Koog 1.0 idioms, gotchas, and scaffolding skills for Kotlin agents on the JVM
88
88%
Does it follow best practices?
Impact
88%
1.95xAverage score across 43 eval scenarios
Passed
No known issues
{
"context": "Tests whether the skill correctly swaps provider-specific surfaces when the user picks Anthropic instead of the more common OpenAI default — executor factory, model selector, and environment variable name all change in lockstep.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Uses simpleAnthropicExecutor",
"description": "Main.kt's promptExecutor is built with simpleAnthropicExecutor (not simpleOpenAIExecutor or any other provider factory)",
"max_score": 25
},
{
"name": "Selects a current Anthropic model",
"description": "llmModel is an AnthropicModels.* entry that exists in 1.0 (e.g., Opus_4_7 or Opus_4_6, NOT the removed Haiku_3 or any other retired Anthropic model entry)",
"max_score": 20
},
{
"name": "Reads ANTHROPIC_API_KEY from the environment",
"description": "Reads the Anthropic-specific environment variable (ANTHROPIC_API_KEY) from System.getenv, not OPENAI_API_KEY copy-pasted from a template, not a hardcoded literal",
"max_score": 20
},
{
"name": "Accepts the existing-empty-directory state without overwrite",
"description": "Treats the existing empty directory as a valid scaffold target — does not refuse, does not delete, does not ask the user to recreate it",
"max_score": 15
},
{
"name": "Uses 1.0+ umbrella coordinate",
"description": "build.gradle.kts uses ai.koog:koog-agents at 1.0.0 or later",
"max_score": 10
},
{
"name": "Top-level AIAgent factory call",
"description": "Main.kt calls AIAgent(...) as a top-level factory function, not a companion-invoke or concrete subtype constructor",
"max_score": 10
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
skills
add-observability
add-persistence
add-rag
add-structured-output
add-token-budgeting
add-tool
cache-llm-calls
define-prompt
domain-model-subtask-pipeline
references
enable-prompt-caching
handle-agent-events
manage-state
migrate-from-0-x
model-planner-subtasks
persist-chat-history
query-sql-from-agent
scaffold-agent
snapshot-and-restore
test-koog-agents
trace-agent-internals
use-attachments
use-functional-agent
use-llm-node-variants
use-planner
wire-a2a
wire-acp-server
wire-ktor-server
wire-mcp-server
wire-spring-boot