Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/deathrashed/agents --skill testThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Control the in-app Browser for opening, navigating, inspecting visible or interactive page state, clicking, typing, screenshots, and local web testing. It can have existing signed-in sessions. For semantic operations on linked resources, prefer a purpose-built connector, API, or CLI when available.
Control the user's Chrome browser for tasks that depend on existing Chrome state: tabs, logged-in sessions, or extensions. Prefer purpose-built connectors, APIs, or CLIs when available.
Control local Mac apps through Computer Use for tasks that require reading or operating app UI. Prefer purpose-built connectors, APIs, or CLIs when available.
Based on SOC occupation classification
Showing SKILL.md
| name | test |
| description | Create and run tests with coverage analysis (Tester Agent) |
Test request:
Task: {{args}}
| Mode | Trigger | Description |
|---|---|---|
| RUN | default | Run full test suite |
| FIX | "fix", "failing", "broken" | Auto-fix failing tests |
| COVERAGE | "coverage", "gaps" | Analyze coverage gaps |
| WRITE | "write", "create", "add" | Generate new tests |
Automatically detect and run according to the project:
| Framework | Detection | Command |
|---|---|---|
| Jest | package.json has jest | npm test |
| Vitest | vitest.config.* | npm run test |
| pytest | pytest.ini / pyproject.toml | pytest -v |
| Flutter | pubspec.yaml | flutter test |
| Go | go.mod | go test ./... |
# Auto-detected: [framework]
[test command]
| Metric | Value | Default Target | Critical Code Target |
|---|---|---|---|
| Statements | X% | 80% | 90% |
| Branches | X% | 75% | 85% |
| Functions | X% | 80% | 90% |
| Lines | X% | 80% | 90% |
Target Guidelines:
✅ Passed: X tests
❌ Failed: Y tests
⏭️ Skipped: Z tests
⏱️ Duration: Xs
⚠️ Uncovered areas:
src/file.ts lines 45-52src/other.ts function handleErrorWhen there are failing tests:
Test: [test name]
Error: [error message]
File: [file:line]
[Why it fails]
// Before
[old code]
// After
[fixed code]
| File | Coverage | Missing |
|---|---|---|
file.ts | 65% | Lines 10-15, 45-50 |
util.ts | 45% | Functions: parse, validate |
[function][scenario]Generate tests for:
describe('[Component/Function]', () => {
describe('[Method]', () => {
it('should [expected behavior]', () => {
// Arrange
// Act
// Assert
});
it('should handle [edge case]', () => {
// Test edge case
});
it('should throw on [error condition]', () => {
// Test error handling
});
});
});
{
"passed": 42,
"failed": 0,
"skipped": 2,
"coverage": 85.5,
"duration": "12.3s",
"timestamp": "2024-12-14T19:00:00Z"
}
/test before starting new workKey Takeaway: Test execution isn't about 100% coverage - it's about 80%+ on critical paths with zero flaky tests.