본문으로 건너뛰기
cccskills
무료GitHub에 공개한국어 소개

kotlin-exposed-patterns

Kotlin과 JetBrains Exposed로 데이터베이스 조회와 추가·수정·삭제를 구현하는 패턴을 제공합니다. 연결 재사용, 구조 변경, 트랜잭션과 테스트도 다룹니다.

원문원문 설명 보기

JetBrains Exposed ORM patterns including DSL queries, DAO pattern, transactions, HikariCP connection pooling, Flyway migrations, and repository pattern. Use when working with the Exposed ORM — DSL or DAO queries, transactions, pooling, or migrations.

연동 도구PostgreSQL
AI 평가80점/ 100설치 방법 보기

이럴 때 유용합니다

  • 데이터베이스 조회와 수정 구현
  • 데이터베이스 연결 재사용 설정
  • 데이터베이스 구조 변경 관리
  • 데이터 접근 분리와 테스트

한국어 소개

할 수 있는 일

kotlin-exposed-patterns는 Kotlin에서 데이터베이스 조회, 추가, 수정, 삭제를 구현하는 패턴을 제공합니다. 데이터베이스 구조와 코드를 연결하는 라이브러리인 JetBrains Exposed를 사용합니다. SQL과 비슷하게 작성하는 DSL과 레코드를 객체로 다루는 DAO를 모두 설명합니다. 테이블 조인, 집계, 페이지 나누기, JSON 열과 여러 작업을 함께 성공하거나 실패하게 하는 트랜잭션도 다룹니다.

이럴 때 유용합니다

Exposed로 데이터 접근 코드를 정리하는 개발자에게 적합합니다. HikariCP 연결 재사용, Flyway 데이터베이스 구조 변경 관리, 비즈니스 로직과 데이터 접근을 분리하는 설계를 참고할 수 있습니다. H2 메모리 데이터베이스를 사용하는 테스트 예제도 있습니다.

사용 예시

  • “Exposed로 사용자 검색과 페이지 나누기를 구현해 주세요.”
  • “HikariCP와 Flyway를 사용하는 연결 설정을 만들어 주세요.”
  • “인터페이스로 데이터 접근을 분리하고 H2로 테스트해 주세요.”

주의 사항

Kotlin과 Exposed 환경을 대상으로 합니다. 자료에는 PostgreSQL 드라이버, HikariCP, Flyway, 테스트용 H2 등의 Gradle 의존성이 제시되어 있습니다. 연결 대상에 맞는 URL, 드라이버, 인증 정보를 설정해야 합니다.

이 소개문은 공개된 SKILL.md를 바탕으로 AI(OpenAI Codex)가 작성했습니다. 정확한 사양은 아래 원문을 확인하세요.

객관 평가

AI가 SKILL.md의 내용만을 근거로 4가지 관점에서 판정했습니다. 스타 수나 인기도는 판정에 넣지 않았습니다.

지시의 명확성언제 쓰고 무엇을 하는지 알 수 있는가
A양호Exposed 쿼리, 연결 풀, 데이터베이스 구조 변경 등 사용 상황과 대상을 명시합니다.
절차의 구체성절차·입출력·예시가 구체적으로 적혀 있는가
A양호연결 설정, 마이그레이션 SQL, 테이블 정의와 조회·수정·삭제 코드 예제가 있습니다.
안전성전송·삭제·명령 실행 등을 명시하고 있는가
B일부 부족시작 시 migrate()와 deleteWhere 예제가 있지만 실행 전 확인 절차는 없습니다.
도입의 용이성필요한 도구나 API 키가 적고 적혀 있는가
B일부 부족연결 URL, 드라이버, 인증 정보 예제는 있지만 제공된 부분에 의존성 설치 절차는 없습니다.

총점은 각 항목을 A=25점, B=15점, C=5점으로 더한 값입니다. 2026년 10월 19일 기준으로 AI(OpenAI Codex)가 판정했습니다. 참고용이므로 설치 전에 원문도 확인해 주세요.

