twinmind-core-workflow-a

v2026.09.24

Execute TwinMind primary workflow: Meeting transcription and summary generation. Use when implementing meeting capture, building transcription features, or automating meeting documentation. Trigger with phrases like "twinmind transcription workflow", "meeting transcription", "capture meeting with twinmind".

GitHub
安装命令
npx skhub add jeremylongshore/twinmind-core-workflow-a
Markdown
SKILL.md

TwinMind Core Workflow A: Meeting Transcription & Summary

Contents

Overview

Primary workflow for capturing meetings, generating transcripts with speaker diarization, and creating AI summaries with action items.

Prerequisites

  • Completed twinmind-install-auth setup
  • TwinMind Pro/Enterprise for API access
  • Valid API credentials configured
  • Audio source available (live or file)

Instructions

Step 1: Initialize Meeting Capture

Build a MeetingCapture class with startLiveCapture() for real-time recording and transcribeRecording() for file-based transcription. Use Ear-3 model with auto language detection and speaker diarization.

Step 2: Generate AI Summary

Create a SummaryGenerator with generateSummary() (brief/detailed/bullet-points formats), generateFollowUpEmail(), and generateMeetingNotes() methods.

Step 3: Handle Speaker Identification

Build a SpeakerManager that extracts speakers from transcript segments, calculates speaking time per speaker, and optionally matches speakers to calendar attendees.

Step 4: Orchestrate Complete Workflow

Wire everything together in processMeeting(): transcribe audio, then generate summary and identify speakers in parallel, optionally produce follow-up email and meeting notes.

See detailed implementation for complete MeetingCapture, SummaryGenerator, SpeakerManager, and orchestration code.

Output

  • Complete meeting transcript with timestamps
  • Speaker-labeled segments
  • AI-generated summary
  • Extracted action items with assignees
  • Optional follow-up email draft
  • Optional formatted meeting notes

Error Handling

ErrorCauseSolution
Transcription timeoutLarge audio fileIncrease maxWaitMs or use async callback
Speaker match failedNo calendar dataProvide attendees list manually
Summary generation failedTranscript too shortEnsure minimum 30s of audio
Audio format unsupportedWrong codecConvert to MP3/WAV/M4A
Rate limit exceededToo many requestsImplement queue-based processing

Examples

Basic usage: Apply twinmind core workflow a to a standard project setup with default configuration options.

Advanced scenario: Customize twinmind core workflow a for production environments with multiple constraints and team-specific requirements.

Audio Format Support

FormatSupportedNotes
MP3YesRecommended
WAVYesBest quality
M4AYesiOS recordings
WebMYesBrowser recordings

Resources

  • TwinMind Transcription API
  • Ear-3 Model Details
  • Audio Format Guide

Next Steps

For action item extraction and follow-up automation, see twinmind-core-workflow-b.

发现
标签

此技能尚未发布标签。

版本
最新版本元数据

版本

v2026.09.24

发布时间

2026年9月24日

分类

未分类

许可证

MIT

源路径

skills/.curated/twinmind-core-workflow-a

默认分支

main

最新提交

e5a6c3b

Tree SHA

c2dc8e8