More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Test Suite Generator — Risk-First Unit Tests (Jest, Vitest, Pytest, JUnit, Go)

    2

    Turns a function, module, or class into a risk-prioritized unit test suite: a test plan, edge cases, idiomatic test code, coverage gaps, and the commands to run it.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Test Suite Generator — Risk-First Unit Tests (Jest, Vitest, Pytest, JUnit, Go)

    Test Suite Generator — Risk-First Unit Tests (Jest, Vitest, Pytest, JUnit, Go)

    Example session with this skill installed

    Product: SeatHold venue seat holds
    TypeScript + Vitest
    Function: evaluateHold(heldAtMs, nowMs, holdMinutes, seatsRequested, seatsAvailable)
    Returns: { status: "active" | "expired" | "invalid", reason, expiresAtMs }
    Ask: solid unit suite; edge cases matter

    • Read your context and instructions
    • Compiled the test suite generator

    Coverage confidence: STRONG
    Tests generated: 18 (Vitest, unit)
    Critical paths covered: yes

    Plan highlights

    • CRITICAL: nowMs === expiresAtMs → expired
    • CRITICAL: seatsRequested > seatsAvailable → invalid
    • HIGH: active mid-window + expiresAtMs contract

    Generated: holdWindow.test.ts with it.each tables, fixed epoch clocks
    Run: npx vitest run src/lib/holdWindow.test.ts
    JSON: framework vitest, tests_generated 18, critical_paths 5/5

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

    About this skill

    The problem

    • Blank “write some tests” prompts produce shallow happy-path cases and miss the edges where production breaks.
    • Teams need a plan for what to test and why — not only a pile of assertions.
    • Framework style matters: Jest, Vitest, Pytest, JUnit 5, and Go testing each have different idioms.

    What it does

    • Analyzes a function, module, or class and builds a risk-prioritized test plan.
    • Enumerates edge cases (boundaries, invalid input, empty values, error paths, and more).
    • Generates idiomatic test code for the detected framework (Jest, Vitest, Pytest, JUnit 5, or Go testing).
    • Reports missing coverage honestly and lists what to add next.
    • Provides exact run commands and a machine-readable Test Suite JSON.

    Frameworks & tools

    • JavaScript/TypeScript: Jest or Vitest (describe/it, it.each, spies).
    • Python: Pytest (fixtures, parametrize, raises).
    • Java: JUnit 5 (parameterized tests, clear display names).
    • Go: table-driven tests with testing (and testify only if already used).
    • Works from pasted code or repo paths your agent can read — no SaaS test cloud required.

    Why this beats prompting it yourself

    • Risk-first priorities (CRITICAL/HIGH first) instead of random examples.
    • A full edge-case taxonomy so boundaries and invalid input are not forgotten.
    • Anti-pattern guardrails: no over-mocking, no always-pass asserts, no implementation-detail tests.
    • Framework-aware idioms instead of generic pseudocode.
    • Review-before-write: tests are draft artifacts until you approve saving them.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.

    • Focused on unit (and light integration) tests — not full E2E browser QA
    • Does not invent runtime results; you run the suite to verify
    • Highly coupled code may need a test seam first (the skill will say so)
    • Live external services should be mocked or harnessed, not hit for real
    • Does not refactor production code under the guise of testing

    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 20 days ago

    Software
    vitestNode.js

    Permissions

    Read Files

    This skill analyzes the code you provide and drafts a test suite for you to review. It does not change production code, install packages, call the network, or invent pass/fail results. Grant Read only. Enable Write only if you want the agent to save approved test files; leave Shell, Browser, Network, and Env off unless you later ask it to run tests locally.

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    Unlike generic AI prompts that focus on 'happy paths,' this skill uses a risk-prioritized approach to identify edge cases, boundary conditions, and error paths that typically break in production. It generates a structured test plan and framework-specific code (Jest, Pytest, etc.) rather than just a list of assertions.

    The skill currently supports idiomatic test generation for Jest and Vitest (JS/TS), Pytest (Python), JUnit 5 (Java), and the standard testing package for Go (including table-driven tests). It automatically detects the language and applies the correct framework-specific patterns like fixtures or parameterization.

    Upon purchase, you receive the full AI agent skill configuration, including the risk-analysis logic, edge-case taxonomy, and framework-specific templates. It is designed to work with any AI agent platform that supports custom instructions or tool-calling, requiring only access to your local or pasted code.

    No, this is a local-first tool that processes the code provided to your agent; it does not require a third-party SaaS subscription or cloud testing account. It generates the test code and the exact shell commands needed to run them directly in your own environment.

    The skill is specifically designed to avoid common pitfalls like over-mocking or testing private implementation details. It focuses on 'black-box' functional requirements and provides a 'Review-before-write' phase, allowing you to approve the test plan and coverage gaps before any code is generated.

    New in Testing & Debugging