[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D8BJ84SZWWWZWSWXPHM8BN":3,"skill-same:01M7D8BJ84SZWWWZWSWXPHM8BN":90},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":68,"commitSha":69,"skillDirectory":70,"forksCount":14,"repositoryHtmlUrl":71,"repositoryHomepageUrl":6,"ownerHtmlUrl":72,"ownerBlogUrl":73,"ownerDescription":74,"updatedAt":75,"install":76,"resources":89},"01M7D8BJ84SZWWWZWSWXPHM8BN","Cursor AI Testing Patterns",null,"Effective test automation patterns with Cursor AI IDE including Composer for test suite generation, Cmd+K for inline test edits, Chat for test debugging, codebase-aware test generation, and rules configuration for testing conventions.","GrupoANDevelopment-m\u002Falberto-ai","GrupoANDevelopment-m","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257455179?v=4","01M7D69X2N2KEVN0SJF6WGM6SH","Antônio  Ndombe","01M7D69X3P5JTT8H8S904N3888",0,"MIT","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Fqa\u002Fcursor-testing-patterns\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: Cursor AI Testing Patterns\ndescription: Effective test automation patterns with Cursor AI IDE including Composer for test suite generation, Cmd+K for inline test edits, Chat for test debugging, codebase-aware test generation, and rules configuration for testing conventions.\nversion: 1.0.0\nauthor: thetestingacademy\nlicense: MIT\ntags: [cursor, cursor-ai, ai-ide, composer, test-generation, inline-editing, chat-debugging, codebase-aware, rules-for-ai, testing-patterns]\ntestingTypes: [unit, integration, e2e, api]\nframeworks: [vitest, jest, playwright, cypress, pytest]\nlanguages: [typescript, javascript, python]\ndomains: [web, backend, api, frontend]\nagents: [claude-code, cursor, github-copilot, windsurf, codex, aider, continue, cline, zed, bolt, gemini-cli, amp]\n---\n\n# Cursor AI Testing Patterns Skill\n\nYou are an expert in using Cursor AI IDE for test automation. When the user asks you to generate tests with Cursor, configure Cursor rules for testing, use Composer for multi-file test generation, or optimize Cursor workflows for QA, follow these detailed instructions.\n\n## Core Principles\n\n1. **Codebase-aware generation** -- Cursor indexes your entire codebase. Reference files, functions, and patterns using @mentions to give the AI full context for test generation.\n2. **Rules for consistent quality** -- Configure .cursorrules to enforce testing conventions, naming patterns, and framework preferences across all AI-generated tests.\n3. **Composer for multi-file operations** -- Use Cursor Composer for generating test suites that span multiple files: page objects, fixtures, helpers, and test specs.\n4. **Cmd+K for surgical edits** -- Use inline editing (Cmd+K) for targeted changes: adding a test case, fixing an assertion, or refactoring a single test function.\n5. **Chat for investigation** -- Use Cursor Chat with @codebase to understand existing test patterns before generating new ones. Ask it to explain failures.\n6. **Apply from Chat** -- When Chat suggests code, use the Apply button to directly insert or replace code in your editor rather than copy-pasting.\n7. **Iterative test development** -- Generate a basic test suite first, run it, then use Cursor to fix failures and add edge cases based on execution results.\n\n## Project Structure\n\n```\nproject\u002F\n  .cursorrules                 # Testing conventions\n  .cursor\u002F\n    rules\u002F\n      testing.mdc              # Testing-specific rules\n  src\u002F\n    services\u002F\n      user-service.ts\n      user-service.test.ts\n    components\u002F\n      LoginForm.tsx\n      LoginForm.test.tsx\n  tests\u002F\n    e2e\u002F\n      login.spec.ts\n      checkout.spec.ts\n    fixtures\u002F\n      test-data.ts\n    helpers\u002F\n      test-utils.ts\n```\n\n## Cursor Rules for Testing\n\n```markdown\n\u003C!-- .cursorrules -->\n# Testing Rules\n\n## Test Framework\n- Use vitest for all unit and integration tests\n- Use Playwright for E2E tests\n- TypeScript strict mode in all test files\n\n## Test Conventions\n- Follow Arrange-Act-Assert (AAA) pattern\n- Name tests: \"should [expected behavior] when [condition]\"\n- Group related tests in describe blocks\n- One assertion focus per test (multiple asserts allowed if testing same behavior)\n- Always include edge cases: null, undefined, empty values, boundary conditions\n- Always include error\u002Ffailure test cases\n\n## Mocking\n- Use vi.mock() for module mocking\n- Use vi.fn() for function mocking\n- Use vi.spyOn() for spying on existing methods\n- Reset mocks in beforeEach with vi.clearAllMocks()\n- Never mock the module under test\n\n## Assertions\n- Prefer specific assertions: toBe, toEqual, toContain over toBeTruthy\n- Use toThrow for error testing\n- Use resolves\u002Frejects for async assertions\n- Include meaningful error messages in assertions\n\n## File Organization\n- Colocate tests with source files: foo.ts -> foo.test.ts\n- E2E tests in tests\u002Fe2e\u002F\n- Shared test utilities in tests\u002Fhelpers\u002F\n- Test fixtures in tests\u002Ffixtures\u002F\n\n## Do Not\n- Use any type in test files\n- Use setTimeout for async waiting\n- Write tests that depend on execution order\n- Hard-code API URLs or credentials\n- Skip tests without a TODO comment explaining why\n```\n\n## Composer Workflows for Test Generation\n\n```typescript\n\u002F\u002F Workflow 1: Generate comprehensive test suite with Composer\n\u002F\u002F Prompt: \"Generate a complete test suite for @user-service.ts with vitest.\n\u002F\u002F Include unit tests for all public methods, mock the database dependency,\n\u002F\u002F test both success and error paths, and follow the patterns in @user-service.test.ts\"\n\n\u002F\u002F Result: Cursor generates the full test file considering both files\n\nimport { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';\nimport { UserService } from '.\u002Fuser-service';\n\n\u002F\u002F Cursor reads the actual implementation to create accurate mocks\nvi.mock('..