skills.rest
GYF0311
GYF0311COMMUNITY
Explore all skills by this author →
GitHub

archive-crawler

Mine personal file archives for high-value writing and ideas.

5|1|Updated Apr 15, 2026
Search Tags:#data safety#personal knowledge base#wiki ingestion#manifest tracking#email takeout#content triage#archive scanning
One-click install
npx skills add https://github.com/GYF0311/lorekit --skill archive-crawler-gyf0311
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: archive-crawler
Source: https://github.com/GYF0311/lorekit/tree/main/brain/skills/archive-crawler
Command: npx skills add https://github.com/GYF0311/lorekit --skill archive-crawler-gyf0311

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

archive-crawler helps you explore large personal file archives and surface the high-value writing, ideas, and relationship material worth ingesting into your wiki—without accidentally scanning or ingesting sensitive data.

Core Features & Use Cases

  • Safety-gated archive scanning: Refuses to run unless gbrain.yml explicitly allow-lists archive-crawler.scan_paths for the permitted scan roots.
  • Interactive triage with a persistent manifest: Builds an inventory and a priority queue, then records per-item review status and the user’s exact reactions in projects/<archive-slug>/STATUS.md.
  • Gold-filtered ingestion into brain pages: Reads candidate files, applies a “gold” relevance filter, and when you approve, files content into the appropriate brain directories based on your filing rules.
  • Multi-source archive support: Works across local mounts and multiple archive formats/targets (e.g., Dropbox/B2/Gmail takeouts/mbox/pst), while skipping noise like configs, system files, and binary junk.

Quick Start

Add an explicit allow-list under archive-crawler.scan_paths in your gbrain.yml, then tell the agent: "crawl my archive and surface the writing worth keeping".

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 file archives for high-value content without exposing sensitive data?▼

Safely scanning personal file archives requires an allow-list safety gate via gbrain.yml to explicitly permit scan roots, ensuring sensitive data is skipped while surfacing high-value writing and ideas for wiki ingestion.

Can I ingest Gmail takeout mbox files into my personal wiki?▼

Yes, you can ingest Gmail takeouts by adding the archive path to your allow-list, running the gold relevance filter, and approving prioritized items for schema-generic filing into your wiki directories.

What is the best way to triage large Dropbox archives for my personal knowledge base?▼

Triage large Dropbox archives by building an interactive priority queue that records per-item review status and user reactions in a persistent manifest, allowing guided review before wiki ingestion.

Does archive-crawler work with local directories and B2 cloud storage mounts?▼

Yes, archive-crawler works across local mounts and multiple archive formats including B2 cloud storage, applying a gold relevance filter to skip system files and binary junk during the scanning process.

How do I track the ingestion status of reviewed files from my personal archives?▼

Track ingestion status by maintaining a persistent manifest in projects/<archive-slug>/STATUS.md, which records per-item review status and your exact reactions during the interactive triage process.

Why does the archive scanning process refuse to run without configuration?▼

Archive scanning refuses to run without configuration to enforce data safety, requiring explicit allow-listing of scan_paths in gbrain.yml to prevent accidental scanning or ingestion of sensitive personal files.

Related Skills

Explore More Personal & Entrepreneur Skills→
NinatuziNinatuzi

archive-crawler

Automate discovery and ingestion of personal content from file archives.

Community
Advanced
sheawinklersheawinkler
78

llm-wiki

Build and maintain an interlinked Markdown knowledge base with YAML frontmatter and SCHEMA compliance.

Community
Advanced
RDCrystalLabRDCrystalLab

obsidian-para-wiki

Organize fragmented research sources into a structured Obsidian PARA wiki.

Official
Advanced
weipingweiping
1

archive-crawler

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

Community
Advanced