평가가 다르다고 생각되면 재검토를 요청하기

어느 항목이 왜 다르다고 생각하는지 적어 주세요. 로그인은 필요 없습니다. SKILL.md와 대조해 평가를 다시 만들고 이곳에 반영합니다.

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

포함된 파일(1)

  • SKILL.md21.6 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Kotlin Exposed Patterns

Comprehensive patterns for database access with JetBrains Exposed ORM, including DSL queries, DAO, transactions, and production-ready configuration.

When to Use

  • Setting up database access with Exposed
  • Writing SQL queries using Exposed DSL or DAO
  • Configuring connection pooling with HikariCP
  • Creating database migrations with Flyway
  • Implementing the repository pattern with Exposed
  • Handling JSON columns and complex queries

How It Works

Exposed provides two query styles: DSL for direct SQL-like expressions and DAO for entity lifecycle management. HikariCP manages a pool of reusable database connections configured via HikariConfig. Flyway runs versioned SQL migration scripts at startup to keep the schema in sync. All database operations run inside newSuspendedTransaction blocks for coroutine safety and atomicity. The repository pattern wraps Exposed queries behind an interface so business logic stays decoupled from the data layer and tests can use an in-memory H2 database.

Examples

DSL Query

suspend fun findUserById(id: UUID): UserRow? =
    newSuspendedTransaction {
        UsersTable.selectAll()
            .where { UsersTable.id eq id }
            .map { it.toUser() }
            .singleOrNull()
    }

DAO Entity Usage

suspend fun createUser(request: CreateUserRequest): User =
    newSuspendedTransaction {
        UserEntity.new {
            name = request.name
            email = request.email
            role = request.role
        }.toModel()
    }

HikariCP Configuration

val hikariConfig = HikariConfig().apply {
    driverClassName = config.driver
    jdbcUrl = config.url
    username = config.username
    password = config.password
    maximumPoolSize = config.maxPoolSize
    isAutoCommit = false
    transactionIsolation = "TRANSACTION_READ_COMMITTED"
    validate()
}

Database Setup

HikariCP Connection Pooling

// DatabaseFactory.kt
object DatabaseFactory {
    fun create(config: DatabaseConfig): Database {
        val hikariConfig = HikariConfig().apply {
            driverClassName = config.driver
            jdbcUrl = config.url
            username = config.username
            password = config.password
            maximumPoolSize = config.maxPoolSize
            isAutoCommit = false
            transactionIsolation = "TRANSACTION_READ_COMMITTED"
            validate()
        }

        return Database.connect(HikariDataSource(hikariConfig))
    }
}

data class DatabaseConfig(
    val url: String,
    val driver: String = "org.postgresql.Driver",
    val username: String = "",
    val password: String = "",
    val maxPoolSize: Int = 10,
)

Flyway Migrations

// FlywayMigration.kt
fun runMigrations(config: DatabaseConfig) {
    Flyway.configure()
        .dataSource(config.url, config.username, config.password)
        .locations("classpath:db/migration")
        .baselineOnMigrate(true)
        .load()
        .migrate()
}

// Application startup
fun Application.module() {
    val config = DatabaseConfig(
        url = environment.config.property("database.url").getString(),
        username = environment.config.property("database.username").getString(),
        password = environment.config.property("database.password").getString(),
    )
    runMigrations(config)
    val database = DatabaseFactory.create(config)
    // ...
}

Migration Files

-- src/main/resources/db/migration/V1__create_users.sql
CREATE TABLE users (
    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
    name VARCHAR(100) NOT NULL,
    email VARCHAR(255) NOT NULL UNIQUE,
    role VARCHAR(20) NOT NULL DEFAULT 'USER',
    metadata JSONB,
    created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
    updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
);

CREATE INDEX idx_users_email ON users(email);
CREATE INDEX idx_users_role ON users(role);