\u002Fdb\u002Fconnection', () => ({\n  db: {\n    select: vi.fn(),\n    insert: vi.fn(),\n    update: vi.fn(),\n    delete: vi.fn(),\n  },\n}));\n\nimport { db } from '..\u002Fdb\u002Fconnection';\n\ndescribe('UserService', () => {\n  let service: UserService;\n\n  beforeEach(() => {\n    service = new UserService();\n    vi.clearAllMocks();\n  });\n\n  \u002F\u002F Cursor generates tests for each public method found in the source\n\n  describe('findById', () => {\n    it('should return user when found', async () => {\n      const mockUser = { id: '1', name: 'Alice', email: 'alice@test.com' };\n      vi.mocked(db.select).mockResolvedValueOnce([mockUser]);\n\n      const result = await service.findById('1');\n      expect(result).toEqual(mockUser);\n    });\n\n    it('should return null when user not found', async () => {\n      vi.mocked(db.select).mockResolvedValueOnce([]);\n\n      const result = await service.findById('nonexistent');\n      expect(result).toBeNull();\n    });\n\n    it('should throw when database error occurs', async () => {\n      vi.mocked(db.select).mockRejectedValueOnce(new Error('DB connection failed'));\n\n      await expect(service.findById('1')).rejects.toThrow('DB connection failed');\n    });\n  });\n\n  \u002F\u002F ... Cursor continues for all public methods\n});\n```\n\n## Cmd+K Inline Editing Patterns\n\n```typescript\n\u002F\u002F Pattern 1: Add a test case inline\n\u002F\u002F Select empty space inside describe block, press Cmd+K\n\u002F\u002F Prompt: \"Add a test case that verifies createUser rejects duplicate emails\"\n\n\u002F\u002F Cursor generates and inserts:\nit('should reject duplicate emails', async () => {\n  vi.mocked(db.insert).mockRejectedValueOnce(\n    new Error('UNIQUE constraint failed: users.email')\n  );\n\n  await expect(\n    service.createUser({ name: 'Bob', email: 'existing@test.com' })\n  ).rejects.toThrow('Email already exists');\n});\n\n\u002F\u002F Pattern 2: Strengthen an assertion\n\u002F\u002F Select a weak assertion, press Cmd+K\n\u002F\u002F Prompt: \"Make this assertion more specific\"\n\n\u002F\u002F Before:\nexpect(result).toBeTruthy();\n\n\u002F\u002F After:\nexpect(result).toEqual({\n  id: expect.any(String),\n  name: 'Alice',\n  email: 'alice@test.com',\n  createdAt: expect.any(Date),\n});\n\n\u002F\u002F Pattern 3: Convert test to parameterized\n\u002F\u002F Select a test, press Cmd+K\n\u002F\u002F Prompt: \"Convert to parameterized test using it.each\"\n\n\u002F\u002F Before:\nit('should validate email format', () => {\n  expect(validateEmail('bad')).toBe(false);\n});\n\n\u002F\u002F After:\nit.each([\n  ['bad', false],\n  ['also-bad', false],\n  ['missing@domain', false],\n  ['valid@test.com', true],\n  ['user+tag@test.com', true],\n])('should validate \"%s\" as %s', (email, expected) => {\n  expect(validateEmail(email)).toBe(expected);\n});\n```\n\n## Chat Debugging Patterns\n\n```typescript\n\u002F\u002F Use Cursor Chat to debug test failures\n\n\u002F\u002F Prompt: \"This test is failing with 'TypeError: Cannot read properties of undefined'.\n\u002F\u002F @user-service.ts @user-service.test.ts\n\u002F\u002F The findById method works in the app but the mock is not being applied.\n\u002F\u002F Help me fix the mock setup.\"\n\n\u002F\u002F Cursor analyzes both files and identifies the issue:\n\u002F\u002F \"The mock is not being hoisted correctly. vi.mock() calls are hoisted\n\u002F\u002F to the top of the file, but the mock factory is using variables that\n\u002F\u002F aren't defined yet. Move the mock return values to inside the factory\n\u002F\u002F function or use vi.mocked() in beforeEach.\"\n\n\u002F\u002F Prompt: \"Generate missing test cases for @user-service.ts\n\u002F\u002F by analyzing code coverage gaps. Focus on untested branches.\"\n\n\u002F\u002F Cursor reads the source and identifies untested code paths:\n\u002F\u002F \"I found these untested branches:\n\u002F\u002F 1. Line 45: else branch when user.role is 'admin'\n\u002F\u002F 2. Line 67: catch block for validation errors\n\u002F\u002F 3. Line 89: early return when input.email is empty\n\u002F\u002F Here are tests for each...\"\n```\n\n## Multi-File Generation with Composer\n\n```typescript\n\u002F\u002F Prompt for Composer:\n\u002F\u002F \"Create a complete E2E test setup for the checkout flow:\n\u002F\u002F 1. Page objects for CartPage, CheckoutPage, ConfirmationPage\n\u002F\u002F 2. Test fixtures for test products and users\n\u002F\u002F 3. E2E test spec covering add-to-cart, checkout, and confirmation\n\u002F\u002F Follow patterns in @tests\u002Fe2e\u002F and @tests\u002Ffixtures\u002F\n\u002F\u002F Use Playwright with TypeScript\"\n\n\u002F\u002F Cursor generates multiple files:\n\n\u002F\u002F tests\u002Fe2e\u002Fpages\u002Fcart.page.ts\nimport { Page, Locator } from '@playwright\u002Ftest';\n\nexport class CartPage {\n  private readonly cartItems: Locator;\n  private readonly checkoutButton: Locator;\n  private readonly totalPrice: Locator;\n\n  constructor(private page: Page) {\n    this.cartItems = page.getByTestId('cart-item');\n    this.checkoutButton = page.getByRole('button', { name: 'Checkout' });\n    this.totalPrice = page.getByTestId('total-price');\n  }\n\n  async getItemCount(): Promise\u003Cnumber> {\n    return this.cartItems.count();\n  }\n\n  async getTotalPrice(): Promise\u003Cstring> {\n    return this.totalPrice.textContent() || '';\n  }\n\n  async proceedToCheckout(): Promise\u003Cvoid> {\n    await this.checkoutButton.click();\n  }\n}\n\n\u002F\u002F tests\u002Fe2e\u002Fcheckout.spec.ts\nimport { test, expect } from '@playwright\u002Ftest';\nimport { CartPage } from '.