Paper Figure Generate
GRIND-Lab-Core/night_owl_research_agent
Generates publication-quality figures and diagrams from output/PAPERPLAN.md for GIScience, GeoAI, and remote sensing journals (IJGIS, ISPRS JPRS, RSE, TGIS).
根据用户给出的城市、地点列表、地址表或已有 POI JSON，生成 GIS/OSM 城市导览地图、打卡地图、街区指南、小酒馆/咖啡/餐饮点位地图，并可选用 GPT Image 做风格化。用户要求“出一张地图”“生成城市点位图”“检查点位对齐”“用高德解析地址”“做 OSM/GIS 底图”“风格化地图海报”时使用。
Install Map Creator
$ npx skills add Hatari130/map-creator --skill map-creator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Hatari130/map-creator map-creator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "map-creator" agent skill from https://github.com/Hatari130/map-creator/tree/main into .claude/skills/map-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "map-creator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hatari130/map-creator --skill map-creator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Hatari130/map-creator map-creator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "map-creator" agent skill from https://github.com/Hatari130/map-creator/tree/main into .agents/skills/map-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "map-creator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hatari130/map-creator --skill map-creator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Hatari130/map-creator map-creator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "map-creator" agent skill from https://github.com/Hatari130/map-creator/tree/main into .cursor/skills/map-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "map-creator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hatari130/map-creator --skill map-creator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Hatari130/map-creator map-creator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "map-creator" agent skill from https://github.com/Hatari130/map-creator/tree/main into .gemini/skills/map-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "map-creator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Hatari130/map-creator map-creatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Hatari130/map-creator --skill map-creator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "map-creator" agent skill from https://github.com/Hatari130/map-creator/tree/main into .github/skills/map-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "map-creator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hatari130/map-creator --skill map-creator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Hatari130/map-creator map-creator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "map-creator" agent skill from https://github.com/Hatari130/map-creator/tree/main into .opencode/skills/map-creator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "map-creator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
map-creator- GitHub stars
- 193
- Token cost
- ~896 tokens
- SKILL.md length
- 232 words
- Files
- 57
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
根据用户给出的城市、地点列表、地址表或已有 POI JSON，生成 GIS/OSM 城市导览地图、打卡地图、街区指南、小酒馆/咖啡/餐饮点位地图，并可选用 GPT Image 做风格化。用户要求“出一张地图”“生成城市点位图”“检查点位对齐”“用高德解析地址”“做 OSM/GIS 底图”“风格化地图海报”时使用。
- Works in 5 steps: 从用户请求中提取 → 从地点名生成 GIS 地图草稿 → 从已有 POI JSON 生成 GIS 地图草稿 → …
- Tasks that involve Image generation
- SKILL.md covers 主流程, 配置, POI 解析规则 and 地图范围方法, plus 7 more sections
- Runs Python scripts from its folder; calls python; needs AMAP_KEY and OPENAI_API_KEY
What it does
Map Creator is an agent skill from Hatari130/map-creator. 根据用户给出的城市、地点列表、地址表或已有 POI JSON，生成 GIS/OSM 城市导览地图、打卡地图、街区指南、小酒馆/咖啡/餐饮点位地图，并可选用 GPT Image 做风格化。用户要求“出一张地图”“生成城市点位图”“检查点位对齐”“用高德解析地址”“做 OSM/GIS 底图”“风格化地图海报”时使用。
Its SKILL.md is about 900 tokens, which your agent loads only when the skill is triggered. The skill folder holds 61 other files (for example `README.md`, `config.example.json` and `guide_maps/__init__.py`).
It sits in Media & Creative, covering Image generation and Geospatial analysis. The repository describes itself as: 结合gis+gpt，用自然语言生成可商用城市打卡地图. The licence is MIT.
When your agent uses it
- Tasks that involve Image generation
- Tasks that involve Geospatial analysis
Example prompts
- “生成城市点位图”
- “检查点位对齐”
- “用高德解析地址”
- “/map-creator”
Requirements
- Python 3
- A credential in AMAP_KEY
- A credential in OPENAI_API_KEY
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 从用户请求中提取
- 从地点名生成 GIS 地图草稿
- 从已有 POI JSON 生成 GIS 地图草稿
- 如需保存解析结果以便复查，加入
- GIS 草稿输出到
What it can do on your machine
Read from SKILL.md and the folder at commit 240d68a. 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
Ships script files (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python
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 these keys or tokens, usually read from environment variables:
AMAP_KEYOPENAI_API_KEYGPT_IMAGE_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Map Creator loads about 896 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 232 words of instructions outside code blocks.
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 Hatari130/map-creator at commit 240d68a, republished under its MIT licence (© Hatari130). 232 words, ~896 tokens.
