smithery.ai

analyze-meeting

Extract insights from a meeting transcript including summary, action items, decisions, and key topics. Use when the user wants to analyze a transcript, extract meeting notes, find action items, or summarize a meeting.

First seen Mar 21, 2026

Installation

$ npx skills add https://smithery.ai

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,454 B
  • docs SUMMARY.md 240 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Analyze Meeting Transcript

Parse a VTT transcript and extract structured insights.

Instructions

  1. Read the transcript from projects/{project}/transcripts/{date}.vtt
  2. Parse the VTT format and extract the conversation
  3. Analyze the content and extract:

Required Extractions

  • Summary: 2-3 sentence overview of the meeting
  • Attendees: List of participants (from speaker labels like "Speaker 1:", names, etc.)
  • Key Topics: Main subjects discussed (3-7 bullet points)
  • Decisions Made: Any explicit decisions or agreements reached
  • Action Items: Tasks mentioned with:

- Task description - Owner (if mentioned) - Deadline (if mentioned)

  • Open Questions: Unresolved questions or concerns raised
  • Next Steps: Follow-up items or future meeting topics
  1. Save the analysis to projects/{project}/analysis/{date}.json

VTT Format Reference

WebVTT files contain timestamped captions:

WEBVTT

00:00:00.000 --> 00:00:05.000
Speaker 1: Hello everyone, let's get started.

00:00:05.000 --> 00:00:12.000
Speaker 2: Sure, first item on the agenda is...

Extract speaker names from labels like "Speaker 1:", "John:", "[John Smith]", etc.