Table Definitions

DSL Style Tables

// tables/UsersTable.kt
object UsersTable : UUIDTable("users") {
    val name = varchar("name", 100)
    val email = varchar("email", 255).uniqueIndex()
    val role = enumerationByName<Role>("role", 20)
    val metadata = jsonb<UserMetadata>("metadata", Json.Default).nullable()
    val createdAt = timestampWithTimeZone("created_at").defaultExpression(CurrentTimestampWithTimeZone)
    val updatedAt = timestampWithTimeZone("updated_at").defaultExpression(CurrentTimestampWithTimeZone)
}

object OrdersTable : UUIDTable("orders") {
    val userId = uuid("user_id").references(UsersTable.id)
    val status = enumerationByName<OrderStatus>("status", 20)
    val totalAmount = long("total_amount")
    val currency = varchar("currency", 3)
    val createdAt = timestampWithTimeZone("created_at").defaultExpression(CurrentTimestampWithTimeZone)
}

object OrderItemsTable : UUIDTable("order_items") {
    val orderId = uuid("order_id").references(OrdersTable.id, onDelete = ReferenceOption.CASCADE)
    val productId = uuid("product_id")
    val quantity = integer("quantity")
    val unitPrice = long("unit_price")
}

Composite Tables

object UserRolesTable : Table("user_roles") {
    val userId = uuid("user_id").references(UsersTable.id, onDelete = ReferenceOption.CASCADE)
    val roleId = uuid("role_id").references(RolesTable.id, onDelete = ReferenceOption.CASCADE)
    override val primaryKey = PrimaryKey(userId, roleId)
}

DSL Queries

Basic CRUD

// Insert
suspend fun insertUser(name: String, email: String, role: Role): UUID =
    newSuspendedTransaction {
        UsersTable.insertAndGetId {
            it[UsersTable.name] = name
            it[UsersTable.email] = email
            it[UsersTable.role] = role
        }.value
    }

// Select by ID
suspend fun findUserById(id: UUID): UserRow? =
    newSuspendedTransaction {
        UsersTable.selectAll()
            .where { UsersTable.id eq id }
            .map { it.toUser() }
            .singleOrNull()
    }

// Select with conditions
suspend fun findActiveAdmins(): List<UserRow> =
    newSuspendedTransaction {
        UsersTable.selectAll()
            .where { (UsersTable.role eq Role.ADMIN) }
            .orderBy(UsersTable.name)
            .map { it.toUser() }
    }

// Update
suspend fun updateUserEmail(id: UUID, newEmail: String): Boolean =
    newSuspendedTransaction {
        UsersTable.update({ UsersTable.id eq id }) {
            it[email] = newEmail
            it[updatedAt] = CurrentTimestampWithTimeZone
        } > 0
    }

// Delete
suspend fun deleteUser(id: UUID): Boolean =
    newSuspendedTransaction {
        UsersTable.deleteWhere { UsersTable.id eq id } > 0
    }

// Row mapping
private fun ResultRow.toUser() = UserRow(
    id = this[UsersTable.id].value,
    name = this[UsersTable.name],
    email = this[UsersTable.email],
    role = this[UsersTable.role],
    metadata = this[UsersTable.metadata],
    createdAt = this[UsersTable.createdAt],
    updatedAt = this[UsersTable.updatedAt],
)

Advanced Queries

// Join queries
suspend fun findOrdersWithUser(userId: UUID): List<OrderWithUser> =
    newSuspendedTransaction {
        (OrdersTable innerJoin UsersTable)
            .selectAll()
            .where { OrdersTable.userId eq userId }
            .orderBy(OrdersTable.createdAt, SortOrder.DESC)
            .map { row ->
                OrderWithUser(
                    orderId = row[OrdersTable.id].value,
                    status = row[OrdersTable.status],
                    totalAmount = row[OrdersTable.totalAmount],
                    userName = row[UsersTable.name],
                )
            }
    }