Download SKILL.mdSave it as
.claude/skills/map-creator/SKILL.md (or your agent's skills folder). This skill also uses 56 other files; get the full folder from GitHub.- name
- map-creator
- description
- 根据用户给出的城市、地点列表、地址表或已有 POI JSON，生成 GIS/OSM 城市导览地图、打卡地图、街区指南、小酒馆/咖啡/餐饮点位地图，并可选用 GPT Image 做风格化。用户要求“出一张地图”“生成城市点位图”“检查点位对齐”“用高德解析地址”“做 OSM/GIS 底图”“风格化地图海报”时使用。
map-creator
在仓库根目录执行命令。当前项目是扁平化 skill 工具包，主要代码在 guide_maps/。
主流程
从用户请求中提取：
city：城市名。places：地点名或地址，保持用户给出的顺序。title：地图标题；如果用户没给，按主题补一个简短标题。- 可选
road_labels：用户特别关心的道路名，只作为自动道路名筛选的加权提示，不是白名单。
从地点名生成 GIS 地图草稿：
python -m guide_maps.cli.create_gis_map --city <城市> --places "<地点1>" "<地点2>" --title "<标题>"- 从已有 POI JSON 生成 GIS 地图草稿：
python -m guide_maps.cli.create_gis_map --city <城市> --poi-json <poi.json> --title "<标题>"- 如需保存解析结果以便复查，加入：
--save-poi-json outputs/poi_sets/<name>.json- GIS 草稿输出到：
outputs/posters/配置
从 config.local.json 读取本地 key；该文件已被忽略，不要提交真实 key。
- 高德：
amap.api_key，也可用环境变量AMAP_KEY。 - GPT Image：
gpt_image.api_key，也可用环境变量OPENAI_API_KEY或GPT_IMAGE_API_KEY。
config.example.json 只保留字段结构，不要写真实 key。
POI 解析规则
- 优先尝试本地 AMap CLI；不可用时使用高德 Web API。
- 高德返回 GCJ-02 坐标。
- 渲染前转换为 WGS84，以匹配 OSMnx / OpenStreetMap 坐标系。
- 保存可复查字段：输入名、解析名、地址、区县、候选结果、置信度、WGS84 坐标。
- 左侧索引的小字优先使用高德候选中的
formatted_address或address，并去掉省市前缀。
相关代码：
guide_maps/cli/create_gis_map.pyguide_maps/geocoding/workflow.pyguide_maps/geocoding/poi_resolver.pyguide_maps/geocoding/coordinate_transform.pyguide_maps/geocoding/poi_io.py
地图范围方法
- 将 POI 投影到本地 UTM。
- 计算点位包围盒。
- 添加 padding。
- 强制使用 16:10 或 16:9 的目标画幅。
- 计算中心点和 OSM 抓取半径
dist。 dist > 3200判定为大范围地图。
大范围地图：
- 路网使用
drivenetwork type。 - 减少生活方式 POI。
- 道路名数量更少。
小范围地图：
- 路网使用
walknetwork type。 - 显示步行路、建筑、公园、水体和生活方式 POI。
OSM 数据获取
Overpass API 在中国大陆可能很慢。当前实现会：
- 单独请求一次 OSM 路网。
- 把建筑、公园、水体、生活方式 POI、交通点等 features 合并成一次 Overpass 请求。
- 在本地拆分图层。
- 缓存到
cache/，后续同一区域会复用缓存。
相关代码：
guide_maps/rendering/osm_context_style.pyguide_maps/rendering/osm_context_map_template.py
GIS 渲染要求
地图应至少包含：
- 底色。
- 水系。
- 公园绿地。
- 建筑轮廓。
- 道路网络。
- 目标点编号。
- 目标点旁边的地点名。
- 左侧索引：编号、地点名、地址。
- 公园名称。
- 自动道路名。
- 标题。
不要在左侧 legend 区渲染地图底图元素。不要显示 subtitle；如果用户提供 subtitle，当前版本先忽略。
道路名筛选
不要把 --road-labels 当作白名单。道路名采用自动筛选：
- 从当前画面内可见路网中找候选道路。
- 按道路等级、可见长度、用户提示道路加权排序。
- 大范围地图最多显示约 5 个道路名，小范围地图最多约 7 个。
- 排除快速路、隧道、立交、内环、铁路、地铁、城际、各种“线”等不适合导览图的道路名。
- 道路名必须避让点位名和公园名；放不下就跳过。
如果用户明确不要道路名，使用：
--no-road-labels标签避让
使用 LabelPlacer 做文本避让：
- 先注册左侧索引、标题、点位圆点等已占用区域。
- 再放 POI 名。
- 再放公园名。
- 最后放道路名。
- 如果候选位置和已有文本重叠，尝试下一个位置。
- 放不下时宁可跳过，也不要压住重要信息。
GPT Image 风格化
当用户要求“风格化”“海报化”“AI 重绘”时，在 GIS 草稿完成后运行：
python -m guide_maps.cli.style_poster_with_gpt_image --input outputs/posters/<draft>.png提示词模板在：
prompts/map_style_templates/没有 GPT Image key 时，不要阻塞 GIS 草稿生成；提示用户可先使用 outputs/posters/ 中的草稿。
常用命令
从地点名生成：
python -m guide_maps.cli.create_gis_map --city 南京 --places "地点1" "地点2" --title "南京小酒馆地图"从 POI JSON 生成：
python -m guide_maps.cli.create_gis_map --city 南京 --poi-json outputs/poi_sets/nanjing_bars_no_baijiahu.json --title "南京小酒馆地图"提示重点道路名：
python -m guide_maps.cli.create_gis_map --city 南京 --poi-json <poi.json> --title "南京小酒馆地图" --road-labels 长江路 石鼓路 应天大街关闭道路名：
python -m guide_maps.cli.create_gis_map --city 南京 --poi-json <poi.json> --title "南京小酒馆地图" --no-road-labels测试
python -m compileall guide_maps tests
python -m pytest tests地图输出后需要目视检查：
- 点位是否落在正确街区。
- 编号和左侧索引是否一一对应。
- 道路名、公园名和 POI 名是否互相遮挡。
- 大范围地图是否没有挤太多细节。
- 建筑层是否没有压住点位和道路。
© Hatari130, 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 56 other files in the repository root of Hatari130/map-creator.
