go-test

Command View source on GitHub

Enforce TDD workflow for Go. Write table-driven tests first, then implement. Verify 80%+ coverage with go test -cover.

Go TDD Command

This command enforces test-driven development methodology for Go code using idiomatic Go testing patterns.

What This Command Does

Define Types/Interfaces: Scaffold function signatures first
Write Table-Driven Tests: Create comprehensive test cases (RED)
Run Tests: Verify tests fail for the right reason
Implement Code: Write minimal code to pass (GREEN)
Refactor: Improve while keeping tests green
Check Coverage: Ensure 80%+ coverage

When to Use

Use /go-test when:

Implementing new Go functions
Adding test coverage to existing code
Fixing bugs (write failing test first)
Building critical business logic
Learning TDD workflow in Go

TDD Cycle

RED     → Write failing table-driven test
GREEN   → Implement minimal code to pass
REFACTOR → Improve code, tests stay green
REPEAT  → Next test case

Example Session

User: /go-test I need a function to validate email addresses

Agent:
# TDD Session: Email Validator

## Step 1: Define Interface

```go
// validator/email.go
package validator

// ValidateEmail checks if the given string is a valid email address.
// Returns nil if valid, error describing the issue otherwise.
func ValidateEmail(email string) error {
    panic("not implemented")
}
```

## Step 2: Write Table-Driven Tests (RED)

```go
// validator/email_test.go
package validator

import (
    "testing"
)

func TestValidateEmail(t *testing.T) {
    tests := []struct {
        name    string
        email   string
        wantErr bool
    }{
        // Valid emails
        {"simple email", "user@example.com", false},
        {"with subdomain", "user@mail.example.com", false},
        {"with plus", "user+tag@example.com", false},
        {"with dots", "first.last@example.com", false},

        // Invalid emails
        {"empty string", "", true},
        {"no at sign", "userexample.com", true},
        {"no domain", "user@", true},
        {"no local part", "@example.com", true},
        {"double at", "user@@example.com", true},
        {"spaces", "user @example.com", true},
        {"no tld", "user@example", true},
    }

    for _, tt := range tests {
        t.Run(tt.name, func(t *testing.T) {
            err := ValidateEmail(tt.email)
            if tt.wantErr && err == nil {
                t.Errorf("ValidateEmail(%q) = nil; want error", tt.email)
            }
            if !tt.wantErr && err != nil {
                t.Errorf("ValidateEmail(%q) = %v; want nil", tt.email, err)
            }
        })
    }
}
```

## Step 3: Run Tests - Verify FAIL

```bash
$ go test ./validator/...

--- FAIL: TestValidateEmail (0.00s)
    --- FAIL: TestValidateEmail/simple_email (0.00s)
        panic: not implemented

FAIL
```

✓ Tests fail as expected (panic).

## Step 4: Implement Minimal Code (GREEN)

```go
// validator/email.go
package validator

import (
    "errors"
    "regexp"
)

var emailRegex = regexp.MustCompile(`^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$`)

var (
    ErrEmailEmpty   = errors.New("email cannot be empty")
    ErrEmailInvalid = errors.New("email format is invalid")
)

func ValidateEmail(email string) error {
    if email == "" {
        return ErrEmailEmpty
    }
    if !emailRegex.MatchString(email) {
        return ErrEmailInvalid
    }
    return nil
}
```

## Step 5: Run Tests - Verify PASS

```bash
$ go test ./validator/...

PASS
ok      project/validator    0.003s
```

✓ All tests passing!

## Step 6: Check Coverage

```bash
$ go test -cover ./validator/...

PASS
coverage: 100.0% of statements
ok      project/validator    0.003s
```

✓ Coverage: 100%

## TDD Complete!

Test Patterns

Table-Driven Tests

tests := []struct {
    name     string
    input    InputType
    want     OutputType
    wantErr  bool
}{
    {"case 1", input1, want1, false},
    {"case 2", input2, want2, true},
}

for _, tt := range tests {
    t.Run(tt.name, func(t *testing.T) {
        got, err := Function(tt.input)
        // assertions
    })
}

Parallel Tests

for _, tt := range tests {
    tt := tt // Capture
    t.Run(tt.name, func(t *testing.T) {
        t.Parallel()
        // test body
    })
}

Test Helpers

func setupTestDB(t *testing.T) *sql.DB {
    t.Helper()
    db := createDB()
    t.Cleanup(func() { db.Close() })
    return db
}

Coverage Commands

# Basic coverage
go test -cover ./...

# Coverage profile
go test -coverprofile=coverage.out ./...

# View in browser
go tool cover -html=coverage.out

# Coverage by function
go tool cover -func=coverage.out

# With race detection
go test -race -cover ./...

Coverage Targets

Code Type	Target
Critical business logic	100%
Public APIs	90%+
General code	80%+
Generated code	Exclude

TDD Best Practices

DO:

Write test FIRST, before any implementation
Run tests after each change
Use table-driven tests for comprehensive coverage
Test behavior, not implementation details
Include edge cases (empty, nil, max values)

DON’T:

Write implementation before tests
Skip the RED phase
Test private functions directly
Use time.Sleep in tests
Ignore flaky tests

/go-build - Fix build errors
/go-review - Review code after implementation
verification-loop skill - Run full verification loop

Skill: skills/golang-testing/
Skill: skills/tdd-workflow/

← Back to Commands