data-ingest

Ingest unstructured text sources into an Obsidian vault as structured notes.

Updated Aug 23, 2026

Search Tags:#obsidian #ingest #data-wrangling #text-processing #unstructured-data #log-ingestion

Ready to run

npx skills add https://github.com/samuelcastro/noter --skill data-ingest-samuelcastro

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingest unstructured text data into an Obsidian wiki, turning scattered sources like chat exports, meeting transcripts, logs, CSV dumps, and bookmarks into searchable, structured notes.

Core Features & Use Cases

Unified ingestion of diverse text sources into an Obsidian vault.
Policy-bound processing that preserves source data and avoids executing commands or exfiltrating information.
Guidance and boundary checks using .env, .manifest.json, and index.md to prevent re-ingestion of unchanged content.

Quick Start

Run the ingestion workflow by pointing to your source data and your Obsidian vault.

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 data like chat exports and transcripts into Obsidian?▼

You can ingest unstructured data into Obsidian by pointing the workflow to raw text sources like chat exports, transcripts, and CSV dumps, which then converts them into searchable, structured notes.

What types of unstructured text data can I import into an Obsidian wiki?▼

Supported unstructured text data includes chat exports, meeting transcripts, logs, CSV dumps, and bookmarks, all of which are transformed into structured notes within your Obsidian vault.

How does the ingestion process prevent duplicate notes from unchanged sources?▼

The ingestion process prevents duplicates by reading a .manifest.json file to determine prior ingestions and consulting index.md at the vault root to guide existing content and avoid re-ingesting unchanged data.

Do I need to set environment variables to import raw text files into Obsidian?▼

Yes, you need to set the OBSIDIAN_VAULT_PATH variable in a .env file, which the workflow reads to locate your target Obsidian vault before processing raw text files into notes.

Are there security limitations when processing log files and CSV dumps into Obsidian?▼

Yes, the processing strictly follows policy-bound boundaries that preserve source data integrity, ensuring it never executes commands or exfiltrates information while handling log files and CSV dumps.