// Aggregation
suspend fun countUsersByRole(): Map<Role, Long> =
    newSuspendedTransaction {
        UsersTable
            .select(UsersTable.role, UsersTable.id.count())
            .groupBy(UsersTable.role)
            .associate { row ->
                row[UsersTable.role] to row[UsersTable.id.count()]
            }
    }

// Subqueries
suspend fun findUsersWithOrders(): List<UserRow> =
    newSuspendedTransaction {
        UsersTable.selectAll()
            .where {
                UsersTable.id inSubQuery
                    OrdersTable.select(OrdersTable.userId).withDistinct()
            }
            .map { it.toUser() }
    }

// LIKE and pattern matching — always escape user input to prevent wildcard injection
private fun escapeLikePattern(input: String): String =
    input.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")

suspend fun searchUsers(query: String): List<UserRow> =
    newSuspendedTransaction {
        val sanitized = escapeLikePattern(query.lowercase())
        UsersTable.selectAll()
            .where {
                (UsersTable.name.lowerCase() like "%${sanitized}%") or
                    (UsersTable.email.lowerCase() like "%${sanitized}%")
            }
            .map { it.toUser() }
    }

Pagination

data class Page<T>(
    val data: List<T>,
    val total: Long,
    val page: Int,
    val limit: Int,
) {
    val totalPages: Int get() = ((total + limit - 1) / limit).toInt()
    val hasNext: Boolean get() = page < totalPages
    val hasPrevious: Boolean get() = page > 1
}

suspend fun findUsersPaginated(page: Int, limit: Int): Page<UserRow> =
    newSuspendedTransaction {
        val total = UsersTable.selectAll().count()
        val data = UsersTable.selectAll()
            .orderBy(UsersTable.createdAt, SortOrder.DESC)
            .limit(limit)
            .offset(((page - 1) * limit).toLong())
            .map { it.toUser() }

        Page(data = data, total = total, page = page, limit = limit)
    }

Batch Operations

// Batch insert
suspend fun insertUsers(users: List<CreateUserRequest>): List<UUID> =
    newSuspendedTransaction {
        UsersTable.batchInsert(users) { user ->
            this[UsersTable.name] = user.name
            this[UsersTable.email] = user.email
            this[UsersTable.role] = user.role
        }.map { it[UsersTable.id].value }
    }

// Upsert (insert or update on conflict)
suspend fun upsertUser(id: UUID, name: String, email: String) {
    newSuspendedTransaction {
        UsersTable.upsert(UsersTable.email) {
            it[UsersTable.id] = EntityID(id, UsersTable)
            it[UsersTable.name] = name
            it[UsersTable.email] = email
            it[updatedAt] = CurrentTimestampWithTimeZone
        }
    }
}

DAO Pattern

Entity Definitions

// entities/UserEntity.kt
class UserEntity(id: EntityID<UUID>) : UUIDEntity(id) {
    companion object : UUIDEntityClass<UserEntity>(UsersTable)

    var name by UsersTable.name
    var email by UsersTable.email
    var role by UsersTable.role
    var metadata by UsersTable.metadata
    var createdAt by UsersTable.createdAt
    var updatedAt by UsersTable.updatedAt

    val orders by OrderEntity referrersOn OrdersTable.userId

    fun toModel(): User = User(
        id = id.value,
        name = name,
        email = email,
        role = role,
        metadata = metadata,
        createdAt = createdAt,
        updatedAt = updatedAt,
    )
}

class OrderEntity(id: EntityID<UUID>) : UUIDEntity(id) {
    companion object : UUIDEntityClass<OrderEntity>(OrdersTable)

    var user by UserEntity referencedOn OrdersTable.userId
    var status by OrdersTable.status
    var totalAmount by OrdersTable.totalAmount
    var currency by OrdersTable.currency
    var createdAt by OrdersTable.createdAt

