engine. The licence is MIT.

When your agent uses it

  • Create interactive maps with WebGL rendering
  • Visualize geographic data (points
  • Build location-based data dashboards
  • Process and display GeoJSON

Example prompts

  • “/antv-l7”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 场景初始化优先: 始终从创建 Scene 开始
  2. 数据格式规范: 优先使用 GeoJSON 标准格式
  3. 性能优先: 大数据量时使用数据过滤和聚合
  4. 渐进增强: 先实现基础功能,再添加交互和动画
  5. 错误处理: 添加事件监听和数据验证

What it can do on your machine

Read from SKILL.md and the folder at commit 6e3dbfe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Antv L7 loads about 1.4k tokens when it runs, and up to ~92k if it reads all its reference files. Until then it costs about 126 tokens; SKILL.md has 202 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~92k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from antvis/L7 at commit 6e3dbfe, republished under its MIT licence (© antvis). 202 words, ~1,395 tokens.

Download SKILL.mdSave it as .claude/skills/antv-l7/SKILL.md (or your agent's skills folder). This skill also uses 39 other files; get the full folder from GitHub.
name
antv-l7
description
Comprehensive guide for AntV L7 geospatial visualization library. Use when users need to: (1) Create interactive maps with WebGL rendering (2) Visualize geographic data (points, lines, polygons, heatmaps) (3) Build location-based data dashboards (4) Add map layers, interactions, or animations (5) Process and display GeoJSON, CSV, or other spatial data (6) Integrate maps with AMap (GaodeMap), Mapbox, Maplibre, or standalone L7 Map (7) Optimize performance for large-scale geographic datasets
license
MIT

AntV L7 Geospatial Visualization

AntV L7 是基于 WebGL 的大规模地理空间数据可视化引擎,支持多种地图底图和丰富的可视化图层类型。

Quick Start

创建最简单的 L7 地图应用:

javascript
import { Scene, PointLayer } from '@antv/l7';
import { GaodeMap } from '@antv/l7-maps';

// 1. 初始化场景
const scene = new Scene({
  id: 'map',
  map: new GaodeMap({
    center: [120.19, 30.26],
    zoom: 10,
    style: 'light',
  }),
});

// 2. 添加图层
scene.on('loaded', () => {
  const pointLayer = new PointLayer()
    .source(data, {
      parser: { type: 'json', x: 'lng', y: 'lat' },
    })
    .shape('circle')
    .size(10)
    .color('#5B8FF9');

  scene.addLayer(pointLayer);
});

Core Workflow

L7 的典型开发流程:

1. 场景初始化 (Scene) → 2. 数据准备 → 3. 创建图层 (Layer) → 4. 添加交互 → 5. 优化性能

📚 Reference Documentation

详细文档按领域组织,根据需要加载:

基础功能 (references/core/)
  • scene.md - Scene 初始化、生命周期、方法
  • map-types.md - GaodeMap、Mapbox、Maplibre、Map 的配置
数据处理 (references/data/)
  • geojson.md - GeoJSON 格式、解析、转换
  • csv.md - CSV 数据加载和处理
  • json.md - JSON 数据、OD 数据、路径数据
  • parser.md - Parser 配置、Transform 转换
  • source-raster.md - 栅格数据源(GeoTIFF、多波段、遥感影像)
图层类型 (references/layers/)
视觉映射 (references/visual/)
  • mapping.md - 颜色、大小、形状映射
  • style.md - 透明度、描边、纹理等样式
交互组件 (references/interaction/)
动画效果 (references/animation/)
性能优化 (references/performance/)

使用指南

按用户需求选择文档
用户请求示例加载的文档
"创建一个地图"core/scene.md, core/map-types.md
"显示点位数据"layers/point.md, data/geojson.md
"绘制路径"layers/line.md
"热力图"layers/heatmap.md
"加载卫星影像"layers/tile-raster.md, data/source-raster.md
"添加点击事件"interaction/events.md
"显示弹窗"interaction/popup.md, interaction/layer-popup.md
"添加标注"interaction/components.md, interaction/marker-layer.md
"添加控件"interaction/controls.md
技能组合模式

复杂需求需要组合多个技能:

城市可视化 = scene + polygon + point + events + popup
轨迹动画 = scene + line + animation
热力分析 = scene + heatmap + data/json
依赖检查

使用 metadata/skill-dependency.json 检查技能依赖关系:

json
{
  "point-layer": {
    "requires": ["scene-initialization"],
    "optional": ["source-geojson", "color-mapping"],
    "nextSteps": ["event-handling", "popup"]
  }
}

版本信息

  • 当前版本: L7 2.x
  • 浏览器支持: Chrome ≥60, Firefox ≥60, Safari ≥12
  • 坐标系: WGS84 (地理坐标) / Plane coordinates (独立 Map)
  • 底图: 高德地图、Mapbox、Maplibre、L7 Map (独立)

最佳实践

  1. 场景初始化优先: 始终从创建 Scene 开始
  2. 数据格式规范: 优先使用 GeoJSON 标准格式
  3. 性能优先: 大数据量时使用数据过滤和聚合
  4. 渐进增强: 先实现基础功能,再添加交互和动画
  5. 错误处理: 添加事件监听和数据验证

快速参考

常用导入
javascript
// 核心
import { Scene } from '@antv/l7';
import { GaodeMap } from '@antv/l7-maps';

// 图层
import { PointLayer, LineLayer, PolygonLayer, HeatmapLayer } from '@antv/l7';

// 组件
import { Popup, Marker } from '@antv/l7';
地图样式选项
  • 'light' - 浅色风格
  • 'dark' - 深色风格
  • 'normal' - 标准风格
  • 'satellite' - 卫星影像
  • 'blank' - 空白底图(独立 Map)
坐标格式
javascript
[经度, 纬度]; // [120.19, 30.26]
// 经度: -180 ~ 180
// 纬度: -90 ~ 90

元数据

  • skill-dependency.json - 技能依赖关系图
  • skill-tags.json - 中英文标签检索
  • version-compatibility.json - 版本兼容性信息

查看 index.md 获取完整技能列表和导航。

© antvis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 39 other files (references) in skills/l7 of antvis/L7.

