skills.rest
AgriciDaniel
AgriciDanielCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

wiki-retrieve

Select and rerank chunk-level passages from an Obsidian Compound Vault.

10.6k|1.2k|Updated Apr 7, 2026
Search Tags:#search#obsidian#reranking#bm25#hybrid retrieval#wiki chunks#contextual prefix
One-click install
npx skills add https://github.com/AgriciDaniel/claude-obsidian --skill wiki-retrieve
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wiki-retrieve
Source: https://github.com/AgriciDaniel/claude-obsidian/tree/main/skills/wiki-retrieve
Command: npx skills add https://github.com/AgriciDaniel/claude-obsidian --skill wiki-retrieve

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

It improves answer quality by finding the most relevant passages inside a large Obsidian “Compound Vault” at chunk-level granularity instead of relying on slower, page-level reads.

Core Features & Use Cases

  • Contextual-prefix chunking: Builds paragraph-boundary chunks and contextual prefixes for each chunk to better match real questions to the right text.
  • Hybrid retrieval pipeline: Uses BM25 to shortlist candidates and then applies dense cosine reranking to reorder results by semantic relevance.
  • Feature-gated, safe integration: Detects whether the retrieval index is provisioned and otherwise cleanly falls back to the legacy hot→index→drill order.
  • Privacy-aware egress control: Supports explicit consent gating for off-machine contextual-prefix generation, with an on-machine synthetic mode option.

Quick Start

Install retrieval indexing by running bash bin/setup-retrieve.sh.

Frequently Asked Questions about wiki-retrieve

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

FAQPage Schema
How does hybrid retrieval improve search relevance in an Obsidian vault?▼

Chunk-level retrieval prevents missed answers by splitting Obsidian pages into paragraph-boundary chunks. It selects and reranks the most relevant passages for your query, avoiding the lower recall and slower reads of page-level granularity.

What is contextual-prefix chunking and when do I need it for knowledge retrieval?▼

Contextual-prefix chunking builds paragraph-boundary chunks with contextual prefixes to match real questions to the right text. You need it when page-level retrieval misses specific answers buried inside large documents.

How do I set up BM25 and dense cosine reranking for my Obsidian vault?▼

Run the bash bin/setup-retrieve.sh script to provision the retrieval index. This configures the hybrid pipeline, enabling BM25 candidate retrieval and optional dense cosine reranking with embedding caching for your vault.

Does wiki-retrieve work without a provisioned retrieval index?▼

Yes, the Skill uses feature-gated safe integration to detect if the retrieval index is provisioned. If the index is missing, it cleanly falls back to the legacy hot→index→drill retrieval path without breaking your workflow.

Can I generate contextual prefixes on-machine to keep my Obsidian vault data private?▼

Yes, the Skill supports privacy-aware egress control with explicit consent gating for off-machine generation. You can use the on-machine synthetic mode option to generate contextual prefixes without sending vault data externally.

Related Skills

Explore More Software Engineering Skills→
anotherbenanotherben
6

vault-init

Automate vault and enterprise ecosystem setup for new project directories.

Community
Advanced
deox420deox420

wiki-retrieve

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

Community
Advanced
ClaudioCeppi83ClaudioCeppi83

obsidian

Automate Obsidian vault management and Markdown note operations via obsidian-cli.

Community
Basic
ConsiliencyConsiliency
8

docs-navigation

Navigate hierarchical AI documentation indexes to locate and load relevant pages efficiently.

Official
Intermediate