    val items by OrderItemEntity referrersOn OrderItemsTable.orderId
}

DAO Operations

suspend fun findUserByEmail(email: String): User? =
    newSuspendedTransaction {
        UserEntity.find { UsersTable.email eq email }
            .firstOrNull()
            ?.toModel()
    }

suspend fun createUser(request: CreateUserRequest): User =
    newSuspendedTransaction {
        UserEntity.new {
            name = request.name
            email = request.email
            role = request.role
        }.toModel()
    }

suspend fun updateUser(id: UUID, request: UpdateUserRequest): User? =
    newSuspendedTransaction {
        UserEntity.findById(id)?.apply {
            request.name?.let { name = it }
            request.email?.let { email = it }
            updatedAt = OffsetDateTime.now(ZoneOffset.UTC)
        }?.toModel()
    }

Transactions

Suspend Transaction Support

// Good: Use newSuspendedTransaction for coroutine support
suspend fun performDatabaseOperation(): Result<User> =
    runCatching {
        newSuspendedTransaction {
            val user = UserEntity.new {
                name = "Alice"
                email = "alice@example.com"
            }
            // All operations in this block are atomic
            user.toModel()
        }
    }

// Good: Nested transactions with savepoints
suspend fun transferFunds(fromId: UUID, toId: UUID, amount: Long) {
    newSuspendedTransaction {
        val from = UserEntity.findById(fromId) ?: throw NotFoundException("User $fromId not found")
        val to = UserEntity.findById(toId) ?: throw NotFoundException("User $toId not found")

        // Debit
        from.balance -= amount
        // Credit
        to.balance += amount

        // Both succeed or both fail
    }
}

Transaction Isolation

suspend fun readCommittedQuery(): List<User> =
    newSuspendedTransaction(transactionIsolation = Connection.TRANSACTION_READ_COMMITTED) {
        UserEntity.all().map { it.toModel() }
    }

suspend fun serializableOperation() {
    newSuspendedTransaction(transactionIsolation = Connection.TRANSACTION_SERIALIZABLE) {
        // Strictest isolation level for critical operations
    }
}

Repository Pattern

Interface Definition

interface UserRepository {
    suspend fun findById(id: UUID): User?
    suspend fun findByEmail(email: String): User?
    suspend fun findAll(page: Int, limit: Int): Page<User>
    suspend fun search(query: String): List<User>
    suspend fun create(request: CreateUserRequest): User
    suspend fun update(id: UUID, request: UpdateUserRequest): User?
    suspend fun delete(id: UUID): Boolean
    suspend fun count(): Long
}

Exposed Implementation

class ExposedUserRepository(
    private val database: Database,
) : UserRepository {

    override suspend fun findById(id: UUID): User? =
        newSuspendedTransaction(db = database) {
            UsersTable.selectAll()
                .where { UsersTable.id eq id }
                .map { it.toUser() }
                .singleOrNull()
        }

    override suspend fun findByEmail(email: String): User? =
        newSuspendedTransaction(db = database) {
            UsersTable.selectAll()
                .where { UsersTable.email eq email }
                .map { it.toUser() }
                .singleOrNull()
        }

    override suspend fun findAll(page: Int, limit: Int): Page<User> =
        newSuspendedTransaction(db = database) {
            val total = UsersTable.selectAll().count()
            val data = UsersTable.selectAll()
                .orderBy(UsersTable.createdAt, SortOrder.DESC)
                .limit(limit)
                .offset(((page - 1) * limit).toLong())
                .map { it.toUser() }
            Page(data = data, total = total, page = page, limit = limit)
        }

    override suspend fun search(query: String): List<User> =
        newSuspendedTransaction(db = database) {
            val sanitized = escapeLikePattern(query.lowercase())
            UsersTable.selectAll()
                .where {
                    (UsersTable.name.lowerCase() like "%${sanitized}%") or
                        (UsersTable.email.lowerCase() like "%${sanitized}%")
                }
                .orderBy(UsersTable.name)
                .map { it.toUser() }
        }

