skills.rest
Postergully
PostergullyCOMMUNITY
Explore all skills by this author →
GitHub

archive-crawler

Inventory allow-listed personal archives and surface high-value content for ingestion.

Updated May 4, 2026
Search Tags:#manifest#archive#personal-data#privacy-safety#brain-pages#gold-filter
One-click install
npx skills add https://github.com/Postergully/11mirror-plugin --skill archive-crawler-postergully
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: archive-crawler
Source: https://github.com/Postergully/11mirror-plugin/tree/main/skills/archive-crawler
Command: npx skills add https://github.com/Postergully/11mirror-plugin --skill archive-crawler-postergully

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

People accumulate large personal archives across local drives, cloud dumps, and email exports. They need a safe, governance-friendly way to surface high-signal content (writing, ideas, relationships) and organize it for ingestion into brain pages without leaking sensitive data or over-scanning.

Core Features & Use Cases

  • Safety gate requiring an explicit archive-crawler.scan_paths allow-list in gbrain.yml to run.
  • Schema-generic, manifest-driven ingestion that tracks inventory, triage, and back-links for future recall.
  • Flexible sources: local file trees, email dumps, cloud archives; surfaces gold content for brain-page creation.

Quick Start

Run the archive crawler against your allow-listed paths to generate the STATUS.md manifest and surface high-signal items for ingestion.

Frequently Asked Questions about archive-crawler

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

FAQPage Schema
How do I safely scan personal archives without exposing sensitive data?▼

You can scan email exports and cloud dumps by adding their paths to the archive-crawler.scan_paths allow-list in your gbrain.yml file. The crawler then inventories these sources and surfaces high-value content for brain-page ingestion.

How does manifest-driven archive ingestion work?▼

Manifest-driven ingestion inventories your archive items by generating a STATUS.md manifest during the scan. This manifest tracks classified content, triage status, and back-links to ensure robust tracking for future recall.

What is the best way to surface high-value content from local file trees?▼

To surface high-value content from local file trees, run the archive crawler against your explicitly allow-listed local paths. It applies schema-driven filing rules and a gold filter to classify items and surface high-signal writing and ideas.

Can I organize personal archives for brain pages without over-scanning?▼

You can organize archives for brain pages without over-scanning by enforcing an explicit scan_paths allow-list in gbrain.yml. This strict gate prevents the crawler from accessing unlisted directories, ensuring safe and targeted ingestion.

Do I need a gbrain.yml configuration to inventory personal archives?▼

Yes, you need a gbrain.yml configuration containing the archive-crawler.scan_paths allow-list to inventory personal archives. This strict gate ensures the crawler only processes explicitly authorized paths, maintaining safety and storage compliance.

Related Skills

Explore More Content & Communication Skills→
Morris-UTRUSTMorris-UTRUST

archive-crawler

Crawl configured archive sources to surface high-signal content for ingestion.

Community
Intermediate
SigmacodeatSigmacodeat

brain-taxonomist

Determine filing locations for new brain pages using an active taxonomy schema.

Community
Advanced
mkalhitti-cloudmkalhitti-cloud
2

pptx

Generate and update PPTX presentations from templates using Python-pptx and html2pptx workflows.

Community
Advanced
weipingweiping
1

archive-crawler

Crawl allow-listed personal archives and convert high-signal content into brain pages.

Community
Advanced