Agent skill

Amap

by nano-muse in nano-muse/nanoMuse

Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server.

GPL-3.0Auto-check passedAgent Workflows

Install Amap

skills CLI
$ npx skills add nano-muse/nanoMuse --skill amap -a claude-code

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

GitHub CLI
$ gh skill install nano-muse/nanoMuse amap --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/nano-muse/nanoMuse.git skills-src && mkdir -p .claude/skills && cp -r skills-src/nanomuse/skills/builtin/amap .claude/skills/amap && 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
amap
GitHub stars
381
Token cost
~964 tokens
SKILL.md length
528 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
GPL-3.0

At a glance

Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server.

  • The user asks how far
  • SKILL.md covers Is it there?, The tools, How to answer and With the other hands, plus 1 more section
  • Reaches mcp.amap.com; needs AMAP_KEY and AMAP_MAPS_API_KEY
  • How to get somewhere (car

What it does

Amap is an agent skill from nano-muse/nanoMuse. Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server. Use when the user asks how far, how long, how to get somewhere (car, transit, bike, foot), what is near a place, or about the weather in a Chinese city.

Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers… The licence is GPL-3.0.

When your agent uses it

  • The user asks how far
  • How to get somewhere (car
  • What is near a place
  • About the weather in a Chinese city

Example prompts

  • “/amap”

Requirements

  • A credential in AMAP_KEY
  • A credential in AMAP_MAPS_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 29e7a91. 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 toml).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • mcp.amap.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • AMAP_KEY
    • AMAP_MAPS_API_KEY

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

Context cost

Amap loads about 964 tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 528 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~964

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 nano-muse/nanoMuse at commit 29e7a91, republished under its GPL-3.0 licence (© nano-muse). 528 words, ~964 tokens.

Download SKILL.mdSave it as .claude/skills/amap/SKILL.md (or your agent's skills folder).
name
amap
description
Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server. Use when the user asks how far, how long, how to get somewhere (car, transit, bike, foot), what is near a place, or about the weather in a Chinese city.
channel
api
metadata.author
nanoMuse
metadata.version
1

高德地图 (Amap) through MCP

高德 publishes an MCP server with twelve tools; configured, they appear to you as amap__maps_*. No browser, no phone, no screenshots: a question about a place is one or two tool calls.

Is it there?

Look for amap__maps_geo in your tools. If it is not there, say so in one line and give the user the four lines to add to config.toml, then stop. Your tools list is the only place it can be: do not run shell commands or scripts to look for it, and when the user asked for an app on their phone and you have read it there, the answer is complete without this skill:

toml
[[mcp.servers]]
name = "amap"
url = "https://mcp.amap.com/mcp?key={{vault:AMAP_KEY}}"   # a free Web 服务 key from console.amap.com
risk = "safe"

and nanomuse vault set AMAP_KEY. Without Node, the hosted URL is the way; with it, command = "npx", args = ["-y", "@amap/amap-maps-mcp-server"], env = { AMAP_MAPS_API_KEY = "{{vault:AMAP_KEY}}" } does the same.

The tools

  • amap__maps_geo: an address or a landmark (北京南站, 上海市浦东新区世纪大道100号) → coordinates lng,lat; amap__maps_regeocode the other way round. Almost everything else wants coordinates, so this comes first.
  • amap__maps_text_search: places by keyword (咖啡, 汉庭酒店) in a city; amap__maps_around_search, the same within radius metres of a location; amap__maps_search_detail, one place's details by its id (opening hours, rating, phone, address).
  • amap__maps_direction_driving, amap__maps_direction_walking, amap__maps_bicycling: a route between two coordinates with distance, duration and the steps; amap__maps_direction_transit_integrated, bus, metro and train together, and across cities with city and cityd.
  • amap__maps_distance: just the distance and time between points (type 1 = driving, 3 = straight line).
  • amap__maps_weather: today and the next few days for a city name or adcode.

Coordinates are 经度,纬度 (longitude first, GCJ-02). Durations come in seconds and distances in metres: say them as minutes and kilometres.

