Add Geolocation logo

Add Geolocation

Organization
microsoft
add-geolocation

Internal implementation skill invoked by /add-native for native background GPS tracking with durable storage and Dataverse sync using @microsoft/power-apps-native-bglocation.

Overview

Publishermicrosoft
Repositorypower-platform-skills
Skill nameadd-geolocation
Stars
895
Forks
182
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

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

Installation

Install the Add Geolocation 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.
  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/microsoft/power-platform-skills.git /tmp/power-platform-skills
mkdir -p .claude/skills
cp -r /tmp/power-platform-skills/plugins/mobile-apps/skills/add-native/add-geolocation .claude/skills/add-geolocation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Add Geolocation 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 Add Geolocation 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 Add Geolocation 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.

Shared instructions: shared-instructions.md - read first.

Add Geolocation

Internal helper for /add-native geolocation, /add-native location-tracking, /add-native background-location, /add-native gps-tracking, and /add-native @microsoft/power-apps-native-bglocation.

Use this only for continuous/background GPS tracking with native durable storage and inline Dataverse upload. For a single foreground coordinate read, use /add-native location (expo-location) instead.

Hard rules:

  • Auth is MSAL-only. Do not expose OneAuth or an auth selector.
  • Use geoService(dataSource, app_id) and BgLocationClient.
  • Do not use GeolocationExtension, HostingSDK, PCF, Launch URI, or CordovaV2 bridge paths.
  • Do not install packages or edit native config.
  • The control is not usable until its Dataverse target table and mapped columns are verified.

1. Verify app and package

bash
test -f app.config.js && test -f power.config.json && test -f package.json && test -d src
node -e "const p=require('./package.json'); const m='@microsoft/power-apps-native-bglocation'; if (!p.dependencies?.[m]) { console.error('MISSING: ' + m); process.exit(1); } console.log('OK: geolocation package present');"

If either check fails, stop. The template/app must already ship the native package.

2. Verify the Dataverse target table first

This control uses the package default Dataverse entity set:

text
msdyn_locationrecords

Do not ask the user for a table name and do not invent a custom table. msdyn_locationrecords must already exist before the control can be used.

bash
ENV_JSON=$(node "${PLUGIN_ROOT}/scripts/resolve-environment.js" "$(node -e "console.log(require('./power.config.json').environmentId)")")
ENV_URL=$(node -e "const j=JSON.parse(process.argv[1]); process.stdout.write(j.environmentUrl || '')" "$ENV_JSON")

TABLE="msdyn_locationrecords"
node "${PLUGIN_ROOT}/scripts/dataverse-request.js" "$ENV_URL" GET \
  "EntityDefinitions?\$filter=EntitySetName eq '$TABLE'&\$select=LogicalName,EntitySetName"

Required result:

  • One row returned: capture LogicalName and verify columns.
  • Empty value: []: stop. Mark BLOCKED (target table missing). Do not create the table, do not route to /add-dataverse, and do not report the control as usable. Tell the user to run the geolocation-control table provisioning/setup mechanism, then re-run /add-native geolocation.
  • Auth/environment error: stop. Mark UNVERIFIED (target table not checked). Do not report the control as usable.

When the table exists, verify every mapped column exists:

bash
node "${PLUGIN_ROOT}/scripts/dataverse-request.js" "$ENV_URL" GET \
  "EntityDefinitions(LogicalName='<logicalName>')/Attributes?\$select=LogicalName,AttributeType"

Required default fieldMap columns from the package README:

text
msdyn_locationrecordid, msdyn_appid, msdyn_latitude, msdyn_longitude,
msdyn_altitude, msdyn_accuracy, msdyn_heading, msdyn_speed, msdyn_timestamp

If any active fieldMap column is missing, stop. Mark BLOCKED (target columns missing) and tell the user to fix the control table through the geolocation-control table provisioning/setup mechanism.

3. Write src/native/geolocation.ts

Create or patch src/native/geolocation.ts so screens import this wrapper, not the package directly.

