Mappu logo

Mappu

Community
xenodium
mappu

Use when the user asks about a specific place — restaurant, cafe, shop, business, landmark — or when context implies a location-based lookup ("where is X", "find Y", "X in Z", "X near A"). Calls the mappu CLI to search Apple Maps and returns local results with addresses, websites, preview images, and a map snapshot.

Overview

Publisherxenodium
Repositoryemacs-skills
Skill namemappu
Stars
148
Forks
18
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Mappu 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/xenodium/emacs-skills/tree/main/skills/mappu
  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/xenodium/emacs-skills.git /tmp/emacs-skills
mkdir -p .claude/skills
cp -r /tmp/emacs-skills/skills/mappu .claude/skills/mappu
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mappu 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 Mappu 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 Mappu 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.

Search places with mappu

When the user asks about a specific place or implies a location-based query, use the mappu CLI to search Apple Maps and present the results.

Examples of triggering contexts:

  • "where can I get good ramen?"
  • "is Roti King open?"
  • "find sushi places in Soho"
  • "what cafes are near St James's Park?"
  • "any good Malaysian food around Chinatown?"

Locating context (always set --near)

mappu requires a --near value. Determine it like this:

  1. If the user mentioned a location ("in Soho", "near Charing Cross", "around Tokyo"), use that.
  2. If recent conversation context establishes a location (e.g., they have been talking about restaurants in London), use that.
  3. Otherwise, ask the user "Near where?" before running mappu. Do not guess silently and do not fall back to a default city.

How to invoke

Run via the Bash tool. Always include --preview --map for richer output:

sh
mappu --preview --map --near "Soho London" "roti king"

Flags:

  • --near "<location>" — required, set every call.
  • --limit <N> — max results; mappu's default is 10.
  • --radius <KM> — search radius in kilometers.
  • --preview — include website preview images per result (use by default).
  • --map — include a map snapshot with numbered pins (use by default).

Output schema

mappu prints JSON to stdout:

json
{
  "map": "/path/to/map.png",
  "results": [
    {
      "name": "Roti King",
      "address": "6 Artillery Lane, London, England, E1 7LS, United Kingdom",
      "neighborhood": "City of London",
      "category": "Restaurant",
      "url": "https://rotiking.com/location/spitalfields",
      "mapsUrl": "https://maps.apple.com/?ll=51.5183405,-0.0790983&q=Roti%20King",
      "image": "/path/to/preview.png",
      "phone": "+44 20 1234 5678",
      "countryCode": "GB",
      "timeZone": "Europe/London",
      "coordinate": { "lat": 51.5183405, "lng": -0.0790983 }
    }
  ]
}

On failure, mappu prints {"error": "..."} and exits non-zero.

Render as markdown

For successful responses, output in this order: top-level map (if present), then each result as image + name link + category + address. Pin numbers on the map match the order of results[] (1-based).

![map of results](path/to/map.png)

![Roti King](path/to/preview1.png)
[Roti King](https://rotiking.com/location/spitalfields)
Restaurant
6 Artillery Lane, London, England, E1 7LS, United Kingdom

![Roti King](path/to/preview2.png)
[Roti King](https://rotiking.com/location/waterloo)
Restaurant
97 Lower Marsh, London, England, SE1 7AB, United Kingdom

Rules

  • Always set --near; ask the user "Near where?" if it is not obvious from the request or recent context.
  • Always include --preview --map unless the user explicitly asks for fast / text-only results.
  • Use the result's url as the link target. Fall back to mapsUrl if url is missing.
  • Omit the image line for results without an image field rather than fabricating one.
  • Do not invent ratings, opening hours, prices, or any fields not present in the JSON.
  • If mappu returns {"error": "..."}, surface that error to the user and stop.
  • Requires the mappu binary on $PATH. If invocation fails with "command not found", tell the user to install it (e.g. copy the release binary to /usr/local/bin/).

Frequently asked questions

What does the Mappu AI skill do?

Use when the user asks about a specific place — restaurant, cafe, shop, business, landmark — or when context implies a location-based lookup ("where is X", "find Y", "X in Z", "X near A"). Calls the mappu CLI to search Apple Maps and returns local results with addresses, websites, preview images, and a map snapshot.

Why use Mappu on TypingMind?

Because you install it once and use it with any model. Mappu 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 Mappu in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xenodium/emacs-skills/tree/main/skills/mappu. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mappu?

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 Mappu?

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

Is the Mappu AI skill free?

It is published on GitHub by xenodium. Check the repository for licensing terms. 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 👇