archive-crawler

Scan allow-listed paths in gbrain.yml to surface personal writing and ideas.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/mscully4/franklin --skill archive-crawler-mscully4
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: archive-crawler
Source: https://github.com/mscully4/franklin/tree/main/.claude/skills/archive-crawler
Command: npx skills add https://github.com/mscully4/franklin --skill archive-crawler-mscully4

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you organize and uncover valuable content from your personal archives, making it easy to find and review important information.

Core Features & Use Cases

  • Universal Archive Support: Works with Dropbox, B2, Gmail-takeout, local mounts, and more.
  • Gold Filter: Focuses on personal writing, ideas, relationships, and creative work.
  • Interactive Review: Allows you to interactively review and tag content.
  • Use Case: If you have a large collection of personal documents and want to find all your journal entries, letters, or important ideas, this Skill can help you surface them quickly.

Quick Start

Use the archive-crawler skill to scan your Dropbox for personal writing and ideas.

Frequently Asked Questions about archive-crawler

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

FAQPage Schema
How do I find personal writing and ideas in my archives?

To find personal writing and ideas in your archives, you can use a crawler to scan your personal archives and filter for high-value content like journal entries, letters, and creative work. It surfaces this content quickly for interactive review and tagging.

Can I scan my Dropbox and Gmail takeout for personal content?

Yes, you can scan Dropbox and Gmail takeout for personal content. The archive crawler supports universal archive sources including Dropbox, B2, Gmail-takeout, and local mounts to surface high-value personal writing and relationships.

How do I safely configure archive scanning for specific file systems?

To safely configure archive scanning for specific file systems, you must explicitly allow-list scan paths in the gbrain.yml configuration file. This explicit allow-listing requirement ensures the crawler only accesses authorized directories for safety.

What is the best way to organize and retrieve data from personal archives?

The best way to organize and retrieve data from personal archives is using a gold filter that focuses specifically on personal writing, ideas, and relationships. This approach filters out noise and surfaces only high-value content for interactive review.

Does the archive crawler automatically search all my local mounts?

No, the archive crawler does not automatically search all local mounts. For safety, it requires explicit allow-listing of scan paths in the gbrain.yml file before it can scan any local mounts or other connected file systems.