Show full SKILL.md (259 more words)Show less

How to answer

  • Resolve both ends first, then one route call per mode the user cares about. When they did not say how they travel, compare transit and driving in one line each and say which you would take at that hour.
  • A "what's near" question: geocode the centre, one around_search, then give three places at most with what makes each worth it (rating, distance, open now), not the whole list.
  • Travel time is an estimate for now; for a departure later or tomorrow say so, and for a real day-of-travel plan add slack.
  • Weather goes into plans the user is making (an outdoor day, a trip) without being asked when it changes the plan (rain on the day of the hike).

With the other hands

  • 高德 + 12306: the route to the station (this skill) and the train itself (the train-tickets skill on the phone) make one plan: leave home at 07:10, G1 at 08:00.
  • 高德 + 飞书: a route or an address the user wants to share goes to a colleague with the feishu skill; a meeting's location is checked before the event is created.
  • 高德 + the workspace: a day's itinerary with places, times and the routes between them is a page in trips/, written with the trip-plan skill; the coordinates and distances come from here.

Finish

A few lines: where, how far, how long, by what, and the weather when it matters. Save nothing unless asked. remember the user's home and workplace once they name them, so that the next "how long to get to …" needs no question.

© nano-muse, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in nanomuse/skills/builtin/amap of nano-muse/nanoMuse.

Open the folder on GitHubat commit 29e7a91

Compare with similar skills

Amap 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.

Amap compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Amap this skillnano-muse/nanoMuse381—~964Automated safety check: PassGPL-3.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

More from nano-muse/nanoMuse

All 11 skills in this repo
  • Kuaidi100

    nano-muse/nanoMuse

    Where a parcel is, when it will arrive and what a shipment would cost, through the 快递100 MCP server: any Chinese courier (顺丰, 京东, 中通, 圆通, 韵达, 邮政 and more) from a tracking number.

    381 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Train Tickets

    nano-muse/nanoMuse

    Trains in China through the 12306 MCP server: routes, dates, options, connections and stops with no screen; booking only on the user's word, in the 12306 app on their phone, stopping before payment.

    381 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Compare Options

    nano-muse/nanoMuse

    Compare two to five options (products, plans, places, tools, offers) on the criteria that matter to the user, in a table the user can re-weight, with a recommendation.

    381 GitHub stars~588 tokensUpdated today
    Auto-check passed
  • Feishu

    nano-muse/nanoMuse

    The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open.

    381 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Inbox Triage

    nano-muse/nanoMuse

    Go through recent mail and sort it into needs-a-reply, waiting-on-others, to-do and can-ignore, with draft replies ready for review.

    381 GitHub stars~597 tokensUpdated today
    Auto-check passed
  • Meeting Prep

    nano-muse/nanoMuse

    Prepare for a meeting (who is in it, what was last said with them, what the user owes them and wants from them) as a one-page brief.

    381 GitHub stars~659 tokensUpdated today
    Auto-check passed

Categories

Questions about Amap

What does Amap do?

Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server. Amap is an agent skill from nano-muse/nanoMuse. Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server.

When should I use Amap?

Amap fits situations like: the user asks how far; how to get somewhere (car; what is near a place; about the weather in a Chinese city.

How do I install Amap in Claude Code?

Run `npx skills add nano-muse/nanoMuse --skill amap -a claude-code`. Or copy the skill folder (nanomuse/skills/builtin/amap in nano-muse/nanoMuse) into .claude/skills/amap in your project. Claude Code loads it when a task matches its description.

How do I install Amap in Codex?

Run `npx skills add nano-muse/nanoMuse --skill amap -a codex`. Or copy the skill folder (nanomuse/skills/builtin/amap in nano-muse/nanoMuse) into .agents/skills/amap in your project. Codex loads it when a task matches its description.

Can I use Amap 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 nano-muse/nanoMuse --skill amap -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/amap, .gemini/skills/amap, .github/skills/amap and .opencode/skills/amap in your project.

What does Amap need to run?

Going by SKILL.md and its folder, Amap needs credentials named AMAP_KEY and AMAP_MAPS_API_KEY. Our summary lists: A credential in AMAP_KEY; A credential in AMAP_MAPS_API_KEY.

Does Amap access the network?

SKILL.md names 1 domain. In commands or code: mcp.amap.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Amap 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 Amap use?

Amap is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Amap use?

About 964 tokens (SKILL.md is roughly 3.9k 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 Amap?

Skills that share tags, products or a category with Amap: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Amap?

nano-muse (a GitHub organization) maintains it in nano-muse/nanoMuse, which has 381 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 9, 2026.

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