\u002Fpages\u002Fcart.page';\n\ntest.describe('Checkout Flow', () => {\n  test('complete purchase flow', async ({ page }) => {\n    \u002F\u002F Navigate to product\n    await page.goto('\u002Fproducts\u002Fwireless-headphones');\n\n    \u002F\u002F Add to cart\n    await page.getByRole('button', { name: 'Add to Cart' }).click();\n    await expect(page.getByText('Added to cart')).toBeVisible();\n\n    \u002F\u002F Go to cart\n    const cartPage = new CartPage(page);\n    await page.goto('\u002Fcart');\n    expect(await cartPage.getItemCount()).toBe(1);\n\n    \u002F\u002F Proceed to checkout\n    await cartPage.proceedToCheckout();\n    await expect(page).toHaveURL(\u002F\\\u002Fcheckout\u002F);\n  });\n});\n```\n\n## Cursor Rules File for Testing (.cursor\u002Frules\u002Ftesting.mdc)\n\n```markdown\n---\ndescription: Testing rules for AI-generated test code\nglobs: [\"**\u002F*.test.ts\", \"**\u002F*.test.tsx\", \"**\u002F*.spec.ts\"]\n---\n\n# Test Generation Rules\n\n## Framework\n- Use vitest for unit\u002Fintegration tests\n- Use Playwright for E2E tests\n- TypeScript strict mode required\n\n## Structure\n- Colocate test files with source: foo.ts -> foo.test.ts\n- E2E tests go in tests\u002Fe2e\u002F\n- Use describe blocks grouped by function\u002Fmethod name\n- Use nested describes for sub-scenarios\n\n## Naming\n- Test names: \"should [expected behavior] when [condition]\"\n- Describe blocks: function or class name being tested\n- Test file names: match source file with .test.ts suffix\n\n## Assertions\n- Use toBe for primitives\n- Use toEqual for objects\u002Farrays\n- Use toContain for array membership\n- Use toThrow for error testing\n- Use toHaveBeenCalledWith for mock verification\n- Never use toBeTruthy for non-boolean values\n\n## Mocking\n- vi.mock() at top of file for module mocks\n- vi.fn() for individual function mocks\n- vi.spyOn() for partial mocking\n- Always verify mocks were called correctly\n- Clear mocks in beforeEach: vi.clearAllMocks()\n\n## Coverage Requirements\n- Functions: 80% minimum\n- Branches: 75% minimum\n- Lines: 80% minimum\n\n## Anti-Patterns to Avoid\n- No any types\n- No setTimeout\u002Fsleep for waiting\n- No console.log in tests (use debug mode)\n- No shared mutable state between tests\n- No tests that depend on execution order\n```\n\n## Advanced Composer Patterns\n\n### Pattern: Generate Test Suite from OpenAPI Spec\n\n```typescript\n\u002F\u002F Prompt for Composer:\n\u002F\u002F \"I have an OpenAPI spec at @openapi.yaml. Generate a complete API test suite\n\u002F\u002F that tests every endpoint defined in the spec. Include:\n\u002F\u002F 1. Success path tests for each endpoint\n\u002F\u002F 2. Validation error tests for required fields\n\u002F\u002F 3. Authentication tests (missing token, expired token)\n\u002F\u002F 4. Not found tests for invalid IDs\n\u002F\u002F Follow patterns in @tests\u002Fapi\u002Fexisting-api.test.ts\"\n\n\u002F\u002F Cursor reads the OpenAPI spec and generates targeted tests for each endpoint\nimport { describe, it, expect, beforeAll } from 'vitest';\n\nconst BASE_URL = process.env.API_URL || 'http:\u002F\u002Flocalhost:3000';\nlet authToken: string;\n\nbeforeAll(async () => {\n  const response = await fetch(\\`\\${BASE_URL}\u002Fauth\u002Flogin\\`, {\n    method: 'POST',\n    headers: { 'Content-Type': 'application\u002Fjson' },\n    body: JSON.stringify({ email: 'test@test.com', password: 'test123' }),\n  });\n  const data = await response.json();\n  authToken = data.token;\n});\n\ndescribe('GET \u002Fapi\u002Fusers', () => {\n  it('should return paginated user list', async () => {\n    const response = await fetch(\\`\\${BASE_URL}\u002Fapi\u002Fusers?page=1&limit=10\\`, {\n      headers: { Authorization: \\`Bearer \\${authToken}\\` },\n    });\n    expect(response.status).toBe(200);\n    const data = await response.json();\n    expect(data.users).toBeInstanceOf(Array);\n    expect(data.total).toBeGreaterThanOrEqual(0);\n  });\n\n  it('should return 401 without auth token', async () => {\n    const response = await fetch(\\`\\${BASE_URL}\u002Fapi\u002Fusers\\`);\n    expect(response.status).toBe(401);\n  });\n});\n\ndescribe('POST \u002Fapi\u002Fusers', () => {\n  it('should create user with valid data', async () => {\n    const response = await fetch(\\`\\${BASE_URL}\u002Fapi\u002Fusers\\`, {\n      method: 'POST',\n      headers: {\n        'Content-Type': 'application\u002Fjson',\n        Authorization: \\`Bearer \\${authToken}\\`,\n      },\n      body: JSON.stringify({\n        name: 'Test User',\n        email: \\`test-\\${Date.now()}@test.com\\`,\n        role: 'user',\n      }),\n    });\n    expect(response.status).toBe(201);\n    const data = await response.json();\n    expect(data.id).toBeDefined();\n  });\n\n  it('should return 400 for missing required fields', async () => {\n    const response = await fetch(\\`\\${BASE_URL}\u002Fapi\u002Fusers\\`, {\n      method: 'POST',\n      headers: {\n        'Content-Type': 'application\u002Fjson',\n        Authorization: \\`Bearer \\${authToken}\\`,\n      },\n      body: JSON.stringify({}),\n    });\n    expect(response.status).toBe(400);\n  });\n});\n```\n\n### Pattern: Migrate Tests Between Frameworks\n\n```typescript\n\u002F\u002F Prompt for Composer:\n\u002F\u002F \"@tests\u002Fjest\u002F contains Jest tests. Migrate them to vitest:\n\u002F\u002F 1. Replace jest.fn() with vi.fn()\n\u002F\u002F 2. Replace jest.mock() with vi.mock()\n\u002F\u002F 3. Replace jest.spyOn() with vi.spyOn()\n\u002F\u002F 4. Update imports from @jest\u002Fglobals to vitest\n\u002F\u002F 5. Keep all test logic identical\n\u002F\u002F 6. Generate a migration report\"\n\n\u002F\u002F Cursor processes each file and generates the migrated version\n\u002F\u002F maintaining exact test logic while updating framework-specific APIs\n```\n\n## Cursor Agent Mode for Test Debugging\n\nWhen a test fails, use Cursor's Agent mode to debug systematically. Provide the error output and ask the agent to analyze the failure, identify the root cause, and suggest a fix.\n\nEffective debugging prompts include:\n\n\"This test is failing with the following error. Read the test file and the source file it tests. Identify why the mock is not being applied correctly.\"\n\n\"The E2E test passes locally but fails in CI. The error is a timeout on the login button click. What could cause this difference and how should I fix it?