Meeting transcription

Skill naity/professional-growth-agent/.claude/skills/meeting-transcription

Transcribe audio recordings from meetings (MP3, WAV, M4A) into text using AWS Transcribe serviceFrom its SKILL.md

Install

npx -y skills add naity/professional-growth-agent --skill meeting-transcription

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.7 KB, 634 tokens by cl100k_base, as published. Nobody here has run it

Meeting Transcription Skill

This skill enables transcription of meeting audio files to text using AWS Transcribe.

When to Use This Skill

Use this skill when the user:

Provides an audio recording of a meeting
Asks to transcribe a meeting
Wants to analyze meeting content from an audio file
Mentions audio files with extensions like .mp3, .wav, .m4a, .mp4, .flac

How It Works

User provides path to an audio file
This skill calls the transcribe_audio.py script with optional language parameter
The script uploads audio to S3 and uses AWS Transcribe
Returns the full transcript as plain text with speaker labels (if applicable)
You (the agent) can then analyze the transcript

Usage

IMPORTANT: Always specify the language to get speaker labels (spk_0, spk_1).

# English meeting (default)
python transcribe_audio.py /path/to/audio.mp3

# Chinese meeting
python transcribe_audio.py /path/to/audio.mp3 --language zh-CN

# Other languages
python transcribe_audio.py /path/to/audio.mp3 --language es-ES

Supported Languages:

en-US: English (US) - default
zh-CN: Mandarin Chinese (Simplified)
zh-TW: Traditional Chinese (Taiwan)
es-ES: Spanish (Spain)
fr-FR: French
de-DE: German
ja-JP: Japanese
ko-KR: Korean

Speaker Labels: All transcriptions include speaker labels (spk_0, spk_1, spk_2, etc.) to identify different speakers in the conversation. You must know the language beforehand.

Supported Audio Formats

MP3
MP4
WAV
FLAC
M4A
OGG
WebM

Usage Example

When the user says: "Analyze my 1:1 meeting recording at ./recordings/meeting.mp3"

Use this skill to transcribe the audio first
Once you have the transcript, analyze it for insights
Provide actionable feedback to the user

What to Do After Transcription

After getting the transcript, analyze it for:

Key discussion topics: What were the main themes?
Action items: What tasks were assigned or agreed upon?
Speaking balance: Who spoke more? Is it balanced?
Questions: What questions were asked? Were they answered?
Communication patterns: Any interruptions, pauses, or unclear moments?
Tone and engagement: Is the conversation collaborative or one-sided?
Constructive feedback: What could be improved for next time?

Technical Details

Requires AWS credentials configured
Requires S3 bucket for temporary audio storage
Audio files are automatically cleaned up after transcription
Transcription job names are timestamped to avoid conflicts

What ships with it: 1 file

8.6 KB alongside SKILL.md, 1 of them executable

transcribe_audio.pyruns8.6 KB

Gives 0 of the 12 instructions most video audio skills give in 634 tokens

Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07

Read individual rule files for detailed explanationsin 21 of 622, across 10 files
Render final videoin 13 of 622, across 6 files
Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
Use this skill when dealing with Remotion codein 11 of 622, across 4 files
Save generated audio to a WAV filein 11 of 622, across 4 files
Handle conversion errors gracefullyin 10 of 622, across 6 files
Add captions to videos alwaysin 10 of 622, across 4 files
Generate music from text descriptions using MusicGenin 9 of 622, across 2 files
Do not skip pipeline layersin 9 of 622, across 3 files
Do not make one tool do everythingin 9 of 622, across 3 files
Use Azure Document Intelligence for complex PDFsin 9 of 622, across 4 files
Never ask the user to paste their full API keyin 9 of 622, across 3 files

Said here and by no other author read

specify the language to get speaker labels
return the full transcript as text
analyze the transcript for key topics
identify action items in the transcript
evaluate speaking balance between speakers
extract questions from the transcript

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.