wiki-retrieve

Name: wiki-retrieve
Availability: InStock
Author: deox420

Retrieve wiki chunks using contextual-prefix, BM25, and cosine rerank.

Updated Jun 1, 2026

Search Tags:#retrieval #vault #chunking #semantic-search #bm25 #wiki-retrieve #contextual-prefix

Ready to run

npx skills add https://github.com/deox420/second-brain --skill wiki-retrieve-deox420

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: wiki-retrieve
Source: https://github.com/deox420/second-brain/tree/main/skills/wiki-retrieve
Command: npx skills add https://github.com/deox420/second-brain --skill wiki-retrieve-deox420

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Hybrid retrieval over the vault replaces coarse page-level reads with chunk-level analysis to deliver more precise answers.

Core Features & Use Cases

Chunk-level contextual-prefix generation and BM25 indexing for fast, relevant passage retrieval.
Dense reranking using a local or API-backed LLM to surface top passages with citations.
Integration with wiki-query and autoresearch workflows to improve search quality and consistency.

Quick Start

Run bash bin/setup-retrieve.sh to provision the retrieval setup, then test a query with wiki-query to verify retrieval.

Frequently Asked Questions about wiki-retrieve

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

FAQPage Schema

How do I perform chunk-level retrieval over a vault instead of reading full pages?▼

Chunk-level vault retrieval replaces coarse page-level reads by applying contextual-prefix generation, BM25 indexing, and dense reranking to surface precise passages with citations.

How does hybrid retrieval combine BM25 and semantic cosine reranking?▼

Hybrid retrieval uses BM25 indexing for fast keyword-based passage retrieval, then applies a dense cosine rerank using a local or API-backed LLM to surface the most contextually relevant top passages.

Do I need a local LLM to use dense reranking for vault passages?▼

No, dense reranking can use either a local LLM or an API-backed rerank service. The required setup is configured during the bin/setup-retrieve.sh provisioning step.

What's the best way to improve wiki-query and autoresearch search quality?▼

Integrating chunk-level hybrid retrieval into wiki-query and autoresearch workflows improves search quality by replacing page-level reads with contextual-prefix generation and dense passage reranking.

Why does page-level vault retrieval return irrelevant context for my queries?▼

Page-level retrieval returns irrelevant context because it lacks chunking and indexing granularity; applying chunk-level BM25 indexing and dense reranking resolves this by isolating precise passages.

Can I use wiki-retrieve for candidate curation and contextual passage extraction?▼

Yes, wiki-retrieve handles candidate curation by applying chunking, indexing, and dense reranking across wiki pages to extract and cite contextually precise passages.