← Back to Skills

meeting-intelligence-system

OneWave-AI
Updated Today
16 views
11
4
11
View on GitHub
Metaai

About

This skill analyzes meeting transcripts to extract structured information including decisions, action items, blockers, and sentiment. It is used when developers provide meeting notes or recordings to generate summaries, track actions, or create follow-up emails. The system transforms unstructured conversation into actionable insights and deliverables.

Documentation

Meeting Intelligence System

Transform meeting transcripts into actionable insights, decisions, and follow-ups.

When to Use This Skill

Activate when the user:

  • Provides a meeting transcript or recording
  • Asks to "analyze this meeting"
  • Needs action items extracted from notes
  • Wants to generate meeting minutes
  • Asks for decisions made in a meeting
  • Needs a follow-up email created
  • Mentions meeting notes or transcripts

Instructions

  1. Extract Meeting Metadata

    • Identify meeting title/topic
    • Note participants (if mentioned)
    • Determine meeting date/time (if available)
    • Identify meeting type (standup, planning, retrospective, etc.)
  2. Identify Decisions Made

    • Extract all explicit decisions
    • Note who made each decision (if clear)
    • Include rationale for decisions (if stated)
    • Flag tentative decisions vs. final decisions
    • Note decisions that need follow-up approval
  3. Extract Action Items

    • List all tasks assigned or volunteered
    • Identify owner for each action item
    • Note deadlines or timeframes mentioned
    • Flag action items without clear owners
    • Prioritize action items (if priority discussed)
    • Note dependencies between action items
  4. Identify Blockers and Risks

    • Extract mentioned blockers
    • Note risks or concerns raised
    • Identify unresolved issues
    • Flag items needing escalation
    • Note resource constraints mentioned
  5. Analyze Discussion Sentiment

    • Gauge overall meeting tone (productive, tense, confused, aligned)
    • Identify areas of agreement and disagreement
    • Note team morale indicators
    • Flag conflict or tension points
  6. Extract Key Topics Discussed

    • Summarize main discussion points
    • Note questions raised
    • Identify topics needing follow-up
    • Highlight important context or background
  7. Generate Follow-Up Communications

    • Create meeting minutes/summary
    • Draft action item tracking email
    • Suggest calendar invites for follow-ups
    • Recommend next steps

Output Format

# Meeting Summary: [Title]
**Date**: [Date] | **Participants**: [Names]

## πŸ“‹ Executive Summary
[2-3 sentence overview of meeting purpose and outcome]

## βœ… Decisions Made
1. **[Decision]**
   - Owner: [Name]
   - Rationale: [Why]
   - Status: Final / Needs approval

## 🎯 Action Items
| Priority | Action | Owner | Deadline | Status |
|----------|--------|-------|----------|--------|
| High | [Task] | [Name] | [Date] | Not started |
| Medium | [Task] | [Name] | [Date] | Not started |

## 🚧 Blockers & Risks
1. **[Blocker]** - [Impact] - Needs: [Action]
2. **[Risk]** - [Mitigation plan]

## πŸ’¬ Key Discussion Points
- [Topic 1]: [Summary]
- [Topic 2]: [Summary]

## ❓ Open Questions
1. [Question] - Owner: [Who will answer]

## πŸ“Š Sentiment Analysis
- **Overall Tone**: [productive/tense/etc.]
- **Team Alignment**: [high/medium/low]
- **Concerns Raised**: [Summary]

## πŸ“§ Follow-Up Email Draft

Subject: Action Items from [Meeting Title] - [Date]

Hi team,

Thanks for joining today's [meeting type]. Here are our key outcomes:

**Decisions:**
- [Decision 1]

**Your Action Items:**
[Name]: [Task] by [Date]

**Blockers:**
- [Blocker] - please [action]

Next meeting: [Date/Time]

Best,
[Your name]

Examples

User: "Analyze this standup transcript" Response: Extract blockers mentioned β†’ List action items per person β†’ Flag impediments β†’ Note team velocity concerns β†’ Generate summary with focus on blockers

User: "Create action items from this product planning meeting" Response: Identify all decisions (feature prioritization) β†’ Extract action items (design mockups, tech spec) β†’ Assign owners β†’ Set deadlines β†’ Create tracking table β†’ Draft follow-up email

Best Practices

  • Be specific with action items (not vague "look into X")
  • Always try to identify owners (flag if unclear)
  • Differentiate between decisions and proposals
  • Preserve important context for decisions
  • Flag action items without deadlines
  • Note commitments made by each participant
  • Include relevant quotes for controversial decisions
  • Use clear, scannable formatting
  • Prioritize action items by urgency
  • Flag dependencies between tasks
  • Generate professional, actionable follow-up emails

Quick Install

/plugin add https://github.com/OneWave-AI/claude-skills/tree/main/meeting-intelligence

Copy and paste this command in Claude Code to install this skill

GitHub δ»“εΊ“

OneWave-AI/claude-skills
Path: meeting-intelligence

Related Skills

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill

evaluating-llms-harness

Testing

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

View skill

llamaguard

Other

LlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.

View skill

langchain

Meta

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

View skill