{"enrichment":{"faq":[{"a":"wiki-retrieve enables chunk-level search of your vault by breaking pages into smaller passages and scoring them with both BM25 (sparse) and cosine similarity (dense) retrieval. You configure it to search these chunks using hybrid scoring, then optionally apply reranking to surface the most relevant passages. All processing can run on-machine if you use synthetic contextual prefixes, keeping your vault data private.","q":"How do I search chunks in my vault with wiki-retrieve?"},{"a":"wiki-retrieve upgrades vault search from page-level to chunk-level granularity by combining contextual prefixes, BM25 sparse retrieval, and dense reranking to reduce retrieval failures. It works with Obsidian vaults and other wiki systems. Setup is opt-in with built-in privacy gates: run fully on-machine with synthetic prefixes, or opt into Anthropic API or claude CLI tiers for better context generation.","q":"What is wiki-retrieve and how does it improve search?"},{"a":"wiki-retrieve's hybrid setup combines BM25 and cosine similarity scoring. Configure tier-1/tier-2/tier-3 contextual prefix generation to add semantic context to chunks before retrieval. You can run this entirely locally with synthetic prefixes, or enable Anthropic API integration for improved prefix quality. The setup process is opt-in, letting you choose your privacy and performance tradeoff.","q":"How do I set up hybrid retrieval for my wiki?"},{"a":"Yes. wiki-retrieve is designed with privacy gates that let you run fully on-machine using synthetic contextual prefixes and local embedding models like nomic-embed-text. You retain complete control over your vault data. Alternatively, you can opt into Anthropic API or claude CLI tiers for better context generation if you prefer enhanced retrieval quality over full local operation.","q":"Can wiki-retrieve run entirely on my machine?"},{"a":"wiki-retrieve is released under the MIT license, making it free to use, modify, and distribute for both personal and commercial projects.","q":"What license does wiki-retrieve use?"},{"a":"wiki-retrieve generates tier-1/tier-2/tier-3 contextual prefixes that add semantic context to each chunk before retrieval. These prefixes help the BM25 and cosine similarity scorers better understand passage meaning, reducing retrieval failures. You can configure prefix generation to run synthetically on-machine, or use Anthropic API or claude CLI for richer, model-generated context.","q":"How does contextual prefix generation improve retrieval?"}],"shadow_tags":["hybrid-search","dense-sparse-fusion","chunk-retrieval","reranking-pipeline","vector-embeddings","obsidian-plugin","information-retrieval","passage-ranking","local-inference","privacy-first-search"],"summary_rewrite":"wiki-retrieve upgrades vault search from page-level to chunk-level granularity, combining contextual prefixes, BM25 sparse retrieval, and dense reranking to reduce retrieval failures. Setup is opt-in with built-in privacy gates: run fully on-machine with synthetic prefixes, or opt into Anthropic API or claude CLI tiers for better context generation."},"files":[{"bytes":10261,"path":"skills/wiki-retrieve/SKILL.md","sha256":"f64a8e6fe9bb82070fcbe76cd7b97afa111f06445c54f9a3dee72035ac0dc493","url":"https://skillfed.io/files/AgriciDaniel/claude-obsidian/wiki-retrieve/634712dc/SKILL.md"}],"id":"AgriciDaniel/claude-obsidian/wiki-retrieve","links":{"html":"https://skillfed.io/AgriciDaniel/claude-obsidian/wiki-retrieve","md":"https://skillfed.io/AgriciDaniel/claude-obsidian/wiki-retrieve.md","repo":"https://github.com/AgriciDaniel/claude-obsidian"},"meta":{"agents_supported":[],"first_seen":"2026-07-28","forks":1165,"language":"Python","last_updated":"2026-05-28","license":"MIT","name":"wiki-retrieve","publisher":"AgriciDaniel","stars":10007},"relations":{"similar":[{"id":"AgriciDaniel/claude-obsidian/wiki-query"},{"id":"AgriciDaniel/claude-obsidian/wiki-mode"},{"id":"AgriciDaniel/claude-obsidian/wiki-lint"},{"id":"AgriciDaniel/claude-obsidian/wiki-ingest"},{"id":"AgriciDaniel/claude-obsidian/wiki"},{"id":"rohitg00/pro-workflow/wiki-query"},{"id":"AgriciDaniel/claude-obsidian/wiki-cli"},{"id":"AgriciDaniel/claude-obsidian/save"},{"id":"AgriciDaniel/claude-obsidian/autoresearch"},{"id":"CortexReach/memory-lancedb-pro-skill/memory-lancedb-pro-skill"}]},"slug":{"owner":"AgriciDaniel","repo":"claude-obsidian","skill":"wiki-retrieve"},"version":"634712dc"}