rankbrain obsidian semantic search

    2

    Semantic search for Obsidian vault using RankBrain-style TF-IDF + graph scoring for Claude Code agents

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    rankbrain obsidian semantic search

    Example session with this skill installed

    obsearch "playwright bypass bot detection"

    • Read your context and instructions
    • Compiled the rankbrain obsidian semantic
    1. playwright_human_bypass_pattern.md (0.94)
    2. browser_stealth_methods.md (0.89)
    3. cloudflare_waf_workaround.md (0.82)

    Reflecting on these 3 notes will save you 2 hours of re-researching stealth headers.

    1. playwright_human_bypass_pattern.md

    Connects securely to your tools. The creator never sees your data.

    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.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Productivity.

    Requires Python 3.8+. Optimized for vaults up to 1,000 notes. Requires local script execution permissions.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    Permissions

    Terminal / Shell
    Browser
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill allows Claude Code agents to perform hybrid searches of your Obsidian vault by combining text similarity (TF-IDF) with graph-based metrics like node centrality and link proximity, surpassing simple keyword matching.

    The skill is designed as a local CLI tool optimized for Claude Code and other terminal-based AI agents, requiring Python 3.8+ and a standard Obsidian markdown vault.

    No, this skill operates entirely locally on your machine using TF-IDF and NetworkX, ensuring your private notes are never sent to external embedding services or third-party APIs.

    You will receive the RankBrain-style search engine source code, the integration scripts for your AI agent, and a configuration guide for mapping your Obsidian vault path.

    While the graph analysis scales well, the TF-IDF ranking is highly optimized for vaults under 1,000 notes; users with significantly larger vaults may experience longer indexing times.

    The skill identifies "orphaned" notes that have no internal links and suggests conceptually related pages, helping you build a denser, more discoverable knowledge graph automatically.

    New in Productivity