    override suspend fun create(request: CreateUserRequest): User =
        newSuspendedTransaction(db = database) {
            UsersTable.insert {
                it[name] = request.name
                it[email] = request.email
                it[role] = request.role
            }.resultedValues!!.first().toUser()
        }

    override suspend fun update(id: UUID, request: UpdateUserRequest): User? =
        newSuspendedTransaction(db = database) {
            val updated = UsersTable.update({ UsersTable.id eq id }) {
                request.name?.let { name -> it[UsersTable.name] = name }
                request.email?.let { email -> it[UsersTable.email] = email }
                it[updatedAt] = CurrentTimestampWithTimeZone
            }
            if (updated > 0) findById(id) else null
        }

    override suspend fun delete(id: UUID): Boolean =
        newSuspendedTransaction(db = database) {
            UsersTable.deleteWhere { UsersTable.id eq id } > 0
        }

    override suspend fun count(): Long =
        newSuspendedTransaction(db = database) {
            UsersTable.selectAll().count()
        }

    private fun ResultRow.toUser() = User(
        id = this[UsersTable.id].value,
        name = this[UsersTable.name],
        email = this[UsersTable.email],
        role = this[UsersTable.role],
        metadata = this[UsersTable.metadata],
        createdAt = this[UsersTable.createdAt],
        updatedAt = this[UsersTable.updatedAt],
    )
}

JSON Columns

JSONB with kotlinx.serialization

// Custom column type for JSONB
inline fun <reified T : Any> Table.jsonb(
    name: String,
    json: Json,
): Column<T> = registerColumn(name, object : ColumnType<T>() {
    override fun sqlType() = "JSONB"

    override fun valueFromDB(value: Any): T = when (value) {
        is String -> json.decodeFromString(value)
        is PGobject -> {
            val jsonString = value.value
                ?: throw IllegalArgumentException("PGobject value is null for column '$name'")
            json.decodeFromString(jsonString)
        }
        else -> throw IllegalArgumentException("Unexpected value: $value")
    }

    override fun notNullValueToDB(value: T): Any =
        PGobject().apply {
            type = "jsonb"
            this.value = json.encodeToString(value)
        }
})

// Usage in table
@Serializable
data class UserMetadata(
    val preferences: Map<String, String> = emptyMap(),
    val tags: List<String> = emptyList(),
)

object UsersTable : UUIDTable("users") {
    val metadata = jsonb<UserMetadata>("metadata", Json.Default).nullable()
}

Testing with Exposed

In-Memory Database for Tests

class UserRepositoryTest : FunSpec({
    lateinit var database: Database
    lateinit var repository: UserRepository

    beforeSpec {
        database = Database.connect(
            url = "jdbc:h2:mem:test;DB_CLOSE_DELAY=-1;MODE=PostgreSQL",
            driver = "org.h2.Driver",
        )
        transaction(database) {
            SchemaUtils.create(UsersTable)
        }
        repository = ExposedUserRepository(database)
    }

    beforeTest {
        transaction(database) {
            UsersTable.deleteAll()
        }
    }

    test("create and find user") {
        val user = repository.create(CreateUserRequest("Alice", "alice@example.com"))

        user.name shouldBe "Alice"
        user.email shouldBe "alice@example.com"

        val found = repository.findById(user.id)
        found shouldBe user
    }

    test("findByEmail returns null for unknown email") {
        val result = repository.findByEmail("unknown@example.com")
        result.shouldBeNull()
    }

    test("pagination works correctly") {
        repeat(25) { i ->
            repository.create(CreateUserRequest("User $i", "user$i@example.com"))
        }

        val page1 = repository.findAll(page = 1, limit = 10)
        page1.data shouldHaveSize 10
        page1.total shouldBe 25
        page1.hasNext shouldBe true

        val page3 = repository.findAll(page = 3, limit = 10)
        page3.data shouldHaveSize 5
        page3.hasNext shouldBe false
    }
})