- SKILL.md
- .gitignore
- LICENSE
- README.md
- config.example.json
- docs/images/changning-industrial-memory-map.jpg
- docs/images/jufuchang-walking-guide.png
- guide_maps/__init__.py
- guide_maps/__main__.py
- guide_maps/cli/__init__.py
- guide_maps/cli/create_gis_map.py
- guide_maps/cli/resolve_pois.py
- guide_maps/cli/run_full_map_pipeline.py
- guide_maps/cli/style_poster_with_gpt_image.py
- guide_maps/cli/validate_poi_alignment.py
- guide_maps/core/__init__.py
- … and 41 more
Open the folder on GitHubat commit 240d68a
Compare with similar skills
Map Creator 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Map Creator this skillHatari130/map-creator | 193 | — | ~896 | Automated safety check: Pass | MIT | |
| Paper Figure GenerateGRIND-Lab-Core/night_owl_research_agent | 106 | — | ~5.1k | Automated safety check: Notes | None | |
| Structured Image Generationbytedance/deer-flow | 83k | 5 repos | ~2.9k | Automated safety check: Pass | MIT | |
| AI Image Generation and Editingzhayujie/CowAgent | 47k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Canghe Comicfreestylefly/canghe-skills | 461 | 8 repos | ~3.2k | Automated safety check: Pass | None | |
| Generate Imageynulihao/AgentSkillOS | 617 | 10 repos | ~1.7k | Automated safety check: Notes | None |
Similar skills
Structured Image Generation
bytedance/deer-flow
Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.
AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
Canghe Comic
freestylefly/canghe-skills
Knowledge comic creator supporting multiple art styles and tones.
Generate Image
ynulihao/AgentSkillOS
Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.
GPT Image Generation CLI
wuyoscar/GPT-Image2-Skill
Generates and edits images with GPT Image 2 or 2.5 through a packaged CLI and a prompt gallery, after settling which model fits the request.
Related
Categories
Questions about Map Creator
What does Map Creator do?
根据用户给出的城市、地点列表、地址表或已有 POI JSON，生成 GIS/OSM 城市导览地图、打卡地图、街区指南、小酒馆/咖啡/餐饮点位地图，并可选用 GPT Image 做风格化。用户要求“出一张地图”“生成城市点位图”“检查点位对齐”“用高德解析地址”“做 OSM/GIS 底图”“风格化地图海报”时使用。. Map Creator is an agent skill from Hatari130/map-creator.
When should I use Map Creator?
Map Creator fits situations like: tasks that involve Image generation; tasks that involve Geospatial analysis.
How do I install Map Creator in Claude Code?
Run `npx skills add Hatari130/map-creator --skill map-creator -a claude-code`. Or copy the skill folder (the Hatari130/map-creator repository) into .claude/skills/map-creator in your project. Claude Code loads it when a task matches its description.
How do I install Map Creator in Codex?
Run `npx skills add Hatari130/map-creator --skill map-creator -a codex`. Or copy the skill folder (the Hatari130/map-creator repository) into .agents/skills/map-creator in your project. Codex loads it when a task matches its description.
Can I use Map Creator 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 Hatari130/map-creator --skill map-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/map-creator, .gemini/skills/map-creator, .github/skills/map-creator and .opencode/skills/map-creator in your project.
What does Map Creator need to run?
Going by SKILL.md and its folder, Map Creator needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named AMAP_KEY, OPENAI_API_KEY and GPT_IMAGE_API_KEY. Our summary lists: Python 3; A credential in AMAP_KEY; A credential in OPENAI_API_KEY.
Does Map Creator 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 Map Creator 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 Map Creator use?
Map Creator is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Map Creator use?
About 896 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Map Creator?
Skills that share tags, products or a category with Map Creator: Paper Figure Generate (GRIND-Lab-Core/night_owl_research_agent, 106 stars), Structured Image Generation (bytedance/deer-flow, 83k stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars) and Canghe Comic (freestylefly/canghe-skills, 461 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Map Creator?
Hatari130 (a GitHub user) maintains it in Hatari130/map-creator, which has 193 GitHub stars. The repository was last updated on July 19, 2026.
Source: Hatari130/map-creator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.