The target config must require the README's two tracking flags:

  • trackInBackground: boolean
  • persistAcrossRestarts: boolean
ts
// src/native/geolocation.ts
import {
  geoService,
  BgLocationClient,
  AuthMethod,
  ConnectionType,
} from '@microsoft/power-apps-native-bglocation';
import type {
  DataverseDataSource,
  LocationData,
  PermissionStatus,
} from '@microsoft/power-apps-native-bglocation';

export type { LocationData, PermissionStatus } from '@microsoft/power-apps-native-bglocation';

export type GeoTrackingTarget = Omit<DataverseDataSource, 'authMethod' | 'connectionType'>;

export type GeoResult<T> =
  | { ok: true; value: T }
  | {
      ok: false;
      reason: 'NATIVE_MODULE_MISSING' | 'PERMISSION_DENIED' | 'TRACKING_FAILED';
      message?: string;
    };

let activeClient: BgLocationClient | null = null;

function client(): BgLocationClient {
  return activeClient ?? new BgLocationClient();
}

function dataSource(target: GeoTrackingTarget): DataverseDataSource {
  return {
    ...target,
    authMethod: AuthMethod.MSAL,
    connectionType: ConnectionType.Dataverse,
  };
}

function fail(error: unknown): Extract<GeoResult<never>, { ok: false }> {
  const message = error instanceof Error ? error.message : String(error);
  if (/native|module|not.*link|undefined is not an object|null is not an object/i.test(message)) {
    return { ok: false, reason: 'NATIVE_MODULE_MISSING', message };
  }
  if (/permission|denied|authoriz|not granted/i.test(message)) {
    return { ok: false, reason: 'PERMISSION_DENIED', message };
  }
  return { ok: false, reason: 'TRACKING_FAILED', message };
}

export async function startTracking(
  app_id: string,
  target: GeoTrackingTarget,
): Promise<GeoResult<void>> {
  try {
    activeClient = geoService(dataSource(target), app_id);
    await activeClient.startTracking();
    return { ok: true, value: undefined };
  } catch (error) {
    activeClient = null;
    return fail(error);
  }
}

export async function stopTracking(): Promise<GeoResult<void>> {
  try {
    await client().stopTracking();
    activeClient = null;
    return { ok: true, value: undefined };
  } catch (error) {
    return fail(error);
  }
}

export async function isTracking(): Promise<GeoResult<boolean>> {
  try {
    return { ok: true, value: await client().isTracking() };
  } catch (error) {
    return fail(error);
  }
}

export async function getPermissionStatus(): Promise<GeoResult<PermissionStatus>> {
  try {
    return { ok: true, value: await client().getPermissionStatus() };
  } catch (error) {
    return fail(error);
  }
}

export async function getCurrentLocation(): Promise<GeoResult<LocationData>> {
  try {
    return { ok: true, value: await client().getCurrentLocation() };
  } catch (error) {
    return fail(error);
  }
}

4. Usage shape

Screens must pass connectionUrl, trackInBackground, and persistAcrossRestarts. Do not pass tableName or fieldMap; the control uses the default msdyn_locationrecords table and default msdyn_* field map. intervalMs, distanceFilterMeters, and notification are optional.

ts
const target: GeoTrackingTarget = {
  connectionUrl: 'https://org.crm.dynamics.com',
  trackInBackground: true,
  persistAcrossRestarts: false,
};

await startTracking('my-wrap-app', target);

5. Type-check and summary

bash
npx tsc --noEmit

Only after table + columns are verified and TypeScript passes, report:

text
Geolocation status : READY
Package present    : @microsoft/power-apps-native-bglocation
Wrapper            : src/native/geolocation.ts
Required config    : connectionUrl, trackInBackground, persistAcrossRestarts
Auth               : MSAL only
Target table       : <TABLE> verified
Native config      : not changed

If table verification failed, report BLOCKED or UNVERIFIED instead and do not update memory-bank.md as if the control is ready.

Frequently asked questions

What does the Add Geolocation AI skill do?

Internal implementation skill invoked by /add-native for native background GPS tracking with durable storage and Dataverse sync using @microsoft/power-apps-native-bglocation.

Why use Add Geolocation on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/microsoft/power-platform-skills/tree/main/plugins/mobile-apps/skills/add-native/add-geolocation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Add Geolocation?

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 Add Geolocation?

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

Is the Add Geolocation AI skill free?

Yes. It is published on GitHub by microsoft 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 👇