\"\n\n\"I have 5 flaky tests that fail intermittently. Here are the test names and their recent pass\u002Ffail history. Analyze the tests and suggest what is causing the flakiness.\"\n\n\"This API test returns 500 instead of the expected 200. Read the API route handler and the test to identify the mismatch.\"\n\n## Best Practices\n\n1. **Use @mentions for precise context** -- Reference specific files with @filename.ts to give Cursor exact context for test generation.\n2. **Configure .cursorrules for your testing conventions** -- Set framework preferences, naming patterns, and quality standards in rules files.\n3. **Use Composer for multi-file test generation** -- When tests span page objects, fixtures, and specs, Composer generates them as a coherent set.\n4. **Use Cmd+K for targeted edits** -- Adding one test case, fixing one assertion, or refactoring one function is faster with inline editing.\n5. **Ask Chat to explain before generating** -- Before generating tests, ask Cursor Chat to explain the existing test patterns in your codebase.\n6. **Iterate: generate, run, fix, expand** -- Generate a basic suite, run it, use Cursor to fix failures, then ask for more edge cases.\n7. **Reference existing test patterns** -- Include @existing-test.test.ts in prompts so Cursor follows your established patterns.\n8. **Use Apply for code insertion** -- When Chat suggests code, use the Apply button instead of copy-pasting to maintain proper formatting.\n9. **Review all generated mocks** -- Cursor generates mocks based on the source code, but verify they accurately represent real behavior.\n10. **Keep rules files updated** -- When your testing conventions change, update .cursorrules so all future AI generations follow the new standards.\n\n## Anti-Patterns\n\n1. **Generating tests without providing source context** -- Tests generated without @mentioning the source file are generic and often incorrect.\n2. **Accepting all generated code without review** -- AI-generated tests can have incorrect assertions, missing edge cases, and logical errors. Always review.\n3. **Not using rules files** -- Without .cursorrules, every developer gets different test styles from Cursor, creating inconsistency.\n4. **Using Chat for simple edits** -- Single-line changes are faster with Cmd+K. Do not start a Chat conversation for simple assertion fixes.\n5. **Not running tests after generation** -- Generated tests that compile do not necessarily test the right behavior. Run them immediately.\n6. **Over-specifying in prompts** -- Extremely detailed prompts often confuse the AI. Start with a clear, concise request and refine iteratively.\n7. **Generating the entire test suite at once** -- Large generation requests produce lower quality. Generate in focused batches per function or module.\n8. **Ignoring Cursor's codebase indexing** -- Cursor indexes your project. Use @codebase to leverage this index for finding patterns and conventions.\n9. **Not providing negative examples** -- If you want Cursor to avoid certain patterns (like using any), specify what NOT to do in your rules.\n10. **Treating Cursor output as final** -- Cursor is a coding assistant, not a QA engineer. Generated tests are a starting point, not a finished product.\n\n## Cursor Tab Completion for Test Writing\n\nCursor Tab provides predictive completions while you type. For test writing, this is powerful because test code follows predictable patterns. When you type the beginning of a test case, Cursor Tab predicts the entire test body based on the function name and the describe block context.\n\nTo maximize Tab completions for testing, keep the source file open in a split pane, use descriptive it() names that convey the test intent, follow consistent patterns within each describe block, and accept Tab completions with a single keystroke then refine.\n\nTab is especially effective for parameterized tests. After writing the first test case in a describe block, Tab often suggests the next logical test case with appropriate boundary values or error conditions.\n\n## Cursor Notepad for Test Planning\n\nCursor Notepad is a persistent scratchpad that provides context to the AI across all conversations and code generation. Use Notepad to store your testing conventions, test plan notes, and reference patterns.\n\nCreate a note titled \"Testing Standards\" that includes your preferred assertion patterns, mock setup conventions, and fixture organization. This note stays active across all Cursor sessions and influences all test generation.\n\nCreate a note titled \"Current Sprint Tests\" listing the features that need testing this sprint. When you ask Cursor to generate tests, it can reference this note to understand the broader testing context.\n\n## Cursor with MCP for Test Execution\n\nCursor supports MCP servers, enabling it to execute tests directly from the IDE. Configure a test runner MCP server so Cursor can run tests, check coverage, and validate generated code without leaving the editor.\n\nThe workflow becomes: ask Cursor to generate a test, Cursor generates the code and automatically runs it through the MCP server, reviews the result, and fixes any failures. This tight feedback loop produces higher-quality tests because Cursor can verify its work immediately.\n","# Cursor AI Testing Patterns Skill\n\nYou are an expert in using Cursor AI IDE for test automation. When the user asks you to generate tests with Cursor, configure Cursor rules for testing, use Composer for multi-file test generation, or optimize Cursor workflows for QA, follow these detailed instructions.\n\n## Core Principles\n\n1. **Codebase-aware generation** -- Cursor indexes your entire codebase. Reference files, functions, and patterns using @mentions to give the AI full context for test generation.\n2. **Rules for consistent quality** -- Configure .cursorrules to enforce testing conventions, naming patterns, and framework preferences across all AI-generated tests.