twinmind-core-workflow-a
Orchestrates meeting transcription, speaker diarization, and summary generation.
Install
mkdir -p .claude/skills/twinmind-core-workflow-a && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5407" && unzip -o skill.zip -d .claude/skills/twinmind-core-workflow-a && rm skill.zipInstalls to .claude/skills/twinmind-core-workflow-a
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Execute TwinMind primary workflow: Meeting transcription and summaryKey capabilities
- →Initialize meeting capture for real-time or file-based transcription
- →Generate AI summaries in various formats
- →Create follow-up emails and meeting notes
- →Extract speakers from transcript segments and calculate speaking time
- →Orchestrate the complete workflow from transcription to summary generation
- →Match speakers to calendar attendees
How it works
This skill captures meeting audio, transcribes it with speaker diarization using the Ear-3 model, and then generates AI summaries, action items, follow-up emails, and meeting notes. It also identifies speakers and calculates their speaking time.
Inputs & outputs
When to use twinmind-core-workflow-a
- →Implementing meeting transcription
- →Generating AI meeting notes
- →Building meeting capture features
About this skill
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-authsetup - 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
| Error | Cause | Solution |
|---|---|---|
| Transcription timeout | Large audio file | Increase maxWaitMs or use async callback |
| Speaker match failed | No calendar data | Provide attendees list manually |
| Summary generation failed | Transcript too short | Ensure minimum 30s of audio |
| Audio format unsupported | Wrong codec | Convert to MP3/WAV/M4A |
| Rate limit exceeded | Too many requests | Implement 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
| Format | Supported | Notes |
|---|---|---|
| MP3 | Yes | Recommended |
| WAV | Yes | Best quality |
| M4A | Yes | iOS recordings |
| WebM | Yes | Browser 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.
When not to use it
- →When twinmind-install-auth setup is not completed
- →When TwinMind Pro/Enterprise for API access is not available
- →When valid API credentials are not configured
Prerequisites
Limitations
- →Transcription may timeout for large audio files
- →Speaker matching can fail without calendar data
- →Summary generation requires a minimum of 30 seconds of audio
How it compares
This workflow automates the entire meeting capture and documentation process, providing structured outputs unlike manual note-taking.
Compared to similar skills
twinmind-core-workflow-a side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| twinmind-core-workflow-a (this skill) | 1 | 27d | Review | Intermediate |
| telegram-bot-builder | 106 | 6mo | Review | Intermediate |
| playwright-browser-automation | 29 | 7mo | Review | Intermediate |
| workflow-orchestration-patterns | 10 | 2mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
telegram-bot-builder
davila7
Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot.
playwright-browser-automation
lackeyjb
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
workflow-orchestration-patterns
wshobson
Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.
codex-skill
feiskyer
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.
bullmq-specialist
davila7
BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull queue, redis queue, background job, job queue.
n8n-expression-syntax
czlonkowski
Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with webhook data in workflows.