skills.rest
drewid74
drewid74COMMUNITY
Explore all skills by this author →
GitHub

archivebox-knowledge

Archive websites into a searchable personal knowledge base with full-text search.

8|1|Updated Mar 30, 2026
Search Tags:#ocr#full-text search#deduplication#web archiving#archivebox#bookmark import#rss ingestion
One-click install
npx skills add https://github.com/drewid74/ai_skills --skill archivebox-knowledge
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: archivebox-knowledge
Source: https://github.com/drewid74/ai_skills/tree/main/archivebox-knowledge
Command: npx skills add https://github.com/drewid74/ai_skills --skill archivebox-knowledge

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web pages disappear, bookmarks get messy, and reading lists become unsearchable, so you lose knowledge that you meant to keep. This Skill helps you archive websites reliably and turn saved pages into a searchable personal knowledge base.

Core Features & Use Cases

  • ArchiveBox-based capture: preserves pages as HTML/PDF/WARC and supports CLI/API ingest for individual URLs and bulk imports.
  • Import and dedup pipeline: ingests bookmarks and RSS feeds while deduplicating by URL (e.g., stripping tracking params and hashing) to prevent repeated archives.
  • Search-ready knowledge retrieval: routes extracted content into full-text search using Sonic or PostgreSQL FTS, with OCR via Paperless-NGX for scanned materials.
  • JS-rendered site handling: captures JavaScript-heavy pages using a Playwright backend (or SingleFile as a lightweight option).

Quick Start

Use the Skill to set up ArchiveBox, then bulk import your bookmarks from a Netscape HTML export into your archive in one go.

Frequently Asked Questions about archivebox-knowledge

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

FAQPage Schema
How do I archive web pages and build a searchable knowledge base to prevent link rot?▼

You can archive web pages into a durable, searchable knowledge base using ArchiveBox ingestion, which preserves sites as HTML, PDF, and WARC files while routing extracted text into a full-text search backend.

How do I bulk import bookmarks and deduplicate archived web pages?▼

You can bulk import bookmarks from a Netscape HTML export and ingest RSS feeds while deduplicating archived web pages by stripping tracking parameters and hashing URLs to prevent repeated captures.

Can I capture JavaScript-heavy pages for offline retention?▼

Yes, you can capture JavaScript-heavy pages for offline retention using a Playwright backend or SingleFile as a lightweight option to ensure dynamic content renders correctly before saving.

How does full-text search and OCR work for scanned materials in a web archive?▼

Full-text search and OCR for scanned materials work by routing extracted content into Sonic or PostgreSQL FTS, while Paperless-NGX handles OCR to make images and scanned documents searchable.

What is the best way to save individual web pages before they vanish?▼

The best way to save individual web pages before they vanish is using ArchiveBox CLI or API ingestion, which captures the page in multiple durable formats and integrates it into your deduplicated archive.

Does web archiving work with RSS feeds for automated capture?▼

Yes, web archiving supports RSS ingestion for automated capture, allowing you to continuously ingest feed updates into your searchable knowledge base while applying URL deduplication strategies.

Related Skills

Explore More Personal & Entrepreneur Skills→
spamschspamsch
29

paperless_assistant

Manage document search, upload, and metadata in Paperless-ngx.

Community
Basic
hairihouhairihou

extract-pdf-text

Extract text from PDF files via pdfplumber with optional page selection.

Community
Intermediate
dapperdiversdapperdivers
1

paperless-ops

Search, update, and categorize documents in Paperless-ngx via REST API.

Community
Intermediate
erfanzarerfanzar
27

ocr-and-documents

Extract text from PDFs and scanned documents via OCR or direct parsing into Markdown/structured data.

Community
Advanced