- Home
- Skills
- Testing & Debugging
- Write Real Tests in Your Framework
Works with the AI Agents you already use
Write Real Tests in Your Framework
Detects your test framework and conventions, lists the cases first, writes the tests and runs them.
$5
About this skill
Type "/tests" (optionally with a file) and Claude:
- Detects your framework and conventions from package.json and existing tests (Vitest, Jest, Mocha, Playwright, Testing Library) and copies their style and location.
- Lists the cases before writing: happy path, edges (empty, null, limits) and expected errors.
- Writes one behavior per test (Arrange / Act / Assert), mocking only boundaries such as network, clock and database.
- Runs the new tests and shows the real result. If a test fails because of a bug in your code, it reports the bug instead of bending the test until it passes.
Permissions it uses: terminal (runs your test command), read files, write files (creates test files). No browser or network access.
Known limitations: writes tests in the framework your project already uses; it does not set up a test framework from scratch, and does not fix the bugs it finds unless you ask.
Unofficial. Not affiliated with Anthropic.
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.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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 27 days ago