meeting-minutes-taker

Generates structured meeting minutes from raw transcripts using multi-pass generation and union merging.

1.4k|216|Updated Oct 22, 2025
One-click install
npx skills add https://github.com/daymade/claude-code-skills --skill meeting-minutes-taker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: meeting-minutes-taker
Source: https://github.com/daymade/claude-code-skills/tree/main/daymade-audio/meeting-minutes-taker
Command: npx skills add https://github.com/daymade/claude-code-skills --skill meeting-minutes-taker

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Raw meeting transcripts are long, noisy, and hard to act on; this Skill converts them into structured, evidence-based meeting minutes with decisions, action items, and speaker attribution while minimizing content loss.

Core Features & Use Cases

  • Multi-pass generation with UNION merge: Spawns parallel subagents that each produce complete minutes, then merges all versions so no decision, action item, or diagram is lost.
  • Speaker identification: Resolves anonymous labels like "Speaker 1/2" via source-platform relabeling first, with feature-analysis fallback mapped against a team directory in context.md.
  • Retrieval self-test: A fresh-context subagent extracts future-query claims from the transcript and hit-tests them against the minutes, promoting missed directives with verbatim quotes.
  • Use Case: Given a Feishu Minutes export of a two-hour API design review, produce minutes with key decisions (each backed by quotes), an action item table with owners and deadlines, Mermaid sequence diagrams, and a parking lot of deferred items.

Quick Start

Ask the AI to generate meeting minutes from your transcript file, optionally providing a context.md team directory for speaker identification.

Frequently Asked Questions about meeting-minutes-taker

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

FAQPage Schema
How do I generate meeting minutes from a transcript?

Provide the transcript file and request meeting minutes; the skill runs multiple parallel generation passes, merges them with a UNION strategy, and self-reviews against the transcript. You then review the draft and iterate until approving the final version.

How to identify anonymous speakers like Speaker 1 in meeting transcripts?

The skill first asks you to label speakers on the source platform (Feishu Minutes, Tencent Meeting) and re-export. As a fallback, it analyzes word count, speaking style, and topic focus, then matches patterns against a context.md team directory for your confirmation.

Can I merge meeting minutes from different AI tools?

Yes, you can provide output from other AI tools like Gemini or ChatGPT for cross-comparison. The skill verifies each new item against the original transcript before merging, using a UNION strategy that never removes existing content.

Does it work with Word or PDF transcript files?

Convert .docx or .pdf files to Markdown first using the doc-to-markdown skill or markitdown, which preserves tables and images. For poor-quality ASR output, run the transcript-fixer skill before generating minutes.

Why does a single pass lose content when summarizing long meetings?

A single generation pass cannot catch every decision and action item in a long transcript. The skill runs three complete passes with isolated context and merges them, since different passes catch different details that others miss.