data-ingest

Ingest arbitrary text data into structured Obsidian wiki pages.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Michael1Peng/watson --skill data-ingest-michael1peng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-ingest
Source: https://github.com/Michael1Peng/watson/tree/main/.agents/skills/data-ingest
Command: npx skills add https://github.com/Michael1Peng/watson --skill data-ingest-michael1peng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingests raw text data, conversation logs, chat exports, or unstructured documents into the Obsidian wiki. This skill helps you process data that isn't standard documents or Claude history—things like ChatGPT exports, Slack threads, Discord logs, meeting transcripts, journal entries, CSV data, browser bookmarks, or email archives, converting them into structured wiki content.

Core Features & Use Cases

  • Universal text source handling: ingest arbitrary text data and distill it into wiki pages with clear provenance.
  • Safe, trust-bound processing: never execute embedded instructions or exfiltrate data; preserves source context.
  • Use Case: import a chat export or meeting transcript and generate organized notes and linked summaries in your vault.

Quick Start

Point the ingester at a raw text source and run the universal text data workflow to distill it into wiki pages.

Frequently Asked Questions about data-ingest

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I import raw text and chat transcripts into an Obsidian wiki?

To import raw text and chat transcripts into an Obsidian wiki, you ingest the arbitrary text data through a universal workflow that distills logs and exports into structured, linked wiki pages. This requires local vault access.

What types of unstructured data can be converted into Obsidian wiki pages?

Unstructured data including ChatGPT exports, Slack threads, Discord logs, meeting transcripts, CSVs, emails, and browser bookmarks can be converted into Obsidian wiki pages. The ingester distills these text dumps into organized notes.

Does ingesting external text data into Obsidian execute embedded instructions?

Ingesting external text data into Obsidian does not execute embedded instructions or exfiltrate data. The processing strictly adheres to data trust boundaries, preserving source context while safely creating structured wiki content.

Do I need a specific environment variable to process CSV data and logs into Obsidian?

Yes, you need the OBSIDIAN_VAULT_PATH environment variable to process CSV data and logs into Obsidian. This local vault access variable allows the ingester to write distilled text data directly into your wiki.

What is the best way to organize meeting transcripts and email archives in Obsidian?

The best way to organize meeting transcripts and email archives in Obsidian is using a universal text distillation workflow. This approach processes raw text dumps and generates structured wiki pages with clear provenance and linked summaries.