Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
.claude/skills/aiskillstore-meeting-insights-analyzer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 86% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-03 | ✓→✗ | ▼ Worse | -32% | 0% |
| case-08 | ✓→✓ | = Same ✓ | 40% | 0% |
This skill transforms your meeting transcripts into actionable insights about your communication patterns, helping you become a more effective communicator and leader.
~/meetings/)textAnalyze all meetings in this folder and tell me when I avoided conflict.
textLook at my meetings from the past month and identify my communication patterns.
textCompare my facilitation style between these two meeting folders.
textAnalyze all transcripts in this folder and: 1. Identify when I interrupted others 2. Calculate my speaking ratio 3. Find moments I avoided giving direct feedback 4. Track my use of filler words 5. Show examples of good active listening
When a user requests meeting analysis:
If not specified, ask what they want to learn:
For each requested insight:
Conflict Avoidance:
Speaking Ratios:
Filler Words:
Active Listening:
Leadership & Facilitation:
For each pattern found, include:
markdown ### Pattern Name]
Finding: One-sentence summary of the pattern]
Frequency: X times across Y meetings]
Examples:
What Happened: > Actual quote from transcript]
Why This Matters: Explanation of the impact or missed opportunity]
Better Approach: Specific alternative phrasing or behavior]
Repeat for 2-3 strongest examples]
After analyzing all patterns, provide:
markdown # Meeting Insights Summary
Analysis Period: Date range] Meetings Analyzed: X meetings] Total Duration: X hours]
## Key Patterns Identified
### 1. Primary Pattern]
### 2. Second Pattern] Same structure]
## Communication Strengths
## Growth Opportunities
## Speaking Statistics
## Next Steps
3-5 concrete actions to improve communication]
User: "I download all of my meeting recordings and put them in a folder. Tell me all the times I've subtly avoided conflict."
Output:
markdown# Conflict Avoidance Patterns Found 23 instances across 15 meetings where you used indirect communication or avoided addressing tensions directly. ## Pattern: Hedging on Critical Feedback **Frequency**: 8 times across 7 meetings **Example 1: 1:1 with Sarah** - 00:14:32 **What Happened**: > "So, I was thinking... maybe we could, like, potentially > consider looking at the timeline again? I mean, if you > think that makes sense. But whatever you think is best!" **Why This Matters**: You needed to address that Sarah's project was behind schedule, but the hedging language ("maybe", "potentially", "if you think") and the deflection at the end ("whatever you think") made it easy for her to miss the urgency. **Better Approach**: "Sarah, the project is two weeks behind schedule. We need to discuss what's blocking progress and create a new timeline today." [Additional examples...] ## Recommendations 1. **Name the issue directly** in the first sentence 2. **Remove hedging words** like "maybe," "kind of," "sort of" 3. **Ask specific questions** instead of hinting 4. **Schedule difficult conversations** instead of raising them casually
User: "Analyze my team meetings and tell me about my facilitation style."
Output: Provides insights on:
User: "Compare my meetings from Q1 vs. Q2 to see if I've improved my listening skills."
Output: Creates a comparative analysis showing:
From Granola (free with Lenny's newsletter subscription):
From Zoom:
From Google Meet:
From Fireflies.ai, Otter.ai, etc.:
YYYY-MM-DD - Meeting Name.txt format| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,029 | 3,336 | -53% | 1 | 1 | 0% | 1,201 | 2,532 | +111% | 0 | 0 | — |
case-08 | pass→pass | 15,797 | 9,108 | -42% | 1 | 1 | 0% | 2,673 | 3,743 | +40% | 0 | 0 | — |
case-02 | fail→fail | 7,606 | 1,877 | -75% | 1 | 1 | 0% | 1,253 | 2,577 | +106% | 0 | 0 | — |
case-03 | pass→fail | 25,194 | 5,168 | -79% | 1 | 1 | 0% | 3,970 | 2,691 | -32% | 0 | 0 | — |
case-04 | fail→fail | 7,184 | 6,672 | -7% | 1 | 1 | 0% | 1,136 | 3,268 | +188% | 0 | 0 | — |
case-05 | pass→pass | 16,563 | 13,340 | -19% | 1 | 1 | 0% | 3,348 | 4,909 | +47% | 0 | 0 | — |
case-06 | pass→pass | 14,485 | 17,293 | +19% | 1 | 1 | 0% | 2,335 | 4,423 | +89% | 0 | 0 | — |
case-07 | pass→pass | 13,970 | 9,938 | -29% | 1 | 1 | 0% | 2,112 | 3,668 | +74% | 0 | 0 | — |
case-09 | pass→pass | 15,634 | 14,970 | -4% | 1 | 1 | 0% | 2,534 | 4,671 | +84% | 0 | 0 | — |
case-10 | pass→pass | 16,990 | 10,005 | -41% | 1 | 1 | 0% | 2,549 | 3,780 | +48% | 0 | 0 | — |
case-11 | pass→pass | 14,776 | 9,061 | -39% | 1 | 1 | 0% | 2,081 | 3,453 | +66% | 0 | 0 | — |
case-12 | pass→pass | 10,639 | 3,009 | -72% | 1 | 1 | 0% | 1,662 | 2,748 | +65% | 0 | 0 | — |
case-13 | pass→pass | 10,973 | 5,992 | -45% | 1 | 1 | 0% | 1,678 | 3,220 | +92% | 0 | 0 | — |
case-14 | fail→pass | 17,557 | 6,419 | -63% | 1 | 1 | 0% | 2,765 | 3,202 | +16% | 0 | 0 | — |
case-15 | pass→pass | 11,768 | 5,225 | -56% | 1 | 1 | 0% | 1,683 | 3,081 | +83% | 0 | 0 | — |
case-16 | pass→pass | 14,016 | 8,179 | -42% | 1 | 1 | 0% | 2,153 | 3,464 | +61% | 0 | 0 | — |
case-17 | pass→pass | 16,109 | 11,278 | -30% | 1 | 1 | 0% | 2,437 | 4,122 | +69% | 0 | 0 | — |
case-18 | pass→pass | 12,906 | 12,937 | +0% | 1 | 1 | 0% | 2,115 | 4,159 | +97% | 0 | 0 | — |
case-19 | pass→pass | 12,527 | 3,153 | -75% | 1 | 1 | 0% | 1,807 | 2,619 | +45% | 0 | 0 | — |
case-20 | fail→pass | 10,834 | 6,456 | -40% | 1 | 1 | 0% | 1,779 | 3,316 | +86% | 0 | 0 | — |
case-21 | fail→pass | 13,512 | 6,585 | -51% | 1 | 1 | 0% | 1,993 | 3,226 | +62% | 0 | 0 | — |
case-22 | pass→pass | 15,347 | 13,979 | -9% | 1 | 1 | 0% | 2,275 | 4,394 | +93% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.