Outlook Mail logo

Outlook Mail

Community
win4r
outlook_mail

Read, search, send, reply to, and delete messages in the user's Outlook Mail.

Overview

Publisherwin4r
RepositoryMuseAI-Skills
Skill nameoutlook_mail
Stars
382
Forks
116
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by win4r on GitHub. Read the source before you install it.

Installation

Install the Outlook Mail 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/win4r/MuseAI-Skills/tree/main/opt/hatch/skills/outlook-mail
  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/win4r/MuseAI-Skills.git /tmp/MuseAI-Skills
mkdir -p .claude/skills
cp -r /tmp/MuseAI-Skills/opt/hatch/skills/outlook-mail .claude/skills/outlook_mail
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Outlook Mail 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 Outlook Mail 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 Outlook Mail 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.

Outlook Mail

Purpose

Manage Outlook Mail messages with the outlook-mail companion CLI.

Tooling

Use exec to run:

sh
outlook-mail <subcommand> [options]

Core subcommands:

  • disconnect
  • list [--page-size 10] [--unread] [--page-token 20] [--folder sentitems]
  • get "<MESSAGE_ID>"
  • search "<query>" [--folder sentitems] [--page-size 10]
  • send --to alice@example.com [--to bob@example.com] [--cc charlie@example.com] --subject "Hello" --body "Hi ..." [--attachment /path/to/file.pdf]
  • reply "<MESSAGE_ID>" --body "Thanks for the update!" [--reply-all]
  • delete "<MESSAGE_ID>" (moves the message to Deleted Items; recoverable, not a permanent delete)
  • mark-read "<MESSAGE_ID>"
  • mark-unread "<MESSAGE_ID>"

Use --page-size for result count. --top, --limit, and --max-results are compatibility aliases only; do not use them in new commands. Use get "<MESSAGE_ID>" for a single message; read, get --id, and search --query are compatibility forms only.

JSON output contract:

  • disconnect: parse ok, action, status, and disconnect_url
  • list / search: parse ok, count, next_page_token (when present, pass back as --page-token), total_messages, retrieved_at, and messages[] with id, subject, from, to, date, message_received_at, preview, is_read, and has_attachments
  • get: parse ok, retrieved_at, and message with id, subject, from, to, cc, date, message_received_at, body, body_type, is_read, and has_attachments
  • send: parse ok and action
  • reply: parse ok, action, and message_id
  • delete: parse ok, action (trashed), and message_id; the moved message gets a new id, so message_id is not the id you passed in — use the returned one for any follow-up command
  • mark-read / mark-unread: parse ok, action, and message_id

Auth

Use outlook-mail --status for connector state and link management. The binary handles its callback target internally.

  • If the user wants to connect or reconnect, replace <connect_url> with the returned URL and share exactly this Markdown link: [Connect Outlook Mail](<connect_url>); do not paste the raw URL separately.
  • If the user wants to disconnect, run outlook-mail disconnect. When disconnect_url is present, replace <disconnect_url> with the returned URL and share exactly this Markdown link: [Disconnect Outlook Mail](<disconnect_url>); do not paste the raw URL separately. Otherwise say it is already disconnected.
  • Keep status and linking inside outlook-mail --status; do not use a shared connector helper CLI.
  • Never print tokens, cookies, or connector secrets.

Operating Rules

  1. Use search for targeted lookup, list for browsing, and get only when you need the full body of a specific message.
  2. Message IDs are opaque Graph values. Reuse the exact id returned by list or search.
  3. Before send, confirm recipients, subject, and body in the current thread.
  4. Before reply, confirm the reply body and whether the user wants --reply-all. Use --reply-all only when the user explicitly wants everyone included.
  5. delete, mark-read, and mark-unread may proceed from a clear user request without an additional confirmation. delete moves the message to the Deleted Items folder, where the user can still recover it; tell the user that, and do not describe it as permanent or unrecoverable.
  6. For mailbox-summary requests, exclude likely spam, phishing, or irrelevant bulk promotions by default unless the user explicitly asks for junk or spam, and briefly note that filtering if you used it.
  7. If the CLI reports an auth failure or disconnected state, stop and route the user through the --status connect flow before retrying.
  8. Never surface raw Graph identifiers (message ids, conversation ids) or other internal response fields (change keys, @odata fields, page/skip tokens, raw JSON) in text shown to the user — including in summaries, lists, or per-item annotations. Reuse the ids only internally to chain follow-up commands (rule 2). The sole exceptions are when the user explicitly asks for a raw id or you must show one to troubleshoot a failure.
  9. The compatibility date field is Outlook's message-received time. Prefer message_received_at.user_local when presenting it. It is not the time of an event described inside the email; never infer a delivery, payment, trip, meeting, or other event time from it.

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 Outlook Mail AI skill do?

Read, search, send, reply to, and delete messages in the user's Outlook Mail.

Why use Outlook Mail on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/win4r/MuseAI-Skills/tree/main/opt/hatch/skills/outlook-mail. 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 Outlook Mail?

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 Outlook Mail?

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

Is the Outlook Mail AI skill free?

It is published on GitHub by win4r. 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 👇