Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

test-sentinel

bởi guifav

Coding Agents & IDEs
476Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Writes and runs tests (unit, integration, E2E), performs linting, and auto-fixes failures.

Mô tả

Kỹ năng này làm gì

A QA agent for Next.js App Router projects. Writes unit, integration, and E2E tests using Vitest and Playwright, runs them, and autonomously fixes both test bugs and source code bugs it uncovers. Covers linting, type checking, and coverage reporting as part of the same pass.

It closes the loop between writing tests and fixing failures without requiring the developer to manually context-switch between test output, source code, and the linter.

Khi nào nên dùng

  • Adding Vitest unit tests to an untested utility function
  • Writing Playwright E2E tests for a login and redirect flow
  • Running the full test suite before opening a pull request
  • Auto-fixing lint and Prettier errors before a commit
  • Generating integration tests for a Supabase API route with mocked client

Quy trình ví dụ

ĐẦU VÀO

User asks: Add tests for the formatCurrency utility in src/lib/utils.ts

AGENT
  1. 1

    Read src/lib/utils.ts to understand the function signature and edge cases

  2. 2

    Check src/lib/__tests__/ for existing test patterns and utilities

  3. 3

    Build a test plan covering happy path, zero, negative values, and invalid currency codes

  4. 4

    Write colocated Vitest tests in src/lib/__tests__/utils.test.ts

  5. 5

    Run npx vitest run src/lib/__tests__/utils.test.ts, analyze any failures, fix source or test code, then run npx vitest run --coverage to confirm no regression

ĐẦU RA

Passing test file with full edge case coverage and an updated coverage report

Cài đặt

clawhub install guifav/test-sentinel

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết