skills.rest
NukaSoft
NukaSoftOFFICIAL
Explore all skills by this author →
WebsiteGitHub

cassian

Harvests web sources into a centralized Markdown knowledge base with SQLite manifest.

2|Updated Mar 23, 2026
Search Tags:#markdown#manifest#briefings#web-scraping#knowledge-base#knowledge-harvesting#nas-storage
One-click install
npx skills add https://github.com/NukaSoft/nukasoft.ai --skill cassian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cassian
Source: https://github.com/NukaSoft/nukasoft.ai/tree/main/_skills/cassian
Command: npx skills add https://github.com/NukaSoft/nukasoft.ai --skill cassian

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cassian turns scattered content sources into a centralized, searchable knowledge base by automating web scraping, content harvesting, and continuous updates.

Core Features & Use Cases

  • Multi-source scraping and aggregation across TSIA, MVP blogs, LinkedIn, Microsoft Learn, and ad-hoc URLs
  • Structured storage of harvested content as Markdown with YAML frontmatter on NAS
  • SQLite manifest for metadata like title, author, source, tags, and word count
  • Weekly briefings and trend analysis to surface actionable insights
  • Queue management and deployment workflow to NAS

Quick Start

To begin harvesting and updating your knowledge base, say run Cassian to scrape sources, queue URLs, generate a briefing, and refresh the manifest.

Frequently Asked Questions about cassian

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

FAQPage Schema
How do I automate web scraping to build a centralized knowledge base?▼

Automated web scraping for a knowledge base works by harvesting content from multiple sources like blogs, Microsoft Learn, and ad-hoc URLs, then storing it as structured Markdown on NAS. This keeps scattered information centralized and searchable.

What is knowledge harvesting and how does it keep my KB fresh?▼

Knowledge harvesting is the automated extraction of content from web sources into a searchable repository. It keeps your KB fresh by maintaining a SQLite manifest of metadata and scheduling weekly briefings to surface trend analysis and actionable insights.

How do I store scraped web content as Markdown with YAML frontmatter?▼

Store scraped web content as Markdown with YAML frontmatter by deploying harvested files to NAS storage. A SQLite manifest tracks metadata like title, author, source, tags, and word count to maintain searchable structured records.

Can I queue URLs and manage deployment to NAS storage for harvested content?▼

Yes, you can queue URLs and manage deployment to NAS storage for harvested content. The workflow supports queueing ad-hoc URLs, scraping sources, and deploying structured Markdown files directly to network attached storage.

Does web scraping for trend analysis support Microsoft Learn and LinkedIn posts?▼

Web scraping for trend analysis supports Microsoft Learn and LinkedIn posts. It aggregates content from these sources alongside TSIA research and MVP blogs to generate weekly briefings that surface actionable insights.

Related Skills

Explore More Data & Analytics Skills→
rennerenne

nas-and-storage

Configure FRITZ!Box 7690 USB storage for SMB/CIFS, FTP, DLNA, and MyFRITZ! access.

Community
Intermediate
daaaindaaain
1.2k

tool-renderer

Render Claude Code tool interactions as HTML and Markdown.

Community
Intermediate
pluginagentmarketplacepluginagentmarketplace
3

stacks-queues

Implement stacks and queues to manage data flow in algorithms.

Community
Advanced
joyce820309joyce820309

scrape

Automate HTML data extraction using BeautifulSoup and requests.

Community
Intermediate