data-ingest

Name: data-ingest
Availability: InStock
Author: Niraj

Ingest arbitrary text data into structured Obsidian wiki pages.

Updated Apr 27, 2014

Search Tags:#data #obsidian #vault #text #knowledge-management #ingest

Ready to run

npx skills add https://github.com/Nirajkashyap/nirajkashyap.github.io --skill data-ingest-nirajkashyap

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-ingest
Source: https://github.com/Nirajkashyap/nirajkashyap.github.io/tree/main/.agents/skills/data-ingest
Command: npx skills add https://github.com/Nirajkashyap/nirajkashyap.github.io --skill data-ingest-nirajkashyap

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingest raw text data into an Obsidian wiki, turning disparate exports, transcripts, logs, and other unstructured text into searchable, knowledge-rich pages.

Core Features & Use Cases

Universal text source handler: detects and processes a variety of text formats (plain text, CSV, JSON-like exports) and distills them into wiki pages.
Safe, bounded ingestion: validates sources, checks the vault manifest to avoid re-ingestion, and uses the configured Obsidian link format for internal links.
Real-world use cases include importing Slack/Discord transcripts, meeting notes, chat histories, journal dumps, or CSV data into structured pages for later reference.

Quick Start

Ingest a data source by running the ingestion workflow to generate 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 ingest text into an Obsidian vault?▼

To ingest text into an Obsidian vault, this Skill processes arbitrary text data like chat exports and logs, distilling them into structured knowledge pages using a configured vault path and link format.

What is the best way to import Slack transcripts and meeting notes into a wiki?▼

Importing Slack transcripts and meeting notes into a wiki is handled by a universal text source handler that automatically detects unstructured or semi-structured formats and distills them into searchable pages.

Can I ingest CSV dumps and JSON-like exports into Obsidian?▼

Yes, you can ingest CSV dumps and JSON-like exports into Obsidian. The ingestion workflow supports both unstructured and semi-structured data across diverse text formats to generate wiki pages.

Do I need to configure an OBSIDIAN_VAULT_PATH before importing chat histories?▼

Yes, you need to resolve an OBSIDIAN_VAULT_PATH and OBSIDIAN_LINK_FORMAT via a config protocol before importing chat histories to ensure safe processing and correct internal linking.

How does the ingestion process avoid duplicating data in the vault manifest?▼

To avoid duplicating data, the ingestion process checks a vault manifest and reads index files before processing raw text sources, ensuring safe and bounded ingestion without re-ingestion.