skills.rest
Ar9av
Ar9avCOMMUNITY
Explore all skills by this author →
Website𝕏@_ar9avGitHub

data-ingest

Ingest unstructured text data into an Obsidian wiki as structured pages.

3.2k|320|Updated Apr 6, 2026
Search Tags:#data#obsidian#distill#wiki#text#ingest
One-click install
npx skills add https://github.com/Ar9av/obsidian-wiki --skill data-ingest-ar9av
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-ingest
Source: https://github.com/Ar9av/obsidian-wiki/tree/main/.skills/data-ingest
Command: npx skills add https://github.com/Ar9av/obsidian-wiki --skill data-ingest-ar9av

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingest arbitrary text data (exports, logs, transcripts, data dumps) into the Obsidian wiki, distilling it into structured pages for easy search and reuse.

Core Features & Use Cases

  • Ingests chat exports, logs, CSV data, emails, bookmarks, and other unstructured text into the wiki.
  • Distills source content into summarized, linkable pages with provenance.
  • Supports incremental ingestion by inspecting vault state to avoid re-ingesting unchanged data.

Quick Start

Ingest raw text data into the Obsidian wiki.

Frequently Asked Questions about data-ingest

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

FAQPage Schema
How do I ingest unstructured text data like chat exports and logs into Obsidian?▼

To ingest unstructured text data into Obsidian, use this Skill to distill chat exports, logs, CSV data, emails, and bookmarks into structured, linkable wiki pages with provenance. It reads source text and automatically generates summarized pages for easy search and reuse.

Can I incrementally ingest text into the Obsidian wiki without duplicating older data?▼

Yes, incremental text ingestion into the Obsidian wiki is supported by inspecting vault state via index.md and checking a .manifest.json file for prior ingestions. This mechanism identifies and skips unchanged data, preventing duplicate wiki pages.

What do I need to configure before importing CSV data and emails into my Obsidian wiki?▼

Before importing CSV data and emails, you need to configure your environment by setting the OBSIDIAN_VAULT_PATH variable in a .env file. This path tells the ingestion process where to create and store the distilled wiki pages.

What is the best way to distill raw transcripts into searchable wiki pages?▼

The best way to distill raw transcripts into searchable wiki pages is using an ingestion tool that parses unstructured text and generates summarized, linkable Obsidian pages. This process preserves provenance while making the content easily discoverable.

Does this text ingestion method work with arbitrary unstructured text sources?▼

Yes, this text ingestion method works with arbitrary unstructured text sources including chat exports, logs, transcripts, CSV data, emails, and bookmarks. It processes the raw content and structures it into the Obsidian wiki format.

Related Skills

Explore More Data & Analytics Skills→
jykimjykim
31

obsidian-links

Format, validate and fix Obsidian wiki links to conform with vault conventions.

Community
Basic
Nero-kkNero-kk

data-ingest

Convert unstructured text sources into distilled Obsidian wiki pages.

Community
Advanced
WesleyMFrederickWesleyMFrederick

writing-requirements-documents

Generate Obsidian requirements documents with block anchors and validated wiki links.

Community
Advanced
pax-kpax-k
6

data-ingest

Ingests unstructured text files into Obsidian wiki pages with provenance and deduplication.

Community
Intermediate