Neotoma
All skills

Tier 2: Extended

Remember Meetings

Ingest meeting transcripts from Zoom, Otter, Google Meet, or manual notes. Extracts decisions, action items, attendees, and commitments into structured entities with provenance tracing back to specific transcript passages.

Skill instructions

Extract decisions and action items from meeting transcripts Ingest meeting transcripts from Zoom, Otter, Google Meet, or manual notes. Extracts decisions, action items, attendees, and commitments into structured entities with provenance tracing back to specific transcript passages.

Loading preview from repository…

Install and runtime steps for Remember Meetings live in the file below. Agents should fetch the raw URL; humans can use GitHub browse. Follow prerequisites, MCP setup, and workflow there after neotoma setup when the skill is installed via the package.

Repository path
skills/remember-meetings/SKILL.md

Suggested prompt

Use skill prompt
Paste into your harness chat so the agent fetches the canonical markdown and follows it.
Use the Neotoma skill "Remember Meetings". Fetch and follow the instructions at:
https://raw.githubusercontent.com/markmhendrickson/neotoma/main/skills/remember-meetings/SKILL.md
Execute every prerequisite, MCP configuration step, and workflow phase described there for this environment.

Supported data sources

VTT filesSRT filesTXT transcriptsMarkdown notes

Entity types produced

eventdecisiontaskcontactnote

Workflow

  1. 0

    Verify Neotoma

    Confirm MCP connectivity

  2. 1

    Identify transcripts

    Locate and detect transcript format

  3. 2

    Parse and preview

    Show meeting date, participants, key topics

  4. 3

    Extract entities

    Pull decisions, tasks, attendees from content

  5. 4

    Store with provenance

    Preserve raw transcript as source

External tools

Related skills

Related use cases