archive-crawler

Name: archive-crawler
Availability: InStock
Author: Inbrain

Crawl approved archive paths and generate structured manifests for content ingestion.

174|144|Updated Jun 10, 2026

Search Tags:#archive #data-governance #data-ingestion #privacy-safety #brain-pages #personal-archives #filing-rules

Ready to run

npx skills add https://github.com/inbrainfun/inbrain --skill archive-crawler-inbrainfun

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: archive-crawler
Source: https://github.com/inbrainfun/inbrain/tree/main/skills/archive-crawler
Command: npx skills add https://github.com/inbrainfun/inbrain --skill archive-crawler-inbrainfun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill acts as a safe, schema-driven archive crawler that scans user-specified file trees to surface high-signal personal content (writing, ideas, relationships) while preventing overreach by requiring an explicit allow-list in inbrain.yml.

Core Features & Use Cases

Enforces a strict safety gate: archive-crawler refuses to run unless archive-crawler.scan_paths is set, preventing accidental ingestion of sensitive data.
Catalogs and surfaces high-signal content from local and cloud archives (Dropbox, Gmail takeout, hard drives) for user review, triage, and ingestion into brain pages.
Bridges the inventory-to-ingest workflow by generating manifests and schedules, with deterministic, auditable pipelines.

Quick Start

To start crawling, provide an explicit allow-list path in your inbrain.yml and run the agent to scan your approved archives.

Frequently Asked Questions about archive-crawler

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

FAQPage Schema

How do I safely crawl personal archives to surface high-value content for ingestion?▼

To safely crawl personal archives, you must define an explicit allow-list of scan paths in your configuration file. This safety gate prevents accidental ingestion of sensitive data by strictly limiting the crawl to approved directories.

What is the best way to extract writing and ideas from Gmail takeout or local drives?▼

Extracting writing and ideas from takeout or local drives requires a schema-driven crawler that catalogs files and generates a structured manifest. This manifest surfaces high-signal content for your review and triage before ingestion.

How do I route discovered archive content into originals, personal, or ideas folders?▼

To route discovered content into originals, personal, or ideas folders, apply explicit filing rules during the crawl. The pipeline validates content and routes it accordingly, producing a deterministic audit trail for each file.

Does the archive crawler work with cloud backups and local hard drives without scanning everything?▼

The crawler works with cloud backups and local hard drives but refuses to run unless an explicit allow-list is configured. This ensures only approved file trees are scanned, preventing overreach into unapproved directories.

Why does my archive crawl refuse to start or scan my local drives?▼

Your archive crawl refuses to start because a strict safety gate requires an explicit scan paths allow-list in your configuration. Without this setting, the crawler prevents execution to avoid accidental ingestion of sensitive data.

What do I need to set up before scanning my Dropbox archives for personal content?▼

Before scanning Dropbox archives, you need to configure an explicit allow-list of scan paths in your configuration file. This prerequisite establishes a safe boundary for the crawler to discover writing, ideas, and relationships.