meeting-intelligence

Extract decisions, action items, questions, and insights from meeting transcripts.

15|3|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/LazyIsEfficient/agentic-os --skill meeting-intelligence-lazyisefficient
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: meeting-intelligence
Source: https://github.com/LazyIsEfficient/agentic-os/tree/main/.claude/skills/meeting-intelligence
Command: npx skills add https://github.com/LazyIsEfficient/agentic-os --skill meeting-intelligence-lazyisefficient

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, openai, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Meeting notes often become lost and unactionable. This skill automates the extraction of decisions, action items (with owner and deadline), open questions, key insights, and follow-ups from transcripts, turning scattered conversations into trackable outputs.

Core Features & Use Cases

  • Extract decisions with who drove them and context.
  • Capture action items with owner, deadline, priority, and source quotes.
  • Identify open questions, key insights, and follow-up meetings.
  • Catches implicit commitments and can push actions to HubSpot as tasks.
  • Supports batch processing of directories of transcripts and outputs in Markdown or JSON.

Quick Start

Feed a meeting transcript to the tool and receive structured decisions, actions with owners and deadlines, open questions, insights, and follow-ups in Markdown or JSON.

Frequently Asked Questions about meeting-intelligence

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract action items with owners and deadlines from meeting transcripts?

To extract action items from meeting transcripts, feed the text into the tool to automatically identify decisions, open questions, and follow-ups. It captures action items with owner, deadline, and priority using LLM APIs and outputs structured Markdown or JSON.

Can I process multiple meeting transcripts in batch and export the results as JSON?

Yes, you can process multiple meeting transcripts in batch by pointing the tool at a directory of files. It parses each transcript to extract key insights and outputs the structured results in either Markdown or JSON format.

Do I need an Anthropic or OpenAI API key to extract decisions from meeting notes?

Yes, you need LLM access via an ANTHROPIC_API_KEY or OPENAI_API_KEY to extract decisions and action items from meeting notes. The tool relies on these APIs to process transcript text and identify implicit commitments.

How does meeting transcript extraction push action items directly to HubSpot?

Meeting transcript extraction pushes action items to HubSpot by using an optional HUBSPOT_API_KEY. Once configured, the tool automatically creates HubSpot tasks from the captured action items, owners, and deadlines identified in the transcript.

What is the best way to capture implicit commitments and open questions from meeting notes?

The best way to capture implicit commitments and open questions from meeting notes is to use an NLP tool that analyzes transcript text via LLMs. It identifies context, source quotes, and follow-up meetings that are often missed manually.

Can I pipe meeting transcripts through stdin for real-time action item extraction?

Yes, you can pipe meeting transcripts through stdin for action item extraction. The tool supports single transcripts, stdin, and batch directory processing to capture decisions, action items, and key insights.