obsidian-file-intel

Extract content from mixed file formats and generate Obsidian-ready markdown summaries.

6|1|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/kouko/monkey-skills --skill obsidian-file-intel
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: obsidian-file-intel
Source: https://github.com/kouko/monkey-skills/tree/main/obsidian/skills/obsidian-file-intel
Command: npx skills add https://github.com/kouko/monkey-skills --skill obsidian-file-intel

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill automates extracting content and producing Obsidian-ready summaries from diverse file types so users do not have to manually read, summarize, and file large numbers of documents in a vault.

Core Features & Use Cases

  • Batch file processing: Run a local Python processor on a folder (inbox/ or custom) to convert many files into individual markdown summaries.
  • Multi-format support: Handles PDFs, PPTX, XLSX, DOCX, CSV, JSON and common text/code files and distinguishes deliverables from reference material.
  • Consolidated output: Produces per-file *_summary.md files and a MASTER_SUMMARY.md digest in outputs/file_summaries/YYYY-MM-DD/ for easy review and ingestion into Obsidian workflows.

Quick Start

Run the Python processor on the vault inbox/ or a specified folder to generate Obsidian-ready summaries and a master digest.

Frequently Asked Questions about obsidian-file-intel

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

FAQPage Schema
How do I generate Obsidian summaries from a folder of mixed file formats?

To generate Obsidian summaries, run the local Python processor on your target folder to batch convert PDFs, DOCX, XLSX, and code files into individual markdown summaries and a MASTER_SUMMARY.md digest.

Can I batch summarize PDFs and Office documents for my Obsidian vault?

Yes, you can batch summarize PDFs and Office documents by running the Python script on a vault folder, which extracts content and produces per-file markdown summaries ready for Obsidian ingestion.

What is the best way to audit content across a large Obsidian vault inbox?

The best way to audit vault inbox content is running this bulk document summarization processor, which distinguishes deliverables from reference material and outputs a consolidated MASTER_SUMMARY.md digest for folder-level review.

Does the file summarization script require any external dependencies to process spreadsheets and code files?

No external dependencies are required to process spreadsheets and code files, as the Skill runs a standalone local Python script that handles CSV, JSON, XLSX, and common text formats without additional package installations.

Where are the generated markdown summaries stored after processing vault files?

Generated markdown summaries are stored in the outputs/file_summaries/YYYY-MM-DD/ directory, containing individual per-file summary files and a MASTER_SUMMARY.md digest while streaming processing output to the terminal.

Why should I use automated file summarization instead of manually reading documents for my vault?

Automated file summarization eliminates manually reading and summarizing large numbers of diverse documents, handling mixed file formats in bulk to produce Obsidian-ready markdown summaries for efficient inbox processing and content auditing.