Knowledge

Manage a persistent Knowledge Archive with typed cross-linked notes.

1|Updated Apr 16, 2026
One-click install
npx skills add https://github.com/davdunc/pai-framework --skill knowledge-davdunc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Knowledge
Source: https://github.com/davdunc/pai-framework/tree/main/skills/Knowledge
Command: npx skills add https://github.com/davdunc/pai-framework --skill knowledge-davdunc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates the friction of keeping a growing knowledge base consistent, searchable, and connected through typed relationships.

Core Features & Use Cases

  • Archive search with relevance: Runs lexical search, frontmatter/tag search, and wikilink search to quickly find the right notes.
  • Structured knowledge ingestion: Ingests a URL or file into the Knowledge Archive while performing a ripple pass that updates related notes.
  • Contradiction detection and knowledge graph navigation: Surfaces conflicting claims and provides graph stats or traversal for better insight discovery.
  • Seedling development and harvesting: Harvests from PAI sources and helps enrich “seedling” notes until they’re ready for promotion.

Quick Start

Run: /knowledge ingest https://example.com/an-article to create a new knowledge note and ripple updates into related entries.

Frequently Asked Questions about Knowledge

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

FAQPage Schema
How do I build a typed knowledge graph from my research notes?

Maintain consistency in your knowledge graph by running contradiction detection to surface conflicting claims. The archive uses lexical BM25 retrieval and typed cross-links to find and flag conflicting information across related notes.

How do I ingest a URL into my knowledge base and update related notes?

Search your knowledge archive using lexical BM25 retrieval, frontmatter, tag, and wikilink search. This multi-method approach finds relevant notes quickly across People, Companies, Ideas, and Research categories.

What is the best way to detect contradictions in a knowledge archive?

Develop seedling notes by running the develop subcommand to enrich partial entries until ready for promotion. Harvesting pulls from PAI sources to provide context and grow unstructured notes into fully structured archive entries.

Do I need YAML frontmatter to add notes to the knowledge archive?

Yes, mandatory YAML frontmatter including name and description fields is required for note discovery. Enforcing frontmatter and typed related links ensures the archive maintains searchable, consistent metadata across all entries.