Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
GitHub Copilot
Gemini CLI+20 moreClaude CodeCursorCodex CLIGitHub CopilotGemini CLI
OpenClaw
Manus
Grok+17 agentsAgent Test Suite Architect
Autonomous QA architect. Generates robust unit, integration, and E2E test suites targeting a configurable branch-coverage threshold, accessible locators, and deterministic API mocks across TypeScript, Python, and Go.
$18
Agent Test Suite Architect
Example session with this skill installed
Audit src/auth/service.ts and write Vitest tests with 90% branch coverage. Mock the database and external OIDC provider. Run the tests and show me the measured coverage report.
- Read your context and instructions
- Compiled the agent test suite
- Generated the document
I have analyzed src/auth/service.ts, identified five critical logical branches including token expiration and malformed JWKs, and generated a Vitest suite. I executed the tests locally using vitest run --coverage.
Test Suite Execution & Coverage Report
| Metric | Measured Result | Status |
|---|---|---|
| Branch Coverage | 92.3% | PASS (>90%) |
| Line Coverage | 96.8% | PASS |
| Function Coverage | 100% | PASS |
| Total Test Cases | 14 (12 Unit, 2 Integration) | SUCCESS |
Uncovered Gap Analysis
| File | Uncovered Branch / Line | Risk Level | Rationale / Recommendation |
|---|---|---|---|
service.ts | Line 142 (Network Timeout) | Low | Simulated via mock, but physical socket hang not tested. |
service.ts | Line 158 (Memory Limit) | Very Low | Edge case for extremely large JWT payloads. |
import { vi, describe, it, expect, beforeEach } from 'vitest';
import { AuthService } from './service';
import { db } from '../infra/db';
vi.mock('../infra/db', () => ({
db: {
user: { findUnique: vi.fn() }
}
}));
describe('AuthService', () => {
beforeEach(() => {
vi.clearAllMocks();
});
it('should throw Unauthorized when user record is missing', async () => {
// Arrange
const service = new AuthService();
(db.user.findUnique as any).mockResolvedValue(null);
// Act & Assert
await expect(service.validateSession('id_123'))
.rejects.toThrow('Unauthorized');
});
it('should return user data for valid session', async () => {
// Arrange
const mockUser = { id: 'id_123', email: 'test@example.com' };
(db.user.findUnique as any).mockResolvedValue(mockUser);
// Act
const result = await new AuthService().validateSession('id_123');
// Assert
expect(result).toEqual(mockUser);
expect(db.user.findUnique).toHaveBeenCalledWith({ where: { id: 'id_123' } });
});
});
Next steps
- Review the generated
src/auth/__tests__/service.spec.tsfile for business logic alignment. - Add
npm run test:coverageto your pre-commit hooks to maintain the 90% threshold. - Update the OIDC provider discovery URL in your
.env.testto match the new mock configuration.
agent-test-suite-architect.pdf
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
AI-generated code often focuses on the happy path, leading to production crashes caused by unhandled null pointers, network timeouts, or edge cases. Writing comprehensive test suites manually is time-consuming and prone to flaky implementations or weak assertions.
What it does
- Analyzes application logic to build a boundary matrix for nulls, overflows, and edge values.
- Generates idiomatic unit, integration, and E2E tests for TypeScript, Python, Go, and React.
- Implements deterministic mocks for third-party services like Stripe, AWS S3, and database connections.
- Enforces configurable branch coverage by executing real coverage tools and reporting measured gaps.
- Builds Playwright E2E tests using accessible locator hierarchies and web-first assertions.
Frameworks & tools
Vitest, Jest, Pytest, Go testing, Playwright, MSW, and GitHub Actions.
Why this beats prompting it yourself
Generic prompts result in brittle tests with hardcoded sleeps and low-quality mocks. This skill enforces strict QA patterns like Arrange-Act-Assert, eliminates flakiness by prohibiting arbitrary timeouts, and provides a verified gap analysis based on actual execution rather than estimates.
Use cases
- Writing integration tests for complex billing services involving external API mocks.
- Generating table-driven boundary tests for Go or Python backend logic.
- Building accessible, auto-waiting E2E suites for React or Next.js checkout flows.
- Auditing legacy code to identify and fill specific branch-coverage gaps.
Known limitations
Coverage reporting requires a local environment capable of running the project's specific test runner and coverage tool.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 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
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 23 days ago
- Passed all security checks, Safe to install