meeting-minutes
Converts audio recordings into structured meeting minutes.
Install
mkdir -p .claude/skills/meeting-minutes-cm-yoshikikasama && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18106" && unzip -o skill.zip -d .claude/skills/meeting-minutes-cm-yoshikikasama && rm skill.zipInstalls to .claude/skills/meeting-minutes-cm-yoshikikasama
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
音声文字起こしから議事録を生成Key capabilities
- →Confirm audio files in the input directory
- →Perform transcription of audio files
- →Read the latest transcription file
- →Generate detailed meeting minutes in Japanese
- →Save meeting minutes to the 05_Meetings folder
- →Report the path of the generated meeting minutes file
How it works
The skill transcribes audio files, reads the transcription, and generates detailed meeting minutes in Japanese, including an overview, reports, discussions, decisions, and action items.
Inputs & outputs
When to use meeting-minutes
- →Summarizing team meetings
- →Creating action items from discussions
- →Documenting meeting outcomes
About this skill
議事録生成
タスク
- inputディレクトリの音声ファイルを確認し文字起こしを実行
- 最新の文字起こしファイルを読み込む
- 詳細な議事録を生成し05_Meetingsフォルダに保存
引数
/meeting-minutes YYYY-MM-DD 会議名 の形式で日付と会議名を指定可能。
- 引数あり → 指定された日付と会議名を使用
- 引数なし → 実行日の日付を使用し、会議名はユーザーに確認
ステップ1: 音声ファイル確認と文字起こし
ls .claude/skills/scripts/audio_video_to_text/input/
cd .claude/skills/scripts/audio_video_to_text && uv run audio_video_to_text.py
ステップ2: 最新の文字起こしファイル読み込み
ls -la .claude/skills/scripts/audio_video_to_text/output/
outputディレクトリから最新の*_transcript.txtファイルを見つけて読み込む。
読み込み後、出力ファイルをクリーンアップする。
cd .claude/skills/scripts/audio_video_to_text && uv run audio_video_to_text.py --cleanup
ステップ3: 議事録生成
文字起こし内容を分析し、詳細な議事録を日本語で生成する。引数で指定された日付と会議名（または実行日と確認した会議名）を使用し、05_Meetings/YYYY-MM-DD_会議名.mdに保存。
重要: 分析前に必ず文字起こし内容を読み込むこと。すべての内容を日本語で生成すること。
議事録の要件
以下を含む詳細な議事録を生成する
- 会議概要 - 会議の概要、日時、参加者、目的
- 報告事項 - 報告内容と重要な情報
- 討議事項 - 議論内容と質疑応答
- 決定事項 - 決定事項と合意事項
- アクションアイテム - 誰が、何を、いつまでに
- メモ - 重要な備考と課題
すべてのステップを実行し、生成された議事録ファイルのパスをユーザーに報告すること。
When not to use it
- →When the input is not an audio file
- →When meeting minutes are not required in Japanese
- →When the output format is not a Markdown file
Limitations
- →Requires audio files for transcription
- →Generates meeting minutes only in Japanese
- →Output is a Markdown file with a specific structure
How it compares
This skill automates the entire process from audio transcription to structured meeting minutes generation, providing a complete solution compared to manual transcription and report writing.
Compared to similar skills
meeting-minutes side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| meeting-minutes (this skill) | 0 | 6mo | Review | Beginner |
| meeting-minutes | 41 | 5mo | No flags | Beginner |
| transcribe | 11 | 5mo | Review | Beginner |
| deep-reading-analyst | 1 | 8mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
meeting-minutes
github
Generate concise, actionable meeting minutes for internal meetings. Includes metadata, attendees, agenda, decisions, action items (owner + due date), and follow-up steps.
transcribe
openai
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
deep-reading-analyst
ginobefun
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems thinking, six thinking hats). Use when users want to: (1) deeply understand complex articles/content, (2) analyze arguments and identify logical flaws, (3) extract actionable insights from reading materials, (4) create study notes or learning summaries, (5) compare multiple sources, (6) transform knowledge into practical applications, or (7) apply specific thinking frameworks. Triggered by phrases like 'analyze this article,' 'help me understand,' 'deep dive into,' 'extract insights from,' 'use [framework name],' or when users provide URLs/long-form content for analysis.
history-insight
team-attention
This skill should be used when user wants to access, capture, or reference Claude Code session history. Trigger when user says "capture session", "save session history", or references past/current conversation as a source - whether for saving, extracting, summarizing, or reviewing. This includes any mention of "what we discussed", "today's work", "session history", or when user treats the conversation itself as source material (e.g., "from our conversation").
youtube-content-summary
bhaveshpabnani
Summarize YouTube or video transcript content into notes, tasks, blogs, or threads using provided transcripts, web evidence, or native audio summarization paths.
ce-slack-research
Santiagoisper
Search Slack for interpreted organizational context -- decisions, constraints, and discussion arcs -- and produce a synthesized research digest with cross-cutting analysis. Use when the user says 'search slack for', 'what did we discuss about', 'slack context for', or 'what does the team think about