rankbrain obsidian semantic search
by Shogun Labs
Semantic search for Obsidian vault using RankBrain-style TF-IDF + graph scoring for Claude Code agents
Secure checkout via Stripe
Works with the AI tools you already use
See it in action
You say
obsearch "playwright bypass bot detection"
Your agent does
- playwright_human_bypass_pattern.md (0.94)
- browser_stealth_methods.md (0.89)
- cloudflare_waf_workaround.md (0.82)
Reflecting on these 3 notes will save you 2 hours of re-researching stealth headers.
What you get
About this skill
The problem
Static knowledge bases often become "write-only" archives where past solutions are forgotten and reinvented. Builders waste time researching technical hurdles or process steps they already solved months ago because keyword search fails to surface conceptually related notes.
What it does
- Performs hybrid semantic searches using TF-IDF, graph distance, and node centrality.
- Surfaces "orphaned" notes with zero links and suggests relevant connections to build a denser knowledge graph.
- Identifies "pillar pages" or Map of Content (MOC) candidates by calculating network centrality.
- Operates entirely locally via CLI without external API dependencies or subscription costs.
Frameworks & tools
Python 3.8+, Obsidian, TF-IDF, NetworkX for graph analysis. Works as a CLI tool integrated with your local vault.
Why this beats prompting it yourself
Building a hybrid search engine that combines text similarity with graph theory requires significant boilerplate for parsing markdown links and calculating network metrics. This skill provides a battle-tested ranking formula (60% TF-IDF, 30% Proximity, 10% Centrality) out of the box, optimized for the RankBrain "search gate" workflow.
Use cases
- Pre-task research: Pull up past successful patterns and failure logs before starting a new dev ticket.
- Vault maintenance: Finding and linking disconnected research notes to improve discoverability.
- Strategy mapping: Identifying high-impact hub notes to consolidate into structured Map of Content pages.
Known limitations
The included TF-IDF version is optimized for vaults under 1,000 notes. For databases exceeding 10,000 notes, localized embedding-based methods are recommended.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe
Creator
Building battle-tested Claude Code skills from real-world automation — bot-detection bypass, sales copy generation, and n8n workflow tooling.
Frequently Asked Questions
Popular in Productivity
founder-triage
Break analysis paralysis by turning a messy brain dump into exactly one high-impact action.
context-switch-protector
Eliminate the "re-entry tax" with structured state dumps that capture your focus before context switching.
OS Health Check
The 60-second audit your AI knowledge system is missing. A structural health auditor for personal knowledge systems that flags maintenance rot and stale documentation.
task-initiator
Bypass procrastination by generating the single smallest physical action needed to start any task.