菜单
Summarize meeting transcripts or notes into actionable format. Invoke when user provides meeting transcripts, notes, or wants actionable meeting summaries.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | fabric-summarize-meeting |
| description | Summarize meeting transcripts or notes into actionable format. Invoke when user provides meeting transcripts, notes, or wants actionable meeting summaries. |
| allowed-tools | ["Read","WebFetch","Bash","Write"] |
Extract key information from meeting content (transcript, notes, recording) into an actionable summary with decisions and action items.
User provides one of:
From clipboard:
pbpaste > /tmp/meeting_content.txt
cat /tmp/meeting_content.txt
From file: Read the file using Read tool.
From URL: Use WebFetch to extract content.
From the meeting content, extract:
Present the summary in clean markdown:
# Meeting Summary: [Brief Title]
## Meeting Overview
- **Date**: [Date if known]
- **Participants**: [List of attendees]
- **Purpose**: [Main meeting objective]
## One-Sentence Summary
[20 words or less]
## Topics Discussed
- [Topic 1]: [Brief summary]
- [Topic 2]: [Brief summary]
## Decisions
- [Decision 1]
- [Decision 2]
## Action Items
- [ ] [Action] (@person, due: [date])
- [ ] [Action] (@person, due: [date])
## Open Questions
- [Question needing follow-up]
## Key Context
- [Important background]
If user requests, save to their notes location:
# Example: Save to a meetings directory
mkdir -p ~/notes/meetings/
cat > ~/notes/meetings/$(date +%Y-%m-%d)-meeting-title.md << 'EOF'
[Summary content]
EOF
From pasted text:
/summarize-meeting
[User pastes meeting notes]
From clipboard:
/summarize-meeting clipboard
From file:
/summarize-meeting ~/Downloads/meeting-transcript.txt
No content provided:
Content too short:
Audio/Video URL:
Philosophy: Meetings generate information that quickly becomes lost. This command captures the signal (decisions, actions) and discards the noise (tangents, repetition).
Guide users through progressive lessons to learn AI assistant basics
Load context from previous sessions so you can pick up where you left off
Save what you worked on so your AI can pick it up next time
Example skill demonstrating the skill structure. Use as a template for creating your own skills.
Extract actionable content and filter hype/marketing from videos and articles. Invoke when user provides content with potential hype/marketing, wants signal without noise, or needs bullshit filtering.
Improve LLM prompts using prompt engineering best practices. Invoke when user wants to optimize prompts, improve slash commands, or apply prompt engineering.