Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Meeting Action Extractor Free

    2

    Turn messy meeting transcripts into clean, structured action-item tables with clear owners and deadlines.

    Free

    6 usesSecurity scanned
    meeting-action-extractor-free

    meeting-action-extractor-free

    Example session with this skill installed

    Extract the action items from this transcript. Sarah said she'll finish the API docs by Friday, and someone needs to check the server logs, but we didn't say when.

    • Read your context and instructions
    • Compiled the meeting-action-extractor-free

    Action Items

    OwnerActionDeadlineOutcome
    SarahFinish API documentationFridayCompleted docs ready for review
    [needs clarification]Investigate server logs[needs clarification]Root-cause analysis

    Note: Please confirm the owner and deadline for the log investigation.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Automated Meeting Action-Item Extraction

    Drowning in meeting transcripts but struggling to find the actual "to-dos"? This skill solves the problem of manual note-taking by scanning transcripts—from Otter, Fathom, Zoom, Teams, or rough notes—to produce a single, high-fidelity action items table.

    What it does

    The skill first cleans your transcript, stripping out timecodes and conversational filler (ums, uhs, false starts) while preserving speaker attribution. It then identifies every commitment made during the discussion and maps them into a structured format: Owner, Action, Deadline, and Outcome.

    Why use this skill

    • Zero Invention: Unlike general LLMs that might hallucinate owners or dates, this skill strictly flags missing information as "[needs clarification]" if it wasn't explicitly stated.
    • Outcome-Oriented: It doesn't just list tasks; it captures what "done" looks like for every item.
    • Developer-Friendly: Get a clean, Markdown-formatted table that you can paste directly into Jira, GitHub Issues, or Notion.
    • Clean Data: It uses specific rubric-based extraction to ensure every action starts with a strong verb and maps to a specific deliverable.

    Supported Inputs

    Works with text exports from all major meeting platforms including Zoom, Google Meet, Microsoft Teams, Otter.ai, and Fathom, as well as unformatted manual notes.

    • Limited to action item extraction only.
    • Does not generate follow-up emails or role-specific summaries.
    • Requires high-quality text transcripts for best results.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    6 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 4 months ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed4 months ago

    What's inside

    Frequently Asked Questions

    This skill identifies every commitment made in a transcript and organizes them into a structured table with four columns: Owner, Action, Deadline, and Outcome. It ensures accountability by using a rubric that requires a strong verb for every task.

    The skill is designed to work with text exports from any major platform, including Zoom, Microsoft Teams, Otter.ai, and Fathom. It also processes unformatted manual notes, provided the text includes speaker names or clear conversational context.

    Unlike general AI tools that might guess a date or owner, this skill is programmed for "Zero Invention." If a deadline or owner isn't explicitly mentioned in the transcript, the skill will flag it as "[needs clarification]" rather than hallucinating details.

    The output is delivered as a clean, Markdown-formatted table. This allows you to copy and paste the results directly into project management tools like Notion, Jira, GitHub Issues, or Slack without losing the formatting.

    Yes, the skill includes a "pre-cleaning" phase that automatically strips out conversational filler like "ums" and "uhs," as well as messy timecodes, ensuring the resulting action items are based on clear, professional context.