More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    skill miner

    5

    Analyzes your agent conversation history to find and automate your most frequent recurring tasks.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    33 uses5.0 (3 reviews)
    skill miner

    skill miner

    Example session with this skill installed

    Look at what I have been doing in Cursor and Claude Code over the last few months and make skills for the tasks I repeat most.

    • Read your context and instructions
    • Compiled the miner

    I found 412 requests across your history. After clustering, I have identified 'Feature Documentation' and 'PR Security Review' as your top repetitions. I have generated two .skill files for you: doc-gen.skill and security-audit.skill. Shall I build the third candidate?

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

    About this skill

    The problem

    Your agent history is a goldmine of patterns you do not notice. You repeat the same instructions, corrections, and context every day, wasting tokens and time re-explaining your preferences.

    What it does

    • Scans local history from over 20 different AI agents to find recurring requests.
    • Redacts sensitive data including credentials and emails before analysis.
    • Clusters thousands of requests into distinct tasks using lexical analysis and human-in-the-loop scoring.
    • Generates three ready-to-install .skill files based on your specific historical preferences.
    • Produces a detailed report on three additional automation candidates for future development.

    Frameworks & tools

    Python 3, SQLite, Claude Code, Cursor, and various local agent storage formats.

    Why this beats prompting it yourself

    Manual prompts are based on what you remember, which is often biased toward recent tasks. This tool uses cold data to identify high-friction repetitions you have become blind to, ensuring your skills handle the specific edge cases you have historically encountered.

    Use cases

    • Bootstrap a personalized skill library based on your actual work habits.
    • Audit a team's agent usage to identify common bottlenecks.
    • Turn a complex, multi-step workflow into a single, standardized agent command.
    • Migrate your working preferences between different AI tools and agents.

    Known limitations

    Analysis requires at least 40 requests to be meaningful. It cannot access cloud-only history that is not mirrored to local disk.

    Requires local history files on disk. Needs at least 40 requests for meaningful analysis. Performs best with a 6-month history window.

    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 any payment.

    Reviews

    5.0
    3 reviews
    5
    3
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 33 times.

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    Software
    Python

    Permissions

    Terminal / Shell
    Network Access
    Listed3 months ago
    Updated14 days ago

    What's inside

    Frequently Asked Questions

    Skill Miner scans local data from over 20 popular AI agents, including Claude Code, Cursor, and various IDE-integrated AI tools, provided the history is stored on your local disk.

    This skill uses a built-in redaction layer that automatically strips sensitive information like credentials, API keys, and email addresses before analyzing patterns.

    For the lexical analysis and task clustering to provide meaningful, accurate results, you need a minimum of 40 historical request entries stored locally.

    You receive the Skill Miner engine, three ready-to-use .skill files tailored to your specific work patterns, and a comprehensive automation report for future growth.

    Beyond identifying frequent tasks, Skill Miner uses actual historical data to capture the specific edge cases and preferences you've previously expressed, making the resulting automations far more personalized than manual prompts.

    New in Agents & Orchestration