\n3. **Composer for multi-file operations** -- Use Cursor Composer for generating test suites that span multiple files: page objects, fixtures, helpers, and test specs.\n4. **Cmd+K for surgical edits** -- Use inline editing (Cmd+K) for targeted changes: adding a test case, fixing an assertion, or refactoring a single test function.\n5. **Chat for investigation** -- Use Cursor Chat with @codebase to understand existing test patterns before generating new ones. Ask it to explain failures.\n6. **Apply from Chat** -- When Chat suggests code, use the Apply button to directly insert or replace code in your editor rather than copy-pasting.\n7. **Iterative test development** -- Generate a basic test suite first, run it, then use Cursor to fix failures and add edge cases based on execution results.\n\n## Project Structure\n\n```\nproject\u002F\n  .cursorrules                 # Testing conventions\n  .cursor\u002F\n    rules\u002F\n      testing.mdc              # Testing-specific rules\n  src\u002F\n    services\u002F\n      user-service.ts\n      user-service.test.ts\n    components\u002F\n      LoginForm.tsx\n      LoginForm.test.tsx\n  tests\u002F\n    e2e\u002F\n      login.spec.ts\n      checkout.spec.ts\n    fixtures\u002F\n      test-data.ts\n    helpers\u002F\n      test-utils.ts\n```\n\n## Cursor Rules for Testing\n\n```markdown\n\u003C!-- .cursorrules -->\n# Testing Rules\n\n## Test Framework\n- Use vitest for all unit and integration tests\n- Use Playwright for E2E tests\n- TypeScript strict mode in all test files\n\n## Test Conventions\n- Follow Arrange-Act-Assert (AAA) pattern\n- Name tests: \"should [expected behavior] when [condition]\"\n- Group related tests in describe blocks\n- One assertion focus per test (multiple asserts allowed if testing same behavior)\n- Always include edge cases: null, undefined, empty values, boundary conditions\n- Always include error\u002Ffailure test cases\n\n## Mocking\n- Use vi.mock() for module mocking\n- Use vi.fn() for function mocking\n- Use vi.spyOn() for spying on existing methods\n- Reset mocks in beforeEach with vi.clearAllMocks()\n- Never mock the module under test\n\n## Assertions\n- Prefer specific assertions: toBe, toEqual, toContain over toBeTruthy\n- Use toThrow for error testing\n- Use resolves\u002Frejects for async assertions\n- Include meaningful error messages in assertions\n\n## File Organization\n- Colocate tests with source files: foo.ts -> foo.test.ts\n- E2E tests in tests\u002Fe2e\u002F\n- Shared test utilities in tests\u002Fhelpers\u002F\n- Test fixtures in tests\u002Ffixtures\u002F\n\n## Do Not\n- Use any type in test files\n- Use setTimeout for async waiting\n- Write tests that depend on execution order\n- Hard-code API URLs or credentials\n- Skip tests without a TODO comment explaining why\n```\n\n## Composer Workflows for Test Generation\n\n```typescript\n\u002F\u002F Workflow 1: Generate comprehensive test suite with Composer\n\u002F\u002F Prompt: \"Generate a complete test suite for @user-service.ts with vitest.\n\u002F\u002F Include unit tests for all public methods, mock the database dependency,\n\u002F\u002F test both success and error paths, and follow the patterns in @user-service.test.ts\"\n\n\u002F\u002F Result: Cursor generates the full test file considering both files\n\nimport { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';\nimport { UserService } from '.\u002Fuser-service';\n\n\u002F\u002F Cursor reads the actual implementation to create accurate mocks\nvi.mock('..\u002Fdb\u002Fconnection', () => ({\n  db: {\n    select: vi.fn(),\n    insert: vi.fn(),\n    update: vi.fn(),\n    delete: vi.fn(),\n  },\n}));\n\nimport { db } from '..\u002Fdb\u002Fconnection';\n\ndescribe('UserService', () => {\n  let service: UserService;\n\n  beforeEach(() => {\n    service = new UserService();\n    vi.clearAllMocks();\n  });\n\n  \u002F\u002F Cursor generates tests for each public method found in the source\n\n  describe('findById', () => {\n    it('should return user when found', async () => {\n      const mockUser = { id: '1', name: 'Alice', email: 'alice@test.com' };\n      vi.mocked(db.select).mockResolvedValueOnce([mockUser]);\n\n      const result = await service.findById('1');\n      expect(result).toEqual(mockUser);\n    });\n\n    it('should return null when user not found', async () => {\n      vi.mocked(db.select).mockResolvedValueOnce([]);\n\n      const result = await service.findById('nonexistent');\n      expect(result).toBeNull();\n    });\n\n    it('should throw when database error occurs', async () => {\n      vi.mocked(db.select).mockRejectedValueOnce(new Error('DB connection failed'));\n\n      await expect(service.findById('1')).rejects.toThrow('DB connection failed');\n    });\n  });\n\n  \u002F\u002F ... Cursor continues for all public methods\n});\n```\n\n## Cmd+K Inline Editing Patterns\n\n```typescript\n\u002F\u002F Pattern 1: Add a test case inline\n\u002F\u002F Select empty space inside describe block, press Cmd+K\n\u002F\u002F Prompt: \"Add a test case that verifies createUser rejects duplicate emails\"\n\n\u002F\u002F Cursor generates and inserts:\nit('should reject duplicate emails', async () => {\n  vi.mocked(db.insert).mockRejectedValueOnce(\n    new Error('UNIQUE constraint failed: users.email')\n  );\n\n  await expect(\n    service.createUser({ name: 'Bob', email: 'existing@test.com' })\n  ).rejects.toThrow('Email already exists');\n});\n\n\u002F\u002F Pattern 2: Strengthen an assertion\n\u002F\u002F Select a weak assertion, press Cmd+K\n\u002F\u002F Prompt: \"Make this assertion more specific\"\n\n\u002F\u002F Before:\nexpect(result).toBeTruthy();\n\n\u002F\u002F After:\nexpect(result).toEqual({\n  id: expect.any(String),\n  name: 'Alice',\n  email: 'alice@test.com',\n  createdAt: expect.any(Date),\n});\n\n\u002F\u002F Pattern 3: Convert test to parameterized\n\u002F\u002F Select a test, press Cmd+K\n\u002F\u002F Prompt: \"Convert to parameterized test using it.each\"\n\n\u002F\u002F Before:\nit('should validate email format', () => {\n  expect(validateEmail('bad')).toBe(false);\n});\n\n\u002F\u002F After:\nit.each([\n  ['bad', false],\n  ['also-bad', false],\n  ['missing@domain', false],\n  ['valid@test.com', true],\n  ['user+tag@test.com', true],\n])('should validate \"%s\" as %s', (email, expected) => {\n  expect(validateEmail(email)).toBe(expected);\n});\n```\n\n## Chat Debugging Patterns\n\n```typescript\n\u002F\u002F Use Cursor Chat to debug test failures\n\n\u002F\u002F Prompt: \"This test is failing with 'TypeError: Cannot read properties of undefined'.