Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    Unit & Integration Test Generator

    1

    A generated test suite is only worth anything if its tests can actually fail for a real reason.

    Free

    9 installsSecurity scanned
    Unit & Integration Test Generator

    Unit & Integration Test Generator

    Example session with this skill installed

    Write tests for this parse_discount(code, cart_total) function — it returns a discount amount and raises on unknown codes.

    • Read your context and instructions
    • Compiled the unit & integration

    A test plan first (valid code applies the discount; zero and negative cart_total; unknown and empty code raise; very large total rounding; discount never exceeds the total), then a runnable pytest file with parametrized cases, the clock/DB mocked, and assertions on both return values and raised errors — plus a flag: "confirm whether expired codes should error or silently no-op (business rule I can't infer)."

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

    About this skill

    A generated test suite is only worth anything if its tests can actually fail for a real reason. This skill writes those — not coverage-padding stubs that mirror the implementation and break on every refactor. It runs an ordered pass: • Understands the target — inputs, outputs, side effects, dependencies, error conditions, the contract • Detects your framework and conventions — pytest, unittest, Jest, Vitest, JUnit, Go testing, RSpec — and matches your repo's style • Enumerates the cases first — happy path, edge/boundary, error paths, side effects, integration points (shown as a test plan) • Writes clear arrange-act-assert tests — descriptive, isolated, deterministic, with external dependencies mocked properly • Covers the failure modes — the untested error handling where real bugs hide • Adds integration tests where they earn their place • Makes them runnable, with the command to run them You get the test file(s) in your framework plus a coverage summary, including any cases that need domain knowledge it can't infer (flagged, not guessed). It writes tests — it doesn't judge whether an existing suite is adequate; pair it with a test-coverage gate for that.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    9 installs

    Downloaded by developers to date

    Free forever

    No account required to browse

    Trust & safety

    Security scanned

    Verified clean 3 months ago

    • Free to download with an account

    Listed3 months ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions