meeting-insights-analyzer

Analyze meeting transcripts to detect communication patterns and behavioral signals.

1|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/pkoka888/server-infra-templates --skill meeting-insights-analyzer-pkoka888
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: meeting-insights-analyzer
Source: https://github.com/pkoka888/server-infra-templates/tree/main/.kilo/skills/marketplace/meeting-insights-analyzer
Command: npx skills add https://github.com/pkoka888/server-infra-templates --skill meeting-insights-analyzer-pkoka888

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill turns raw meeting transcripts and recordings into clear, actionable insights about communication habits and leadership behaviors so professionals can improve clarity, listening, and meeting effectiveness.

Core Features & Use Cases

  • Pattern Recognition: Detects conflict avoidance, hedging language, interruptions, question vs. statement ratios, and speaker dominance across meetings.
  • Communication Analysis: Measures filler words, speaking time ratios, turn length, sentiment trends, and facilitation quality with timestamped examples.
  • Actionable Feedback & Tracking: Provides specific examples with "what happened", "why it matters", and "better approach", and compares trends over time for coaching or performance reviews.
  • Support for Multiple Formats: Works with common transcript types (txt, md, vtt, srt, docx) and extracts speaker labels and timestamps when available.
  • Use Case: A manager analyzes monthly 1:1s to reduce interruptions, remove hedging language, and demonstrate improvement in a performance review.

Quick Start

Analyze all transcripts in the current folder and report conflict avoidance instances, speaking ratios, filler words, interruptions, and timestamped examples with improvement suggestions.

Frequently Asked Questions about meeting-insights-analyzer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze meeting transcripts to identify filler words and speaking time ratios?

Meeting transcript analysis detects filler words, computes speaking time ratios, and counts interruptions by processing txt, md, vtt, srt, or docx files. It extracts timestamped examples and summarizes communication patterns across single or multiple meetings.

Can I detect conflict avoidance and hedging language in meeting transcripts?

Conflict avoidance detection in meeting transcripts identifies hedging language, question versus statement ratios, and speaker dominance patterns. The analysis provides specific behavioral examples with context on why it matters and suggests a better approach for facilitation improvement.

Does transcript analysis work with vtt and srt subtitle files containing speaker labels?

Transcript analysis supports vtt and srt subtitle formats, automatically detecting and extracting speaker labels and timestamps when present. This allows accurate identification of interruptions, turn length, and individual speaking ratios across the meeting.

How do I track communication trends over time for performance reviews using 1:1 transcripts?

Tracking communication trends over time compares multiple meeting transcripts to highlight behavioral changes in interruptions, hedging, and facilitation quality. It generates timestamped feedback with specific examples to support coaching and performance reviews.

What is the best way to extract actionable feedback from raw meeting transcripts?

Extracting actionable feedback from raw meeting transcripts involves identifying behavioral signals like sentiment patterns and speaker dominance, then mapping them to structured outputs with specific examples to improve clarity, listening, and meeting effectiveness.

Are there limitations when analyzing meeting transcripts without speaker labels or timestamps?

Analysis of meeting transcripts without speaker labels or timestamps limits the ability to compute individual speaking ratios, identify specific interruptions, and extract accurate turn lengths, reducing the precision of behavioral feedback and dominance detection.