home / skills / eyadsibai / ltk / meeting-analysis
This skill analyzes meeting transcripts to reveal communication patterns and provide actionable feedback for improvement.
npx playbooks add skill eyadsibai/ltk --skill meeting-analysisReview the files below or copy the command above to add this skill to your agents.
---
name: meeting-analysis
description: Use when "analyzing meetings", "meeting transcripts", "communication patterns", "speaking habits", or asking about "filler words", "conflict avoidance", "facilitation style"
version: 1.0.0
---
<!-- Adapted from: awesome-claude-skills/meeting-insights-analyzer -->
# Meeting Insights Analyzer
Analyze meeting transcripts to uncover communication patterns and actionable feedback.
## When to Use
- Analyzing communication patterns across meetings
- Getting feedback on leadership/facilitation style
- Identifying conflict avoidance behaviors
- Understanding speaking habits and filler words
- Tracking improvement over time
- Coaching team members on communication
## Pattern Recognition
### Conflict Avoidance
- Hedging language ("maybe", "kind of", "I think")
- Indirect phrasing instead of direct requests
- Changing subject when tension arises
- Agreeing without commitment ("yeah, but...")
### Speaking Ratios
- Percentage of meeting spent speaking
- Interruptions given and received
- Average speaking turn length
- Question vs. statement ratio
### Filler Words
- Count "um", "uh", "like", "you know", "actually"
- Frequency per minute or speaking turn
- Situations where they increase
### Active Listening
- Questions referencing others' points
- Paraphrasing or summarizing
- Building on contributions
- Clarifying questions
### Leadership & Facilitation
- Decision-making approach (directive vs. collaborative)
- How disagreements are handled
- Inclusion of quieter participants
- Time management and agenda control
## Analysis Output Format
```markdown
# Meeting Insights Summary
**Analysis Period**: [Date range]
**Meetings Analyzed**: [X meetings]
## Key Patterns Identified
### 1. [Pattern Name]
- **Observed**: [What was seen]
- **Impact**: [Why it matters]
- **Recommendation**: [How to improve]
### [Pattern Example]
**[Meeting Name]** - [Timestamp]
**What Happened**:
> [Actual quote from transcript]
**Why This Matters**:
[Explanation of impact]
**Better Approach**:
[Specific alternative]
## Speaking Statistics
- Average speaking time: X% of meeting
- Questions asked: X per meeting
- Filler words: X per minute
- Interruptions: X given / Y received
## Next Steps
1. [Concrete action]
2. [Concrete action]
```
## Getting Transcripts
| Source | How to Get |
|--------|-----------|
| Zoom | Enable cloud recording with transcription |
| Google Meet | Use auto-transcription, save docs |
| Fireflies.ai | Export transcripts in bulk |
| Otter.ai | Export and store locally |
## Best Practices
- Use consistent naming: `YYYY-MM-DD - Meeting Name.txt`
- Review monthly or quarterly for trends
- Focus on one improvement area at a time
- Keep sensitive meeting data local
## Common Analysis Requests
- "When do I avoid difficult conversations?"
- "How often do I interrupt others?"
- "What's my speaking vs. listening ratio?"
- "Do I ask good questions?"
- "How do I handle disagreement?"
- "Am I inclusive of all voices?"
- "Do I use too many filler words?"
This skill analyzes meeting transcripts to surface communication patterns, speaking habits, and facilitation dynamics. It provides concise, actionable feedback on filler words, interruptions, inclusion, and conflict avoidance. The outputs focus on measurable speaking statistics and clear recommendations you can apply immediately.
The skill parses transcripts to identify patterns like hedging language, filler words, speaking ratios, interruptions, and active listening behaviors. It quantifies metrics (filler words per minute, speaking percent, question vs statement ratio) and links examples to impact and recommendations. Results are delivered as a structured summary with concrete next steps and sample quotes from the transcripts.
What transcript sources are supported?
Any text transcript works; common sources include cloud recordings with transcription, exported transcripts from meeting tools, or human-generated notes.
Can it track improvement over time?
Yes. By comparing consistent metrics across date ranges you can observe changes in filler words, speaking ratios, interruptions, and other patterns.