Add Sharepoint logo

Add Sharepoint

Organization
microsoft
add-sharepoint

Use when the user wants to read or write SharePoint lists, manage documents in a SharePoint document library, or create a new SharePoint list from a Power Apps mobile app.

Overview

Publishermicrosoft
Repositorypower-platform-skills
Skill nameadd-sharepoint
Stars
895
Forks
182
Bundled files
3
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Add Sharepoint 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-sharepoint .claude/skills/add-sharepoint
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Add Sharepoint 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 Sharepoint 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 Sharepoint 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.

References:

Add SharePoint

Two paths: existing lists (skip to Step 6) or new lists (full workflow).

Workflow

  1. Check Memory Bank → 2. Plan → 3. Setup Graph API Auth → 4. Review Existing Lists → 5. Create Lists → 6. Get Connection ID → 7. Discover Sites → 8. Discover Tables → 9. Add Connector → 10. Configure → 11. Type-check → 12. Update Memory Bank

Step 1: Check Memory Bank

Check for memory-bank.md per shared-instructions.md.

Also confirm this is a mobile app:

bash
test -f power.config.json && test -f app.config.js && echo "OK" || echo "ERROR: not a mobile app"

Step 2: Plan

Telemetry checkpoint: plan_sharepoint_data_source

Ask the user:

  1. Which SharePoint list(s) do they need?
  2. Do the lists already exist on their site, or do they need to create new ones?

If lists already exist: Skip to Step 6.

If creating new lists:

  • Ask about the data they need and design an appropriate schema
  • Reuse existing lists when possible (don't duplicate)
  • Enter plan mode with EnterPlanMode, present the list designs with columns and types
  • Get approval with ExitPlanMode

Step 3: Setup Graph API Auth (if creating lists)

See api-authentication-reference.md for full details.

powershell
az account show   # Verify Azure CLI logged in

$api = Initialize-SharePointGraphApi -SiteUrl "https://<tenant>.sharepoint.com/sites/<site-name>"
$headers = $api.Headers
$siteId = $api.SiteId

Requires Sites.Manage.All permission.

Step 4: Review Existing Lists (if creating lists)

Always query existing lists first before creating:

powershell
$existingLists = Invoke-RestMethod -Uri "https://graph.microsoft.com/v1.0/sites/$siteId/lists?`$select=id,displayName,description,list&`$filter=list/hidden eq false" -Headers $headers

See list-management-reference.md for Find-SimilarLists, Compare-ListSchemas, and Get-ListSchema functions.

Present findings to user with AskUserQuestion:

  • Lists that can be reused (already exist with matching columns)
  • Lists that need extension (exist but missing columns)
  • Lists that must be created (no match found)

Step 5: Create Lists (if creating lists)

Telemetry checkpoint: create_sharepoint_lists

Print before starting:

"→ Creating SharePoint lists via Graph API (sequential per list, columns added after list exists)…"

Get explicit confirmation before creating. Use safe functions from list-management-reference.md:

  • New-SharePointListIfNotExists
  • Add-SharePointColumnIfNotExists
  • Add-SharePointLookupColumn (for cross-list references)

Step 6: Get Connection ID

Get the SharePoint Online connection ID (see connector-reference.md):

bash
npx power-apps create-connection --api-id shared_sharepointonline --json

Use shared_sharepointonline as the apiId and capture connectionId from the output. Use these exact values in the commands below.

If create-connection cannot complete because browser-based connection creation is disabled or the connector needs interactive auth, direct the user to create one:

Open https://make.powerapps.com/environments/<environment-id>/connections+ New connection → search "SharePoint" → Create. Then provide the connection ID or rerun /list-connections shared_sharepointonline.

Step 7: Discover Sites

Print before starting:

"→ Discovering SharePoint sites accessible to this connection…"

bash
npx power-apps list-datasets --api-id <apiId-from-list> --connection-id <connection-id> --json

Present the sites to the user and ask which one(s) they want to connect to. If the user already specified a site URL, confirm it appears in the list.

If npx power-apps list-datasets fails or returns no results:

  • Auth, wrong user, or multiple accounts: follow shared-instructions command-failure handling and retry once.
  • Empty list: Confirm the connection ID is for a SharePoint Online connection and the user has access to at least one site. STOP if the list is empty after confirming.

Step 8: Discover Tables

Print before starting:

"→ Discovering lists/document libraries on each selected site…"

For each selected site:

bash
npx power-apps list-tables --api-id <apiId-from-list> --connection-id <connection-id> --dataset '<site-url>' --json

Present the tables to the user and ask which ones they want to add. Suggest tables that look relevant to their use case. If lists were created in Step 5, they should appear here.

Step 9: Add Connector

Telemetry checkpoint: generate_sharepoint_data_source

Print before starting:

"→ Running npx power-apps add-data-source per list (sequential, ~10–20 seconds each)."

SharePoint is a tabular datasource — requires --connection-id, --dataset, and --resource-name:

bash
npx power-apps add-data-source --api-id <apiId-from-list> --connection-id <connectionId-from-list> --dataset '<site-url>' --resource-name '<table-name>'

Run once per list or document library.

Step 10: Configure

Read sharepoint-reference.md before writing any SharePoint code — column encoding, choice fields, and lookups have critical gotchas.

Use Grep to find methods in src/generated/services/SharePointOnlineService.ts (generated files can be very large — see connector-reference.md).

Sample usage:

typescript
import { SharePointOnlineService } from '../../src/generated/services/SharePointOnlineService';

// Read items
const result = await SharePointOnlineService.GetItems({
  dataset: 'https://contoso.sharepoint.com/sites/projects',
  table: 'Project Milestones',
});
const items = result.value ?? [];

// Create item
await SharePointOnlineService.PostItem({
  dataset: 'https://contoso.sharepoint.com/sites/projects',
  table: 'Project Milestones',
  item: { Title: 'Launch review', Status: 'Not Started' },
});

// Update item (SharePoint IDs are integers, not GUIDs)
await SharePointOnlineService.PatchItem({
  dataset: 'https://contoso.sharepoint.com/sites/projects',
  table: 'Project Milestones',
  id: 42,
  item: { Status: 'Done' },
});

Step 11: Type-check

Telemetry checkpoint: validate_sharepoint_integration

Print before starting:

"→ Regenerating connector schemas + running tsc to verify SharePoint services compile (~15–30 seconds)."

Native diff: npx tsc --noEmit instead of npm run build. Do NOT run platform-specific native build commands here.

npx power-apps add-data-source wrote new files into .power/schemas/sharepointonline/. Regenerate connectorSchemas.ts before type-checking so the new list is wired into the runtime schema map:

bash
npm run generate-schemas
npx tsc --noEmit

Fix TypeScript errors before proceeding.

Step 12: Update Memory Bank

Update memory-bank.md with: connector added, site URL, lists/libraries connected (or created), type-check status.

Note: No manual executor wiring needed. PowerAppsProvider in app/_layout.tsx handles SharePoint connector routing, connection resolution, and OAuth consent automatically at runtime.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Add Sharepoint AI skill do?

Use when the user wants to read or write SharePoint lists, manage documents in a SharePoint document library, or create a new SharePoint list from a Power Apps mobile app.

Why use Add Sharepoint on TypingMind?

Because you install it once and use it with any model. Add Sharepoint 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 Sharepoint 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-sharepoint. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Add Sharepoint?

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 Sharepoint?

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

Is the Add Sharepoint 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 👇