Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    code dojo

    1

    An interactive coding sensei that quizzes you on your own codebase with belts, streaks, and knowledge gap analysis.

    $4

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    code dojo

    code dojo

    Example session with this skill installed

    quiz me on the src/auth folder. green belt level.

    • Read your context and instructions
    • Compiled the code dojo

    Greetings, student. We shall test your mastery of the authentication logic.

    DOJO Belt: Green Score: 0 Streak: 0 Question 1

    In src/auth/session-manager.ts, there is a logic gate at line 42 regarding token expiration. If the refreshWindow is set to 0, what specific side effect occurs during the validate() call, and which line handles the cleanup?

    Next steps

    • Type your answer to receive grading and points.
    • Type hint if you need to narrow down the specific function block.
    • Type stop at any time to generate your progress report.

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

    About this skill

    Onboarding onto a new codebase usually involves hours of passive reading with low retention. Code Dojo replaces aimless scrolling with an active, interactive training session centered on your actual project files. It acts as a technical sensei that probes your understanding of the repository through targeted questions, grading, and structured feedback.

    What it does

    • Codebase Quizzing generates questions based on specific files, functions, and logic within your current project directory.
    • Progressive Difficulty scales from White Belt (basic utility) to Black Belt (architecture and edge-case design) to match your expertise.
    • Automated Grading evaluates your answers with honest feedback, point tallies, and streak tracking to maintain engagement.
    • Knowledge Gap Analysis identifies specific areas where your understanding of the repo is weak and suggests targeted files to study.
    • Interactive Hints provides two-stage hints if you are stuck, ensuring you learn the logic without giving the answer away immediately.

    How it works

    1. Initialize by typing code dojo or quiz me. The agent scans your entry points and file tree to understand the stack.
    2. Configure your session by selecting a belt level and a focus area, such as a specific folder or the entire project.
    3. Engage with one question at a time, using commands like hint if you are stuck or skip to move on.
    4. Review your performance with a session report that highlights strengths and suggests a concrete practice task.

    Frameworks & tools

    This skill works with any text-based codebase. It utilizes read-only file system tools to analyze project structure and code logic without modifying your source files.

    Why this beats prompting it yourself

    Manual prompting requires you to decide what you don't know, which is a significant cognitive burden. This skill automates the curriculum, prevents the AI from leaking answers prematurely, and maintains a persistent gamified state that tracks your progress across the codebase.

    Use cases

    • Onboarding new developers by having them "train" on the repo for 30 minutes.
    • Code Review Prep to ensure you actually understand the implementation details of a sub-module.
    • Knowledge Transfer when inheriting a legacy project without documentation.
    • Daily Practice to keep architectural patterns fresh in your mind.

    Known limitations

    It will skip node_modules, vendor, and generated files. It cannot access .env files or secrets for security reasons. Requires an existing codebase to function.

    Ignores node_modules, vendor folders, and .env files. Requires at least one code file to generate questions. Scoreboard is session-based unless manually saved to DOJO_NOTES.md.

    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

    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 days ago

    Permissions

    Read Files
    Write Files
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    Code Dojo uses read-only file system tools to scan your project's logic and architecture, meaning it can analyze and quiz you on any text-based programming language or framework.

    Unlike a standard chatbot that might simply explain code, Code Dojo acts as an examiner that withholding answers to test your retention, tracks your 'Belt' progress, and identifies specific knowledge gaps you need to fill.

    To protect your project's integrity, Code Dojo operates with read-only permissions and is hard-coded to ignore sensitive files like .env, secrets, and dependency folders like node_modules.

    Simply initialize the skill by typing 'code dojo' in your terminal or agent interface; it will automatically map your file tree and ask you to select a focus area to begin your training session.

    The Knowledge Gap Analysis feature tracks your performance across different modules, providing a session report that highlights which architectural patterns or folders you haven't mastered yet.

    New in Agents & Orchestration