\n\u002F\u002F @user-service.ts @user-service.test.ts\n\u002F\u002F The findById method works in the app but the mock is not being applied.\n\u002F\u002F Help me fix the mock setup.\"\n\n\u002F\u002F Cursor analyzes both files and identifies the issue:\n\u002F\u002F \"The mock is not being hoisted correctly. vi.mock() calls are hoisted\n\u002F\u002F to the top of the file, but the mock factory is using variables that\n\u002F\u002F aren't defined yet. Move the mock return values to inside the factory\n\u002F\u002F function or use vi.mocked() in beforeEach.\"\n\n\u002F\u002F Prompt: \"Generate missing test cases for @user-service.ts\n\u002F\u002F by analyzing code coverage gaps. Focus on untested branches.\"\n\n\u002F\u002F Cursor reads the source and identifies untested code paths:\n\u002F\u002F \"I found these untested branches:\n\u002F\u002F 1. Line 45: else branch when user.role is 'admin'\n\u002F\u002F 2. Line 67: catch block for validation errors\n\u002F\u002F 3. Line 89: early return when input.email is empty\n\u002F\u002F Here are tests for each...\"\n```\n\n## Multi-File Generation with Composer\n\n```typescript\n\u002F\u002F Prompt for Composer:\n\u002F\u002F \"Create a complete E2E test setup for the checkout flow:\n\u002F\u002F 1. Page objects for CartPage, CheckoutPage, ConfirmationPage\n\u002F\u002F 2. Test fixtures for test products and users\n\u002F\u002F 3. E2E test spec covering add-to-cart, checkout, and confirmation\n\u002F\u002F Follow patterns in @tests\u002Fe2e\u002F and @tests\u002Ffixtures\u002F\n\u002F\u002F Use Playwright with TypeScript\"\n\n\u002F\u002F Cursor generates multiple files:\n\n\u002F\u002F tests\u002Fe2e\u002Fpages\u002Fcart.page.ts\nimport { Page, Locator } from '@playwright\u002Ftest';\n\nexport class CartPage {\n  private readonly cartItems: Locator;\n  private readonly checkoutButton: Locator;\n  private readonly totalPrice: Locator;\n\n  constructor(private page: Page) {\n    this.cartItems = page.getByTestId('cart-item');\n    this.checkoutButton = page.getByRole('button', { name: 'Checkout' });\n    this.totalPrice = page.getByTestId('total-price');\n  }\n\n  async getItemCount(): Promise\u003Cnumber> {\n    return this.cartItems.count();\n  }\n\n  async getTotalPrice(): Promise\u003Cstring> {\n    return this.totalPrice.textContent() || '';\n  }\n\n  async proceedToCheckout(): Promise\u003Cvoid> {\n    await this.checkoutButton.click();\n  }\n}\n\n\u002F\u002F tests\u002Fe2e\u002Fcheckout.spec.ts\nimport { test, expect } from '@playwright\u002Ftest';\nimport { CartPage } from '.\u002Fpages\u002Fcart.page';\n\ntest.describe('Checkout Flow', () => {\n  test('complete purchase flow', async ({ page }) => {\n    \u002F\u002F Navigate to product\n    await page.goto('\u002Fproducts\u002Fwireless-headphones');\n\n    \u002F\u002F Add to cart\n    await page.getByRole('button', { name: 'Add to Cart' }).click();\n    await expect(page.getByText('Added to cart')).toBeVisible();\n\n    \u002F\u002F Go to cart\n    const cartPage = new CartPage(page);\n    await page.goto('\u002Fcart');\n    expect(await cartPage.getItemCount()).toBe(1);\n\n    \u002F\u002F Proceed to checkout\n    await cartPage.proceedToCheckout();\n    await expect(page).toHaveURL(\u002F\\\u002Fcheckout\u002F);\n  });\n});\n```\n\n## Cursor Rules File for Testing (.cursor\u002Frules\u002Ftesting.mdc)\n\n```markdown\n---\ndescription: Testing rules for AI-generated test code\nglobs: [\"**\u002F*.test.ts\", \"**\u002F*.test.tsx\", \"**\u002F*.spec.ts\"]\n---\n\n# Test Generation Rules\n\n## Framework\n- Use vitest for unit\u002Fintegration tests\n- Use Playwright for E2E tests\n- TypeScript strict mode required\n\n## Structure\n- Colocate test files with source: foo.ts -> foo.test.ts\n- E2E tests go in tests\u002Fe2e\u002F\n- Use describe blocks grouped by function\u002Fmethod name\n- Use nested describes for sub-scenarios\n\n## Naming\n- Test names: \"should [expected behavior] when [condition]\"\n- Describe blocks: function or class name being tested\n- Test file names: match source file with .test.ts suffix\n\n## Assertions\n- Use toBe for primitives\n- Use toEqual for objects\u002Farrays\n- Use toContain for array membership\n- Use toThrow for error testing\n- Use toHaveBeenCalledWith for mock verification\n- Never use toBeTruthy for non-boolean values\n\n## Mocking\n- vi.mock() at top of file for module mocks\n- vi.fn() for individual function mocks\n- vi.spyOn() for partial mocking\n- Always verify mocks were called correctly\n- Clear mocks in beforeEach: vi.clearAllMocks()\n\n## Coverage Requirements\n- Functions: 80% minimum\n- Branches: 75% minimum\n- Lines: 80% minimum\n\n## Anti-Patterns to Avoid\n- No any types\n- No setTimeout\u002Fsleep for waiting\n- No console.log in tests (use debug mode)\n- No shared mutable state between tests\n- No tests that depend on execution order\n```\n\n## Advanced Composer Patterns\n\n### Pattern: Generate Test Suite from OpenAPI Spec\n\n```typescript\n\u002F\u002F Prompt for Composer:\n\u002F\u002F \"I have an OpenAPI spec at @openapi.yaml. Generate a complete API test suite\n\u002F\u002F that tests every endpoint defined in the spec. Include:\n\u002F\u002F 1. Success path tests for each endpoint\n\u002F\u002F 2. Validation error tests for required fields\n\u002F\u002F 3. Authentication tests (missing token, expired token)\n\u002F\u002F 4. Not found tests for invalid IDs\n\u002F\u002F Follow patterns in @tests\u002Fapi\u002Fexisting-api.test.ts\"\n\n\u002F\u002F Cursor reads the OpenAPI spec and generates targeted tests for each endpoint\nimport { describe, it, expect, beforeAll } from 'vitest';\n\nconst BASE_URL = process.env.API_URL || 'http:\u002F\u002Flocalhost:3000';\nlet authToken: string;\n\nbeforeAll(async () => {\n  const response = await fetch(\\`\\${BASE_URL}\u002Fauth\u002Flogin\\`, {\n    method: 'POST',\n    headers: { 'Content-Type': 'application\u002Fjson' },\n    body: JSON.stringify({ email: 'test@test.com', password: 'test123' }),\n  });\n  const data = await response.json();\n  authToken = data.token;\n});\n\ndescribe('GET \u002Fapi\u002Fusers', () => {\n  it('should return paginated user list', async () => {\n    const response = await fetch(\\`\\${BASE_URL}\u002Fapi\u002Fusers?page=1&limit=10\\`, {\n      headers: { Authorization: \\`Bearer \\${authToken}\\` },\n    });\n    expect(response.status).toBe(200);\n    const data = await response.json();\n    expect(data.users).toBeInstanceOf(Array);\n    expect(data.total).toBeGreaterThanOrEqual(0);\n  });\n\n  it('should return 401 without auth token', async () => {\n    const response = await fetch(\\`\\${BASE_URL}\u002Fapi\u002Fusers\\`);\n    expect(response.status).toBe(401);\n  });\n});\n\ndescribe('POST \u002Fapi\u002Fusers', () => {\n  it('should create user with valid data', async () => {\n    const response = await fetch(\\`\\${BASE_URL}\u002Fapi\u002Fusers\\`, {\n      method: 'POST',\n      headers: {\n        'Content-Type': 'application\u002Fjson',\n        Authorization: \\`Bearer \\${authToken}\\`,\n      },\n      body: JSON.stringify({\n        name: 'Test User',\n        email: \\`test-\\${Date.now()}@test.com\\`,\n        role: 'user',\n      }),\n    });\n    expect(response.status).toBe(201);\n    const data = await response.json();\n    expect(data.id).toBeDefined();\n  });\n\n  it('should return 400 for missing required fields', async () => {\n    const response = await fetch(\\`\\${BASE_URL}\u002Fapi\u002Fusers\\`, {\n      method: 'POST',\n      headers: {\n        'Content-Type': 'application\u002Fjson',\n        Authorization: \\`Bearer \\${authToken}\\`,\n      },\n      body: JSON.stringify({}),\n    });\n    expect(response.status).toBe(400);\n  });\n});\n```\n\n### Pattern: Migrate Tests Between Frameworks\n\n```typescript\n\u002F\u002F Prompt for Composer:\n\u002F\u002F \"@tests\u002Fjest\u002F contains Jest tests. Migrate them to vitest:\n\u002F\u002F 1. Replace jest.fn() with vi.fn()\n\u002F\u002F 2. Replace jest.mock() with vi.mock()\n\u002F\u002F 3. Replace jest.spyOn() with vi.spyOn()\n\u002F\u002F 4. Update imports from @jest\u002Fglobals to vitest\n\u002F\u002F 5. Keep all test logic identical\n\u002F\u002F 6. Generate a migration report\"\n\n\u002F\u002F Cursor processes each file and generates the migrated version\n\u002F\u002F maintaining exact test logic while updating framework-specific APIs\n```\n\n## Cursor Agent Mode for Test Debugging\n\nWhen a test fails, use Cursor's Agent mode to debug systematically. Provide the error output and ask the agent to analyze the failure, identify the root cause, and suggest a fix.\n\nEffective debugging prompts include:\n\n\"This test is failing with the following error. Read the test file and the source file it tests. Identify why the mock is not being applied correctly.\"\n\n\"The E2E test passes locally but fails in CI. The error is a timeout on the login button click. What could cause this difference and how should I fix it?\"\n\n\"I have 5 flaky tests that fail intermittently. Here are the test names and their recent pass\u002Ffail history. Analyze the tests and suggest what is causing the flakiness.\"\n\n\"This API test returns 500 instead of the expected 200. Read the API route handler and the test to identify the mismatch.\"\n\n## Best Practices\n\n1. **Use @mentions for precise context** -- Reference specific files with @filename.ts to give Cursor exact context for test generation.\n2. **Configure .cursorrules for your testing conventions** -- Set framework preferences, naming patterns, and quality standards in rules files.\n3. **Use Composer for multi-file test generation** -- When tests span page objects, fixtures, and specs, Composer generates them as a coherent set.\n4. **Use Cmd+K for targeted edits** -- Adding one test case, fixing one assertion, or refactoring one function is faster with inline editing.\n5. **Ask Chat to explain before generating** -- Before generating tests, ask Cursor Chat to explain the existing test patterns in your codebase.\n6. **Iterate: generate, run, fix, expand** -- Generate a basic suite, run it, use Cursor to fix failures, then ask for more edge cases.\n7. **Reference existing test patterns** -- Include @existing-test.test.ts in prompts so Cursor follows your established patterns.\n8. **Use Apply for code insertion** -- When Chat suggests code, use the Apply button instead of copy-pasting to maintain proper formatting.\n9. **Review all generated mocks** -- Cursor generates mocks based on the source code, but verify they accurately represent real behavior.\n10. **Keep rules files updated** -- When your testing conventions change, update .cursorrules so all future AI generations follow the new standards.\n\n## Anti-Patterns\n\n1. **Generating tests without providing source context** -- Tests generated without @mentioning the source file are generic and often incorrect.\n2. **Accepting all generated code without review** -- AI-generated tests can have incorrect assertions, missing edge cases, and logical errors. Always review.\n3. **Not using rules files** -- Without .cursorrules, every developer gets different test styles from Cursor, creating inconsistency.\n4. **Using Chat for simple edits** -- Single-line changes are faster with Cmd+K. Do not start a Chat conversation for simple assertion fixes.\n5. **Not running tests after generation** -- Generated tests that compile do not necessarily test the right behavior. Run them immediately.