Is my meeting data private during analysis?

Yes, the skill operates within your Claude Code environment, analyzing the local transcript files you provide in your specified directories.

What file formats does this skill support?

The skill analyzes common transcript formats including .txt, .md, .vtt, .srt, and .docx files, especially those containing speaker labels and timestamps.

Can I track my communication progress over time?

Yes, you can point the skill to multiple folders or date-ranged files to generate comparative reports and visualize growth in your communication style.

Does it calculate speaking-to-listening ratios?

Yes, it calculates the percentage of the meeting spent speaking, counts interruptions, and measures your question-vs-statement ratio.

How does it identify conflict avoidance?

It scans for hedging language (e.g., 'maybe', 'kind of'), indirect phrasing instead of direct requests, and instances where the subject is changed when tension arises.

Meeting Insights Analyzer

Name: Meeting Insights Analyzer
Author: Microck

byMicrock

•

Collaboration Tools

Analyzes meeting transcripts to uncover communication patterns, identify conflict avoidance, and provide actionable feedback for professional growth.

About

The Meeting Insights Analyzer is a specialized Claude Code skill designed to transform raw meeting transcripts into a comprehensive professional development tool. It scans your conversation data for specific behavioral markers such as filler word frequency, speaking-to-listening ratios, and subtle instances of conflict avoidance. By providing timestamped examples and comparative analysis over time, this skill helps professionals, leaders, and coaches identify communication blind spots, improve meeting facilitation, and prepare for performance reviews with objective, data-driven insights.

Key Features

Automated filler word detection and frequency tracking
Pattern recognition for conflict avoidance and indirect communication
81 GitHub stars
Active listening evaluation based on clarifying questions and paraphrasing
Longitudinal trend analysis to track communication improvements over time
Quantitative speaking statistics including speaking-to-listening ratios

Use Cases

Analyzing team dynamics and inclusivity within collaborative meetings
Preparing for performance reviews with objective meeting performance data
Professional development and communication coaching for leadership

About

Key Features

Automated filler word detection and frequency tracking
Pattern recognition for conflict avoidance and indirect communication
81 GitHub stars
Active listening evaluation based on clarifying questions and paraphrasing
Longitudinal trend analysis to track communication improvements over time
Quantitative speaking statistics including speaking-to-listening ratios

Use Cases

Analyzing team dynamics and inclusivity within collaborative meetings
Preparing for performance reviews with objective meeting performance data
Professional development and communication coaching for leadership