Gradle Dependencies

// build.gradle.kts
dependencies {
    // Exposed
    implementation("org.jetbrains.exposed:exposed-core:1.0.0")
    implementation("org.jetbrains.exposed:exposed-dao:1.0.0")
    implementation("org.jetbrains.exposed:exposed-jdbc:1.0.0")
    implementation("org.jetbrains.exposed:exposed-kotlin-datetime:1.0.0")
    implementation("org.jetbrains.exposed:exposed-json:1.0.0")

    // Database driver
    implementation("org.postgresql:postgresql:42.7.5")

    // Connection pooling
    implementation("com.zaxxer:HikariCP:6.2.1")

    // Migrations
    implementation("org.flywaydb:flyway-core:10.22.0")
    implementation("org.flywaydb:flyway-database-postgresql:10.22.0")

    // Testing
    testImplementation("com.h2database:h2:2.3.232")
}

Quick Reference: Exposed Patterns

PatternDescription
object Table : UUIDTable("name")Define table with UUID primary key
newSuspendedTransaction { }Coroutine-safe transaction block
Table.selectAll().where { }Query with conditions
Table.insertAndGetId { }Insert and return generated ID
Table.update({ condition }) { }Update matching rows
Table.deleteWhere { }Delete matching rows
Table.batchInsert(items) { }Efficient bulk insert
innerJoin / leftJoinJoin tables
orderBy / limit / offsetSort and paginate
count() / sum() / avg()Aggregation functions

Remember: Use the DSL style for simple queries and the DAO style when you need entity lifecycle management. Always use newSuspendedTransaction for coroutine support, and wrap database operations behind a repository interface for testability.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Design and audit interfaces for Web, iOS, and Android using WCAG 2.2 accessibility guidance. Check screen-reader labels, keyboard navigation, contrast, and control sizes to identify barriers and guide implementation for people using assistive technology.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Adding descriptive labels to icon-only buttons
  • Reviewing keyboard navigation and modal focus
  • Checking contrast and control sizes
affaan-m/ECC28.3만2026년 10월 16일 업데이트

Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Investigating failures that appear only inside an agent application
  • Tracing old conversation content leaking into new sessions
  • Checking skipped or falsely claimed tool execution
affaan-m/ECC28.3만2026년 10월 16일 업데이트

Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Comparing coding agents on real development tasks
  • Evaluating a new tool or model before adoption
  • Checking performance after agent updates
affaan-m/ECC28.3만2026년 10월 16일 업데이트

Design and refine an AI agent’s available actions, tool inputs, and result formats. Define recovery steps for errors, manage the information kept in context, and evaluate changes through completion rates, retries, and cost per successful task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Define an AI agent’s tool set and input formats
  • Make tool results and next steps easier to interpret
  • Specify safe retries and stopping conditions
affaan-m/ECC28.3만2026년 10월 16일 업데이트

Diagnose failed AI agent runs by capturing errors, checking likely causes, and choosing small, reversible recovery actions. The workflow produces a structured report of the failure, recovery steps, and evidence, helping explain repeated retries or stalled progress.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Diagnosing repeated tool calls with no progress
  • Investigating quality loss as context grows
  • Checking file paths and environment mismatches
affaan-m/ECC28.3만2026년 10월 16일 업데이트

Diagnose AI agent runs that fail repeatedly, loop through tools, or lose track of the task. Capture errors and environment details, test a focused recovery action, and produce a report explaining the evidence and outcome.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Diagnosing repeated failures in an agent run
  • Investigating loops through the same tool calls
  • Reviewing output degradation as context grows
affaan-m/ECC28.3만2026년 10월 5일 업데이트

affaan-m의 스킬 모두 보기

이 스킬의 문제 신고