- Home
- Skills
- Business & Operations
- ๐ Meeting Summary
More screenshots
Works with the AI Agents you already use
๐ Meeting Summary
This skill transforms messy meeting transcriptsโwhether pasted directly or as file paths (.vtt, .srt, .txt)โinto high-fidelity, structured markdown documentation.
$5
๐ Meeting Summary
Example session with this skill installed
Summarize the notes from our sync. Extract the action items into a table and list any decisions made. Use the file at ./meeting-transcripts/dev-sync.txt
- Read your context and instructions
- Compiled the meeting summary
Action Items
| What | Who | Due Date |
|---|---|---|
| Send revised API docs | Sarah | Friday |
| Provision staging DB | Not specified | Before the demo |
Decisions
- Switched to PostgreSQL for the analytics service.
- Approved the UI mockups for the dashboard.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
This skill transforms messy meeting transcriptsโwhether pasted directly or as file paths (.vtt, .srt, .txt)โinto high-fidelity, structured markdown documentation. It goes beyond simple summarization by applying specific extraction logic to identify commitments, ownership, and project blocking questions.
Why use this skill
Prompting an AI yourself often leads to "hallucinated" action items or missed deadlines. This skill uses a specialized workflow to resolve speaker identities, extract relative due dates (e.g., "before the demo"), and differentiate between "suggestions" and factual "decisions." It saves developers and PMs from manual cleanup by formatting everything into specific, professional markdown sections including a structured task table.
Supported tools
- Direct text input from pasted transcripts.
- Local file parsing for .txt, .md, .vtt, and .srt formats.
- Compatible with Claude Code, Codex, and other terminal-based AI agents.
Output format
The output is a clean, standardized Markdown report featuring a "Decisions" list, a detailed "Action Items" table with assigned owners and dates, "Open Questions" for blockers, "Key Topics" for context, and "Next Meeting" logistics.
- Best with English transcripts
- Action items require clear "I will..." or "John will..." statements
- Does not record audio (transcript must be provided)
- Owner detection uses names; ambiguous if multiple people have same name
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Requires
Permissions
File Scopes
Meeting Summary reads pasted text directly in the conversation. File read access is optional โ if user provides a file path to a transcript, the skill will read it. File write access is optional โ user can ask to save the summary to a file. No terminal, network, or environment access required.