  • SKILL.md
  • COMPLETENESS_REPORT.md
  • README.md
  • index.md
  • metadata/skill-dependency.json
  • metadata/skill-tags.json
  • metadata/version-compatibility.json
  • references/animation/layer-animation.md
  • references/core/map-types.md
  • references/core/scene-lifecycle.md
  • references/core/scene-methods.md
  • references/core/scene.md
  • references/data/source-csv.md
  • references/data/source-geojson.md
  • references/data/source-json.md
  • references/data/source-mvt.md
  • … and 24 more

Open the folder on GitHubat commit 6e3dbfe

Compare with similar skills

Antv L7 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Antv L7 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Antv L7 this skillantvis/L74.1k—~1.4kAutomated safety check: PassMIT
Cesium Mapgaopengbin/cesium-mcp140—~964Automated safety check: PassMIT
Matlab Import Driving Datamatlab/matlab-agentic-toolkit1.1k—~4.6kAutomated safety check: PassCustom licence
GeomasterLeonChaoX/qinyan-academic-skills9431 repos~2.9kAutomated safety check: PassMIT
GeomasterK-Dense-AI/scientific-agent-skills48k1 repos~2.8kAutomated safety check: PassMIT
Geomasteragent-skills-hub/agent-skills-hub1111 repos~5.2kAutomated safety check: PassMIT

Similar skills

  • Cesium Map

    gaopengbin/cesium-mcp

    Open and operate the Cesium MCP 3D map, create map objects and GeoJSON layers, or inspect the selected object in the connected map.

    140 GitHub stars~964 tokensUpdated yesterday
    Data & AnalyticsAuto-check passed
  • Matlab Import Driving Data

    matlab/matlab-agentic-toolkit

    Import recorded driving sensor data (GPS, camera, lidar, actor tracks, lanes) into scenariobuilder.

    1.1k GitHub stars~4.6k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed
  • Geomaster

    LeonChaoX/qinyan-academic-skills

    Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains.

    943 GitHub starsUsed in 1 repo~2.9k tokens
    Data & AnalyticsAuto-check passed
  • Geomaster

    K-Dense-AI/scientific-agent-skills

    Supports geospatial research workflows for remote sensing, vector and raster GIS, spatial statistics, terrain and network analysis, and machine learning for Earth observation.

    48k GitHub starsUsed in 1 repo~2.8k tokens
    Data & AnalyticsAuto-check passed
  • Geomaster

    agent-skills-hub/agent-skills-hub

    Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains.

    111 GitHub starsUsed in 1 repo~5.2k tokens
    Data & AnalyticsAuto-check passed
  • Dataset Profiler

    brevdev/workshop-build-an-agent

    Systematic procedure for profiling, summarizing, or exploring an unfamiliar CSV file or DataFrame

    146 GitHub stars~409 tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

More from antvis/L7

  • Antv L7

    antvis/L7

    基于 WebGL 的大规模地理空间数据可视化引擎。适用于: (1) 创建交互式 WebGL 地图应用 (2) 可视化地理空间数据(点、线、面、热力图) (3) 构建位置数据驾驶舱 (4) 添加地图图层、交互和动画效果 (5) 处理并展示 GeoJSON、CSV 等空间数据

    4.1k GitHub stars~4.4k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Antv L7

What does Antv L7 do?

Comprehensive guide for AntV L7 geospatial visualization library. Antv L7 is an agent skill from antvis/L7. Comprehensive guide for AntV L7 geospatial visualization library.

When should I use Antv L7?

Antv L7 fits situations like: create interactive maps with WebGL rendering; visualize geographic data (points; build location-based data dashboards; process and display GeoJSON.

How do I install Antv L7 in Claude Code?

Run `npx skills add antvis/L7 --skill antv-l7 -a claude-code`. Or copy the skill folder (skills/l7 in antvis/L7) into .claude/skills/antv-l7 in your project. Claude Code loads it when a task matches its description.

How do I install Antv L7 in Codex?

Run `npx skills add antvis/L7 --skill antv-l7 -a codex`. Or copy the skill folder (skills/l7 in antvis/L7) into .agents/skills/antv-l7 in your project. Codex loads it when a task matches its description.

Can I use Antv L7 in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add antvis/L7 --skill antv-l7 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/antv-l7, .gemini/skills/antv-l7, .github/skills/antv-l7 and .opencode/skills/antv-l7 in your project.

What does Antv L7 need to run?

SKILL.md names no scripts, command-line tools or credentials: Antv L7 is instructions for the agent only.

Does Antv L7 access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Antv L7 safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Antv L7 use?

Antv L7 is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Antv L7 use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 90k tokens, read only when the agent opens those files.

What are the alternatives to Antv L7?

Skills that share tags, products or a category with Antv L7: Cesium Map (gaopengbin/cesium-mcp, 140 stars), Matlab Import Driving Data (matlab/matlab-agentic-toolkit, 1.1k stars), Geomaster (LeonChaoX/qinyan-academic-skills, 943 stars) and Geomaster (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Antv L7?

antvis (a GitHub organization) maintains it in antvis/L7, which has 4,071 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 8, 2026.

Source: antvis/L7 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.