pkm

Search and audit personal knowledge bases with hybrid vector and BM25 indexing.

40|12|Updated Oct 17, 2011
One-click install
npx skills add https://github.com/lanej/dotfiles --skill pkm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pkm
Source: https://github.com/lanej/dotfiles/tree/main/claude/skills/pkm
Command: npx skills add https://github.com/lanej/dotfiles --skill pkm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pkm-cli.

What problem does it solve?

This Skill solves the challenge of finding relevant, up-to-date, and trustworthy information within your personal knowledge base. Traditional systems often lack temporal awareness, quality filtering, and robust relationship tracking, leading to stale or unreliable search results.

Core Features & Use Cases

  • Quality-Filtered Search: Search documents with filters for certainty (high, medium, low), information type (fact, analysis, idea), and freshness (max age, exclude stale).
  • Relationship Tracking: Automatically track wikilinks, references, and backlinks between documents, helping you discover related content and understand knowledge impact.
  • Knowledge Base Audits: Perform systematic quality audits to identify documents needing review, updates, or improved metadata, ensuring your knowledge base remains valuable.
  • Use Case: Search your personal knowledge base for "kubernetes deployment strategies", but only show high-certainty facts from documents updated in the last 30 days, ensuring you get fresh and reliable information for your current project.

Quick Start

Search your workspace for "API authentication" and show only facts from fresh documents.

Frequently Asked Questions about pkm

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

FAQPage Schema
How do I search my personal knowledge base with quality filters?

Quality-filtered search lets you find relevant documents by certainty level, information type, and freshness. Filter for high-certainty facts updated in the last 30 days, or exclude stale content to ensure search results are trustworthy and current for your needs.

What does temporal awareness in knowledge management mean?

Temporal awareness tracks when documents were created and updated, allowing you to filter by recency and identify stale information. This ensures your search results prioritize fresh, up-to-date knowledge over outdated or superseded content.

Can I automatically track relationships between documents in my knowledge base?

Yes, relationship tracking automatically maps wikilinks, references, and backlinks across documents. This reveals how knowledge connects, helps you discover related content, and shows the impact of each document within your workspace.

How do I audit my knowledge base for quality and staleness?

Knowledge base audits systematically identify documents needing review, updates, or better metadata. Run audits to flag outdated content, missing context, and quality gaps, keeping your personal knowledge base valuable and trustworthy over time.

Does this work with hybrid search using both vector and keyword matching?

Yes, hybrid indexing combines vector embeddings and BM25 keyword search. This dual approach retrieves semantically similar results alongside exact keyword matches, improving relevance for complex knowledge queries.

Can I integrate this with my editor or LSP/MCP tools?

The Skill supports LSP and MCP editor integrations for intelligent search and knowledge curation directly within your development environment. Access quality-filtered search and relationship tracking without leaving your editor.