Action Item Extractor logo

Action Item Extractor

OrganizationPopular
microsoft
action-item-extractor

Extract action items with owners, deadlines, and priorities from meeting content

Overview

Publishermicrosoft
Repositorywork-iq
Skill nameaction-item-extractor
Stars
1K
Forks
140
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 microsoft on GitHub. Read the source before you install it.

Installation

Install the Action Item Extractor 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/microsoft/work-iq/tree/main/plugins/workiq-productivity/skills/action-item-extractor
  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/work-iq.git /tmp/work-iq
mkdir -p .claude/skills
cp -r /tmp/work-iq/plugins/workiq-productivity/skills/action-item-extractor .claude/skills/action-item-extractor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Action Item Extractor 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 Action Item Extractor 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 Action Item Extractor 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.

Action Item Extractor

Description

Parses Teams meeting chat messages for action-oriented language — commitments, assignments, and deadlines. Cross-references owners against the attendee list and assigns priority levels. Outputs a structured table ready for downstream recipes.

Prerequisites

RequirementDetails
WorkIQ CLIUser profile, meeting details, chat messages (read queries via ask)

Required Inputs

InputTypeDescription
meeting_identifierstringMeeting title, keyword, or "latest"
datestring (optional)Target date (defaults to today)

Execution Steps

Step 1: Retrieve User Profile, Meeting Details, and Attendees

workiq-ask (
  question: "What is my profile including display name and time zone? Also find the meeting matching '<meeting_identifier>' on <date> and list all attendees with their names and email addresses."
)

Extract: displayName, time zone, attendee list with names and emails.

Step 2: Pull Teams Meeting Chat Messages

workiq-ask (
  question: "Get all chat messages from the Teams meeting '<meeting subject>' held on <date>, including sender names and timestamps."
)

Step 3: Parse for Action-Oriented Language

Scan messages for:

  • Explicit assignments: "[name] will...", "AI: [person] to..."
  • Commitments: "I'll handle...", "Let me take care of..."
  • Deadlines: "by Friday", "end of sprint", "before next meeting"
  • Urgency markers: "ASAP", "urgent", "blocker", "critical"

Step 4: Cross-Reference Owners Against Attendee List

Match extracted owner names to attendees[] from Step 1. Flag any unresolved names.

Step 5: Assign Priority

  • P1 (High): Contains urgency markers, blocker language, or executive requests
  • P2 (Medium): Standard commitments with deadlines
  • P3 (Low): Nice-to-haves, "when you get a chance" items

Step 6: Format Action Items Table

#DescriptionOwnerDue DatePriority
1.........P1/P2/P3

Step 7: Output Structured Data

Return action items as structured data, plus inline display for the user.


Error Handling

ErrorSolution
No chat messagesReport "No meeting content found"
Unresolved owner namesList as "[Unresolved: partial name]" for user clarification
No deadlines mentionedMark all due dates as "TBD"

Output

Returns: structured action item list with owners, due dates, and priorities. Usable as input for downstream recipes.

Instructions

This skill is invoked by recipes or orchestration agents — not directly by end users. To invoke it, supply the required inputs and ensure authentication is configured.

  1. Set the meeting identifier: Pass a meeting title keyword (e.g., "sprint planning"), a partial title, or "latest" to target the most recent meeting.
  2. Optionally specify a date: Provide an ISO date string (e.g., "2026-03-03") to scope the calendar lookup. Omit to default to today.
  3. Invoke the skill: Pass meeting_identifier (and optionally date) as inputs. The skill will execute Steps 1–7 automatically.
  4. Consume the output: The structured action item table is returned as data and is also rendered inline for the user.

Examples

Example 1: Extract items from today's sprint planning meeting

json
{
  "meeting_identifier": "sprint planning",
  "date": "2026-03-03"
}

Output (sample):

#DescriptionOwnerDue DatePriority
1Update API docs with new endpoint schemaFirstname1 Lastname12026-03-07P2
2Fix login blocker bug before releaseFirstname2 Lastname22026-03-04P1
3Review UX mocks when you get a chance[Unresolved: Firstname3]TBDP3

Example 2: Extract items from the latest meeting (no date specified)

json
{
  "meeting_identifier": "latest"
}

The skill resolves today's date from the user profile time zone, finds the most recently concluded meeting, and parses its chat transcript for action items.


Example 3: Target a specific meeting by keyword on a past date

json
{
  "meeting_identifier": "Q1 budget review",
  "date": "2026-02-28"
}

The skill searches calendar events on February 28 for a meeting matching "Q1 budget review", fetches its Teams chat, and returns all commitments made — including any flagged with "ASAP" or "before end of quarter" language as P1 items.

Frequently asked questions

What does the Action Item Extractor AI skill do?

Extract action items with owners, deadlines, and priorities from meeting content

Why use Action Item Extractor on TypingMind?

Because you install it once and use it with any model. Action Item Extractor 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 Action Item Extractor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/microsoft/work-iq/tree/main/plugins/workiq-productivity/skills/action-item-extractor. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Action Item Extractor?

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 Action Item Extractor?

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

Is the Action Item Extractor AI skill free?

It is published on GitHub by microsoft. 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 👇