knowledge-skill

Capture, organize, and retrieve knowledge from web pages, Bilibili videos, and WeChat articles.

4|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/hwj123hwj/custom-skills --skill knowledge-skill-hwj123hwj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: knowledge-skill
Source: https://github.com/hwj123hwj/custom-skills/tree/main/skills/knowledge-skill
Command: npx skills add https://github.com/hwj123hwj/custom-skills --skill knowledge-skill-hwj123hwj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires psycopg2-binary, requests, python-dotenv, python-dotenv, psycopg2-binary, requests, python-dotenv, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the process of capturing, organizing, and accessing knowledge from diverse sources like web pages, Bilibili videos, and WeChat articles, transforming raw information into a structured and retrievable knowledge base.

Core Features & Use Cases

  • Content Ingestion: Capture and structure content from a variety of sources, including Bilibili videos, WeChat articles, and Markdown documents.
  • Search & Retrieval: Efficiently search and retrieve information using both keyword and semantic search methods.
  • Knowledge Organization: Organize knowledge into structured cards, with options for adding context tags and metadata.
  • Markdown & Wiki Compilation: Compile structured knowledge into Markdown or LLM-friendly Wiki formats for easy access by agents and humans.
  • Feishu Knowledge Library Integration: Publish knowledge directly to the Feishu knowledge library for collaboration and long-term storage.
  • Memory Management: Manage knowledge layers (work memory, domain knowledge, and archive) with features like compression, downgrading, and retrieval prioritization.
  • Self-Improvement: Implement a self-evolving mechanism to optimize the knowledge base over time based on usage metrics and feedback.
  • Use Case: Imagine you need to quickly find a piece of information about a specific AI technology. Use this Skill to search the knowledge base and retrieve the relevant information in seconds.

Quick Start

To start, install the knowledge-skill using the command: npx custom-skills install knowledge-skill. Once installed, you can use the following command to search for information: npx custom-skills search "AI technology".

Frequently Asked Questions about knowledge-skill

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

FAQPage Schema
How do I capture and organize web pages and Bilibili videos into a searchable knowledge base?

To build a searchable knowledge base, ingest web pages, Bilibili videos, and WeChat articles into structured cards. This requires PostgreSQL for storage and SiliconFlow API for embedding generation to enable semantic search retrieval.

What is the difference between keyword and semantic search when retrieving information from a knowledge base?

Keyword search matches exact terms, while semantic search uses SiliconFlow API embeddings to match conceptual meaning. This dual approach ensures precise and contextually relevant information retrieval from your structured Markdown wiki.

Does knowledge base content ingestion work with WeChat articles and Markdown documents?

Yes, content ingestion supports WeChat articles, Bilibili videos, and Markdown documents. It structures raw information into retrievable knowledge cards with context tags and metadata for compilation into LLM-friendly Wiki formats.

How do I publish structured Markdown knowledge to a Feishu knowledge library for collaboration?

Compile structured knowledge cards into Markdown or wiki formats and publish directly to the Feishu knowledge library. This integration enables collaborative access and long-term storage of your organized knowledge base.

Do I need PostgreSQL and SiliconFlow API to manage work memory and domain knowledge layers?

Yes, managing work memory, domain knowledge, and archive layers with compression and retrieval prioritization requires PostgreSQL for database management and SiliconFlow API for processing embeddings and ASR.

Can I use LongCat API to generate AI summaries for ingested content?

Yes, the LongCat API generates AI summaries for ingested content from Bilibili videos and web pages. This automates knowledge capture and structures raw information into concise, retrievable knowledge cards.