TG

    Test Gen Agent

    1

    OpenClaw skill for test generation and self-repair loops: reads a target module, derives cases from real branches and error paths instead of restating the im...

    $6.99

    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
    TG

    Test Gen Agent

    Example session with this skill installed

    Write tests for src/auth/session.ts and ensure we cover the expired token branch.

    • Read your context and instructions
    • Compiled the test gen agent

    Target: session.ts (Auth Module)

    Cases: Valid token (happy), Expired token (boundary), Malformed JWT (error).

    Run: Vitest passed 3/3.

    Repair: 0 iterations needed. Result: Green. Tests use an injected clock to simulate expiry.

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

    About this skill

    OpenClaw skill for test generation and self-repair loops: reads a target module, derives cases from real branches and error paths instead of restating the implementation, writes runnable test files, executes the suite in a sandboxed workspace, and iterates on failures with a bounded repair budget that stops and reports rather than weakening assertions. It does not modify production source to make a test pass, delete failing tests, or run the suite against live infrastructure.

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

    • Cannot repair tests by modifying production code.
    • Refuses to run against live databases or network APIs.
    • Requires manual injection points for tightly coupled dependencies.

    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

    Software
    vitestNode.js

    Permissions

    No special permissions declared or detected

    Listed3 months ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions

    The agent analyzes the actual logic, branches, and error paths of your code to generate tests, rather than simply summarizing the implementation like basic LLM scripts.

    This skill is designed for the OpenClaw framework and requires a sandboxed execution environment to safely run and iterate on the generated test suites.

    The agent enters a self-repair loop where it attempts to fix the test code; however, it is strictly programmed to stop and report errors rather than weakening assertions or modifying your production source code.

    No, the agent is restricted to sandboxed workspaces and will not execute test suites against live infrastructure or production databases to ensure environment safety.

    Each purchase includes the core OpenClaw skill logic, configuration templates for the repair budget, and documentation on setting up the sandboxed workspace for test execution.