Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Tdd Coach

    2

    Most 'TDD' skips the failing test. This mentor enforces Red before Green, even on legacy code.

    Free

    8 usesSecurity scanned
    tdd-coach

    tdd-coach

    Example session with this skill installed

    I need to add a password reset feature to my app. Can you create a TDD plan for the first few steps?

    • Read your context and instructions
    • Compiled the tdd-coach

    [TDD Plan: Password Reset]

    1. Red: Assert 404 when email doesn't exist. Expected: AssertionError
    2. Green: Implement basic lookup check.
    3. Refactor: Move lookup to AuthService.
    4. Commit: feat(auth): handle missing email in reset.
      Next Step: Provide the existing AuthService file to begin step 1.

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

    About this skill

    Automate Professional TDD Discipline

    The TDD Coach is an expert-level engineering skill designed to enforce the Red-Green-Refactor cycle. It solves the common problem of "testing after the fact" by guiding developers through disciplined, behavior-driven development. Whether you are building from scratch or managing legacy systems, this skill ensures your code is fully tested, minimally implemented, and cleanly refactored.

    Advanced Multi-Mode Support

    • Interactive Coaching: A pair-programming mentor that refuses to let you skip phases. It waits for actual test failure outputs before allowing implementation code.
    • Legacy Characterization: Safely wrap untested "black box" code in characterization tests before you attempt migrations or refactors.
    • TDD Planning: Converts vague user stories or requirements into a sequence of micro-commits and specific test cases.
    • Audit & Scorecard: Reviews Pull Requests to score TDD compliance, flagging "test smells" like over-mocking or implementation coupling.

    Why It's Better Than Basic Prompting

    Standard LLMs often provide "hallucinated" complete solutions that bypass the TDD loop entirely. This skill forces a state-machine approach: it tracks your progress through the loop, detects when you're trying to do too much at once, and requires objective proof (test output) before moving forward. It supports all major frameworks including Pytest, Vitest, Jest, JUnit, and Go Test.

    • Cannot execute tests directly; requires user to provide console output. - Performance depends on user-provided context for large legacy systems.

    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

    8 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 months ago

    • Free with an Agensi account

    Permissions

    Browser
    Listed5 months ago

    What's inside

    Frequently Asked Questions

    Unlike standard AI models that generate huge blocks of code at once, this skill acts as a state-machine that enforces the iterative Red-Green-Refactor loop, requiring test failure evidence before allowing you to write implementation code.

    The skill is language-agnostic and includes optimized configurations for major frameworks such as Pytest, Vitest, Jest, JUnit, and Go Test, making it compatible with almost any modern development stack.

    The skill excels at 'Characterization Testing,' where it guides you to write safety-net tests that capture the current behavior of a legacy 'black box' before you attempt to refactor or migrate it.

    Simply import the skill into your preferred AI agent environment and use the 'TDD Planning' command to begin converting your first user story into a sequence of micro-test cases.

    You receive the core TDD Coach skill, specialized modes for legacy code and PR auditing, and ongoing access to version updates that refine its coaching logic and framework compatibility.

    New in Testing & Debugging

    Free