Skill Router 1

    1

    Ultra-fast discovery and routing for large-scale AI agent skill libraries.

    Free

    80 uses5.0 (1 review)

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    skill-router

    Example session with this skill installed

    Find a tool that can help me with deep research using NotebookLM.

    • Read your context and instructions
    • Compiled the -router

    Rank 1: notebooklm-search (Score: 98)
    Path: /skills/research/notebooklm.md
    Summary: Specialized deep-research tool using NotebookLM sources.
    Action: Reading SKILL.md...
    System: Loaded "notebooklm-search". Now executing your research request.

    Reading SKILL.md

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

    About this skill

    What it does

    SKRT acts as a high-performance navigation layer for your AI agent's skill library. It allows your agent to intelligently search, discover, and implement specialized skills from a repository of hundreds of tools in under 50ms. Instead of overwhelming your context window with every possible instruction, SKRT enables "just-in-time" skill loading.

    Problem it solves

    As you accumulate AI skills, your agent often forgets what it can do or fails to trigger the right tool for a niche task. Manual browsing takes too long, and loading all skills at once causes prompt injection risks and context bloat. SKRT solves this by providing a lightning-fast vector search interface that connects user intent to the correct SKILL.md documentation.

    Why it's better than manual prompting

    Unlike a standard LLM, which relies on its static training data to guess how to perform a task, SKRT gives your agent dynamic access to your private, version-controlled library of high-precision prompts and workflows. It handles CJK/English mixed-language queries and provides ranked relevance scores to ensure the most capable tool is selected every time.

    Supported Tools

    • Local Skill Libraries (managed via SKILL.md)
    • CLI integration via `skrt` binary
    • Any agentic framework (Claude Code, Cursor, AutoGPT)

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

    • Initial indexing required after new skill installs.
    • Requires local skrt binary in PATH.
    • Best for local libraries; cloud storage may increase latency.

    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

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 80 times.

    Trust & safety

    Security scan

    Security scan passed 7 months ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Listed7 months ago

    What's inside

    Frequently Asked Questions

    SKRT uses a high-speed vector search layer to find specific logic in your skill library, allowing agents to access hundreds of tools without exceeding context window limits or causing "model confusion" from too many instructions.

    This skill is designed to be framework-agnostic and works seamlessly with agentic tools like Claude Code and Cursor, as well as any custom agent built on standard LLM APIs.

    Your purchase includes the compiled `skrt` binary for CLI use, the core routing logic, and a template for the SKILL.md format to help you organize your existing prompt library.

    Setup is straightforward: install the binary, point it to your local skill directory, and integrate the discovery hook into your agent’s loop; most users are up and running in under five minutes.

    SKRT is optimized for extreme low-latency environments, typically returning the most relevant skill or tool documentation in under 50ms, even with libraries containing hundreds of entries.

    Yes, SKRT features robust cross-language support, specifically optimized to handle mixed CJK (Chinese, Japanese, Korean) and English queries for global development workflows.

    New in Agents & Orchestration

    Free