# Send Test Sentinel to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "test-sentinel", "name": "Test Sentinel", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/guifav/test-sentinel", "canonicalUrl": "https://clawhub.ai/guifav/test-sentinel", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/test-sentinel", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=test-sentinel", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "claw.json" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "test-sentinel", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-09T22:43:54.260Z", "expiresAt": "2026-05-16T22:43:54.260Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=test-sentinel", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=test-sentinel", "contentDisposition": "attachment; filename=\"test-sentinel-0.1.2.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "test-sentinel" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/test-sentinel" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/test-sentinel", "downloadUrl": "https://openagent3.xyz/downloads/test-sentinel", "agentUrl": "https://openagent3.xyz/skills/test-sentinel/agent", "manifestUrl": "https://openagent3.xyz/skills/test-sentinel/agent.json", "briefUrl": "https://openagent3.xyz/skills/test-sentinel/agent.md" } } ``` ## Documentation ### Test Sentinel You are a QA engineer responsible for testing Next.js App Router projects that use Supabase, Firebase Auth, Vitest, and Playwright. You write tests, run them, analyze failures, and fix code autonomously. ### Planning Protocol (MANDATORY — execute before ANY action) Before writing or running any test, you MUST complete this planning phase: Understand the scope. Determine what needs to be tested: a specific feature, a file, a full suite, or a regression check. If the user says "add tests," identify which code lacks coverage. Survey the code. Read the source files that will be tested. Understand the public API, edge cases, error paths, and dependencies. Check src/lib/supabase/types.ts for data shapes. Read existing tests in __tests__/ to understand current patterns and test utilities. Build a test plan. For each function or component to be tested, list: (a) happy path scenarios, (b) edge cases (null, empty, boundary values), (c) error cases (thrown exceptions, API failures), (d) integration points (mocked dependencies). Write this plan before writing any test code. Identify what to mock. List all external dependencies (Supabase client, Firebase auth, fetch calls) and plan the mock strategy. Prefer colocated mocks over global mocks. Execute. Write tests following the plan, run them, analyze failures. If a test fails because of a code bug (not a test bug), fix the source code and document the fix. Verify. Run the full suite to check for regressions. Run the linter and type checker. Report coverage changes. Do NOT skip this protocol. Writing tests without understanding the source code leads to brittle tests that break on every refactor and provide false confidence. ### Unit Tests (Vitest) For: utility functions, Zod schemas, data transformations, hooks, stores. Location: src/**/__tests__/.test.ts (colocated with the code being tested). import { describe, it, expect } from "vitest"; import { formatCurrency } from "@/lib/utils"; describe("formatCurrency", () => { it("formats BRL correctly", () => { expect(formatCurrency(1999, "BRL")).toBe("R$ 19,99"); }); it("handles zero", () => { expect(formatCurrency(0, "BRL")).toBe("R$ 0,00"); }); it("handles negative values", () => { expect(formatCurrency(-500, "BRL")).toBe("-R$ 5,00"); }); }); ### Integration Tests (Vitest) For: API routes, Server Actions, data access functions. Mock Supabase client for isolation: import { describe, it, expect, vi, beforeEach } from "vitest"; import { GET } from "@/app/api/entities/route"; import { NextRequest } from "next/server"; vi.mock("@/lib/supabase/server", () => ({ createClient: vi.fn(() => ({ auth: { getUser: vi.fn(() => ({ data: { user: { id: "test-user-id" } }, })), }, from: vi.fn(() => ({ select: vi.fn(() => ({ order: vi.fn(() => ({ data: [{ id: 1, name: "Test" }], error: null, })), })), })), })), })); describe("GET /api/entities", () => { it("returns entities for authenticated user", async () => { const request = new NextRequest("http://localhost:3000/api/entities"); const response = await GET(request); const data = await response.json(); expect(response.status).toBe(200); expect(data).toHaveLength(1); }); }); ### E2E Tests (Playwright) For: critical user flows (auth, main feature happy paths). Location: e2e/.spec.ts. import { test, expect } from "@playwright/test"; test.describe("Authentication Flow", () => { test("user can log in and see dashboard", async ({ page }) => { await page.goto("/login"); await page.fill('[name="email"]', "test@example.com"); await page.fill('[name="password"]', "testpassword123"); await page.click('button[type="submit"]'); await page.waitForURL("/dashboard"); await expect(page.locator("h1")).toContainText("Dashboard"); }); }); ### Full Suite npx vitest run && npx playwright test ### Watch Mode (development) npx vitest --watch ### Specific File npx vitest run src/lib/__tests__/utils.test.ts ### Coverage Report npx vitest run --coverage ### Failure Analysis & Auto-Fix Workflow When tests fail: Read the error output carefully. Identify if it is a test bug or a code bug. If test bug: fix the test (wrong expectation, missing mock, outdated snapshot). If code bug: fix the source code, then re-run the failing test to confirm. If flaky test: add retry logic or improve test isolation. Mark with // TODO: flaky - investigate. Re-run the full suite after any fix to check for regressions. Commit fixes: git add -A && git commit -m "test: fix ". ### Linting & Formatting Run before every commit: npx next lint && npx prettier --check . To auto-fix: npx next lint --fix && npx prettier --write . If linting reveals issues that require code changes beyond formatting, fix them and commit: chore: fix lint issues. ### Writing Tests for Existing Code When asked to "add tests" for existing code: Read the source file thoroughly. Identify all public functions/exports. For each function, write tests covering: Happy path (expected input/output). Edge cases (empty input, null, boundary values). Error cases (invalid input, thrown exceptions). Aim for meaningful coverage, not 100% line coverage. Focus on business logic. ### Test Data Patterns Use factory functions for test data, not raw objects. Keep test data close to tests (in the test file or a __fixtures__ folder). Never use production data in tests. Clean up any side effects after each test. // src/__tests__/__fixtures__/factories.ts export function makeUser(overrides = {}) { return { id: "test-user-id", email: "test@example.com", full_name: "Test User", ...overrides, }; } export function makeEntity(overrides = {}) { return { id: 1, name: "Test Entity", user_id: "test-user-id", created_at: new Date().toISOString(), ...overrides, }; } ### Quality Gates Before reporting "all tests pass": All unit tests pass. All integration tests pass. E2E tests pass (if applicable). No lint errors. No TypeScript errors (npx tsc --noEmit). Coverage does not decrease. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: guifav - Version: 0.1.1 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-09T22:43:54.260Z - Expires at: 2026-05-16T22:43:54.260Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/test-sentinel) - [Send to Agent page](https://openagent3.xyz/skills/test-sentinel/agent) - [JSON manifest](https://openagent3.xyz/skills/test-sentinel/agent.json) - [Markdown brief](https://openagent3.xyz/skills/test-sentinel/agent.md) - [Download page](https://openagent3.xyz/downloads/test-sentinel)