test-generator

仓库: ovachiever/droid-tings
安装量: 38
排名: #18615

安装

npx skills add https://github.com/oimiragieo/agent-studio --skill test-generator
Mode: Cognitive/Prompt-Driven
— No standalone utility script; use via agent context.
Step 1: Identify Test Type
Determine what type of test is needed:
Unit Test
Component/function testing
Integration Test
Service/API integration
E2E Test
Full user flow testing
API Test
Endpoint testing
Step 2: Analyze Target Code
Examine code to test (Use Parallel Read/Grep/Glob):
Read component/function code
Identify test cases
Understand dependencies
Note edge cases
Step 3: Analyze Test Patterns
Review existing tests:
Read similar test files
Identify testing patterns
Note testing framework usage
Understand mocking strategies
Step 4: Generate Test Code
Create test following patterns:
Use appropriate testing framework
Follow project conventions
Include comprehensive coverage
Add edge cases and error scenarios
Step 5: Coverage Analysis
After generating tests, analyze coverage:
Check that generated tests cover all requirements
:
Verify all functions/methods are tested
Check all branches are covered (if/else, switch, etc.)
Ensure all edge cases are tested
Validate error scenarios are covered
Validate tests are runnable
:
Check test syntax is valid
Verify imports are correct
Ensure test framework is properly configured
Validate test setup/teardown is correct
Report coverage percentage
:
Calculate line coverage (if possible)
Calculate branch coverage (if possible)
Report uncovered code paths
Suggest additional tests for uncovered areas
Coverage Validation Checklist
:
All public functions/methods have tests
All error paths are tested
All edge cases are covered
Tests are syntactically valid
Tests can be executed successfully
Coverage meets project thresholds (if defined)
import
{
render
,
screen
,
waitFor
}
from
'@testing-library/react'
import
{
describe
,
it
,
expect
,
vi
}
from
'vitest'
import
{
UserProfile
}
from
'./user-profile'
describe
(
'UserProfile'
,
(
)
=>
{
it
(
'renders user information'
,
async
(
)
=>
{
const
mockUser
=
{
id
:
'1'
,
name
:
'John'
,
email
:
'john@example.com'
}
render
(
<
UserProfile user
=
{
mockUser
}
/
>
)
await
waitFor
(
(
)
=>
{
expect
(
screen
.
getByText
(
'John'
)
)
.
toBeInTheDocument
(
)
expect
(
screen
.
getByText
(
'john@example.com'
)
)
.
toBeInTheDocument
(
)
}
)
}
)
it
(
'handles loading state'
,
(
)
=>
{
render
(
<
UserProfile user
=
{
null
}
loading
/
>
)
expect
(
screen
.
getByTestId
(
'loading'
)
)
.
toBeInTheDocument
(
)
}
)
it
(
'handles error state'
,
(
)
=>
{
render
(
<
UserProfile user
=
{
null
}
error
=
"Failed to load"
/
>
)
expect
(
screen
.
getByText
(
'Failed to load'
)
)
.
toBeInTheDocument
(
)
}
)
}
)
Integration Test (API)
import
{
describe
,
it
,
expect
,
beforeAll
,
afterAll
}
from
'vitest'
;
import
{
createTestClient
}
from
'./test-client'
;
describe
(
'Users API'
,
(
)
=>
{
let
client
:
TestClient
;
beforeAll
(
(
)
=>
{
client
=
createTestClient
(
)
;
}
)
;
afterAll
(
async
(
)
=>
{
await
client
.
cleanup
(
)
;
}
)
;
it
(
'creates a user'
,
async
(
)
=>
{
const
response
=
await
client
.
post
(
'/api/users'
,
{
email
:
'test@example.com'
,
name
:
'Test User'
,
}
)
;
expect
(
response
.
status
)
.
toBe
(
201
)
;
expect
(
response
.
data
)
.
toHaveProperty
(
'id'
)
;
expect
(
response
.
data
.
email
)
.
toBe
(
'test@example.com'
)
;
}
)
;
it
(
'validates required fields'
,
async
(
)
=>
{
const
response
=
await
client
.
post
(
'/api/users'
,
{
}
)
;
expect
(
response
.
status
)
.
toBe
(
400
)
;
expect
(
response
.
data
)
.
toHaveProperty
(
'errors'
)
;
}
)
;
}
)
;
E2E Test (Cypress)
describe
(
'User Authentication Flow'
,
(
)
=>
{
beforeEach
(
(
)
=>
{
cy
.
visit
(
'/login'
)
;
}
)
;
it
(
'allows user to login'
,
(
)
=>
{
cy
.
get
(
'[data-testid="email-input"]'
)
.
type
(
'user@example.com'
)
;
cy
.
get
(
'[data-testid="password-input"]'
)
.
type
(
'password123'
)
;
cy
.
get
(
'[data-testid="login-button"]'
)
.
click
(
)
;
cy
.
url
(
)
.
should
(
'include'
,
'/dashboard'
)
;
cy
.
get
(
'[data-testid="user-menu"]'
)
.
should
(
'be.visible'
)
;
}
)
;
it
(
'shows error for invalid credentials'
,
(
)
=>
{
cy
.
get
(
'[data-testid="email-input"]'
)
.
type
(
'invalid@example.com'
)
;
cy
.
get
(
'[data-testid="password-input"]'
)
.
type
(
'wrong'
)
;
cy
.
get
(
'[data-testid="login-button"]'
)
.
click
(
)
;
cy
.
get
(
'[data-testid="error-message"]'
)
.
should
(
'be.visible'
)
.
and
(
'contain'
,
'Invalid credentials'
)
;
}
)
;
}
)
;
Integration with QA Agent
:
Creates comprehensive test suites
Generates test plans
Validates test quality
Follow Patterns
Match existing test structure
Comprehensive Coverage
Test happy paths and edge cases
Clear Test Names
Descriptive test descriptions
Isolate Tests
Each test should be independent
Mock Dependencies
Use appropriate mocking strategies

Generate tests for a file

node .claude/skills/test-generator/scripts/main.cjs src/components/UserProfile.tsx

The tool will analyze the file and generate appropriate tests

Iron Laws ALWAYS analyze existing test patterns and framework conventions before generating any test code NEVER generate tests that inspect implementation details — test only public behavior and outputs ALWAYS include edge cases: null/undefined inputs, boundary values, and error scenarios for every tested unit NEVER produce tests with shared mutable state — use beforeEach/afterEach to isolate every test ALWAYS verify generated tests are syntactically valid and runnable before marking generation complete Anti-Patterns Anti-Pattern Why It Fails Correct Approach Testing implementation details Breaks on refactor even when behavior is unchanged Test public API behavior and observable outputs No assertions in test body Test always passes, catches nothing Add explicit assertions for every test case Shared mutable state between tests Tests fail depending on execution order Use beforeEach/afterEach for full isolation Magic numbers in assertions Unclear expected values, brittle tests Use named constants or descriptive fixture data Missing error path tests Half coverage, silent failures in production Test both success and failure scenarios Memory Protocol (MANDATORY) Before starting: Read .claude/context/memory/learnings.md After completing: New pattern -> .claude/context/memory/learnings.md Issue found -> .claude/context/memory/issues.md Decision made -> .claude/context/memory/decisions.md ASSUME INTERRUPTION: If it's not in memory, it didn't happen.

← 返回排行榜