archive-crawler

Organize and extract high-value content from personal archives.

2|1|Updated Jun 16, 2026
One-click install
npx skills add https://github.com/bish-x/bx-gbrain --skill archive-crawler-bish-x
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: archive-crawler
Source: https://github.com/bish-x/bx-gbrain/tree/main/skills/archive-crawler
Command: npx skills add https://github.com/bish-x/bx-gbrain --skill archive-crawler-bish-x

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps users organize and extract valuable content from personal archives, making it easier to review and reference important documents.

Core Features & Use Cases

  • Universal Archive Support: Works with local, Dropbox, B2, Gmail, and other archives.
  • High-Value Content Extraction: Filters and extracts personal writing, conversations, ideas, and relationships.
  • Interactive Review: Allows users to interactively review and categorize content.
  • Ingestion and Filing: Automatically ingests and files content based on the user's filing rules.

Quick Start

To start, use the 'archive-crawler scan my archive' command and define the paths you want to scan in your gbrain.yml file.

Frequently Asked Questions about archive-crawler

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

FAQPage Schema
How do I extract high-value content from personal archives across multiple platforms?

To extract high-value content from personal archives, you filter and organize documents using interactive review capabilities and custom filing rules. This process surfaces valuable writings, ideas, and relationships scattered across various storage platforms for easier reference.

Can I scan and organize file archives stored in Dropbox and Gmail?

Yes, you can scan and organize file archives stored in Dropbox, Gmail, local drives, and B2. The system ingests and files content automatically based on your explicitly defined rules, reviewing and categorizing content across these supported platforms.

What is the best way to review and categorize extracted personal writing and conversations?

The best way to review and categorize extracted personal writing and conversations is through an interactive review process. This allows you to evaluate high-value content before automatically filing it according to your specific organizational rules.

How do I configure scan paths to start ingesting my personal file archives?

To configure scan paths for ingesting personal file archives, you must explicitly allow-list the target directories in your gbrain.yml file. Once configured, initiate the scan to begin extracting and filing content based on your rules.

Do I need to define filing rules before scanning my personal archives?

Yes, you need to define filing rules before scanning your personal archives. The system requires explicit adherence to these rules to automatically ingest, filter, and categorize your extracted content correctly during the scan.