skills.rest
xiang2007
xiang2007COMMUNITY
Explore all skills by this author →
GitHub

wiki-retrieve

Search Obsidian Compound Vault content using BM25 indexing and reranking.

Updated Apr 23, 2026
Search Tags:#knowledge management#information retrieval#obsidian#contextual search#vault retrieval
One-click install
npx skills add https://github.com/xiang2007/obsidian-vault --skill wiki-retrieve-xiang2007
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wiki-retrieve
Source: https://github.com/xiang2007/obsidian-vault/tree/main/skills/wiki-retrieve
Command: npx skills add https://github.com/xiang2007/obsidian-vault --skill wiki-retrieve-xiang2007

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, ollama, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps users quickly find relevant information within their Obsidian vault by leveraging advanced search techniques, significantly reducing the time spent on manual content retrieval.

Core Features & Use Cases

  • Hybrid Retrieval: Combines different search algorithms for better results.
  • Contextual Search: Finds information based on context rather than exact keyword matches.
  • BM25 Indexing: Uses the BM25 algorithm to score potential results.
  • Reranking: Refines search results using cosine similarity for improved accuracy.
  • Use Case: When you're working on a complex project and need to quickly find a specific concept or passage from multiple documents in your vault.

Quick Start

Run the setup script to enable advanced retrieval features in your vault.

Frequently Asked Questions about wiki-retrieve

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

FAQPage Schema
How do I perform contextual search in an Obsidian vault?▼

Contextual search in an Obsidian vault is achieved using a hybrid retrieval approach. It combines BM25 indexing with cosine similarity reranking to find information based on context rather than exact keyword matches.

Do I need Python and Ollama to enable reranking for Obsidian vault retrieval?▼

Yes, Python and Ollama are required dependencies to enable advanced retrieval capabilities. They specifically power the reranking phase that refines search results using cosine similarity for improved accuracy.

What is the best way to find specific concepts across multiple Obsidian documents?▼

The best way to find specific concepts across multiple documents is using hybrid BM25 indexing and reranking. This method scores potential results and refines them to quickly retrieve relevant passages from complex vaults.

How does BM25 indexing improve information retrieval in a knowledge management vault?▼

BM25 indexing improves information retrieval by algorithmically scoring potential search results based on relevance. Combined with reranking, it significantly reduces the time spent on manual content retrieval within large knowledge bases.

Can I use this contextual search approach without running a setup script?▼

No, you must run the setup script first to enable the advanced hybrid retrieval features. This initializes the required Python and Ollama environments for the BM25 indexing and reranking processes.

Related Skills

Explore More Product & Management Skills→
CraftOS-devCraftOS-dev
375

qmd

Index and search local files with BM25, vector embeddings, and reranking.

Community
Intermediate
Lloyd-JahnLloyd-Jahn
14

paper-search

Search scholarly papers across arXiv, Crossref, Google Scholar, and PubMed.

Community
Advanced
dallenpyrahdallenpyrah

obsidian-vault

Search, create, and link notes in Obsidian vaults using wikilinks.

Community
Basic
JuanMS20JuanMS20

qmd

Index Markdown and text files for local hybrid search with BM25, vectors, and reranking.

Community
Advanced