Neotoma
All skills

Tier 1: Core

Remember Conversations

Import conversation history from ChatGPT JSON exports, Claude history files, Slack archives, or shared conversation URLs. Reconstructs a timeline of decisions, commitments, and context with full provenance.

Skill instructions

Import chat history into persistent memory Import conversation history from ChatGPT JSON exports, Claude history files, Slack archives, or shared conversation URLs. Reconstructs a timeline of decisions, commitments, and context with full provenance.

Loading preview from repository…

Install and runtime steps for Remember Conversations 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-conversations/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 Conversations". Fetch and follow the instructions at:
https://raw.githubusercontent.com/markmhendrickson/neotoma/main/skills/remember-conversations/SKILL.md
Execute every prerequisite, MCP configuration step, and workflow phase described there for this environment.

Supported data sources

ChatGPT JSON exportClaude historySlack archiveShared URLs

Entity types produced

conversationconversation_messagedecisiontaskcontact

Workflow

  1. 0

    Verify Neotoma

    Confirm MCP connectivity

  2. 1

    Identify source

    Detect file format (ChatGPT JSON, Slack export, etc.)

  3. 2

    Parse and preview

    List conversations with dates and message counts

  4. 3

    Extract entities

    Pull out decisions, tasks, contacts, events

  5. 4

    Reconstruct timeline

    Build a provenance-traced timeline of key events

External tools

Related skills

Related use cases