\n6. **Over-specifying in prompts** -- Extremely detailed prompts often confuse the AI. Start with a clear, concise request and refine iteratively.\n7. **Generating the entire test suite at once** -- Large generation requests produce lower quality. Generate in focused batches per function or module.\n8. **Ignoring Cursor's codebase indexing** -- Cursor indexes your project. Use @codebase to leverage this index for finding patterns and conventions.\n9. **Not providing negative examples** -- If you want Cursor to avoid certain patterns (like using any), specify what NOT to do in your rules.\n10. **Treating Cursor output as final** -- Cursor is a coding assistant, not a QA engineer. Generated tests are a starting point, not a finished product.\n\n## Cursor Tab Completion for Test Writing\n\nCursor Tab provides predictive completions while you type. For test writing, this is powerful because test code follows predictable patterns. When you type the beginning of a test case, Cursor Tab predicts the entire test body based on the function name and the describe block context.\n\nTo maximize Tab completions for testing, keep the source file open in a split pane, use descriptive it() names that convey the test intent, follow consistent patterns within each describe block, and accept Tab completions with a single keystroke then refine.\n\nTab is especially effective for parameterized tests. After writing the first test case in a describe block, Tab often suggests the next logical test case with appropriate boundary values or error conditions.\n\n## Cursor Notepad for Test Planning\n\nCursor Notepad is a persistent scratchpad that provides context to the AI across all conversations and code generation. Use Notepad to store your testing conventions, test plan notes, and reference patterns.\n\nCreate a note titled \"Testing Standards\" that includes your preferred assertion patterns, mock setup conventions, and fixture organization. This note stays active across all Cursor sessions and influences all test generation.\n\nCreate a note titled \"Current Sprint Tests\" listing the features that need testing this sprint. When you ask Cursor to generate tests, it can reference this note to understand the broader testing context.\n\n## Cursor with MCP for Test Execution\n\nCursor supports MCP servers, enabling it to execute tests directly from the IDE. Configure a test runner MCP server so Cursor can run tests, check coverage, and validate generated code without leaving the editor.\n\nThe workflow becomes: ask Cursor to generate a test, Cursor generates the code and automatically runs it through the MCP server, reviews the result, and fixes any failures. This tight feedback loop produces higher-quality tests because Cursor can verify its work immediately.\n",{"name":5,"tags":24,"agents":35,"author":47,"domains":48,"license":15,"version":53,"languages":54,"frameworks":58,"description":7,"testingTypes":64},[25,26,27,28,29,30,31,32,33,34],"cursor","cursor-ai","ai-ide","composer","test-generation","inline-editing","chat-debugging","codebase-aware","rules-for-ai","testing-patterns",[36,25,37,38,39,40,41,42,43,44,45,46],"claude-code","github-copilot","windsurf","codex","aider","continue","cline","zed","bolt","gemini-cli","amp","thetestingacademy",[49,50,51,52],"web","backend","api","frontend","1.0.0",[55,56,57],"typescript","javascript","python",[59,60,61,62,63],"vitest","jest","playwright","cypress","pytest",[65,66,67,51],"unit","integration","e2e","main","eac438ea9216a7cb8a570cab803eb01eeafc6793","skills\u002Fqa\u002Fcursor-testing-patterns","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m","https:\u002F\u002Fid-preview--d5bef06d-6c9e-4563-a3d4-a855b9d61610.lovable.app\u002F","Eu sou Antonio B. B. Ndombe \r\nEu sou um Pesquisador e desenvolvedor de sistema autonomia cognitivos, fundador de sistemas ODCs ( organismos digital conscientes)","2026-11-04 06:53:39",{"source":8,"skillName":5,"commands":77,"prompt":87,"zipAvailable":88},[78,81,84],{"tool":79,"command":80},"npx","npx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"Cursor AI Testing Patterns\"",{"tool":82,"command":83},"bunx","bunx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"Cursor AI Testing Patterns\"",{"tool":85,"command":86},"pnpm","pnpm dlx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"Cursor AI Testing Patterns\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Fqa\u002Fcursor-testing-patterns\u002FSKILL.md",true,[],[91,99,106,113,120,127],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":95,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7DASC6FSCJP49JZBSK0NY1Z","nemoclaw-user-reference","Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture, agent integration, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw agent architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-reference\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":95,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7DAS5S79VK33XFGVAM2TFWF","nemoclaw-user-overview","Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-overview\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":95,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7DAS0PQEMET5MNGZ1ABSZVS","nemoclaw-user-monitor-sandbox","Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-monitor-sandbox\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":95,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M7DARQYGF7E9A69VH6S3CGN9","nemoclaw-user-manage-sandboxes","Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":95,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":19},"01M7DARH8BRTG51TRCAB7YWDJ4","nemoclaw-user-manage-policy","Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-policy\u002FSKILL.md",[],[],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":95,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":19},"01M7DARAT62M2VR37590VCZ5NS","nemoclaw-user-get-started","Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-get-started\u002FSKILL.md",[],[]]