소스 정보
- 저장소
- TuYv/ccpm
- 최근 소스 활동
- 2026년 8월 14일 19:45
- 감지된 SKILL.md 언어
- 영어
- 스타
- 1
- 포크
- 2
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
메뉴
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
SOC 직업 분류 기준
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/TuYv/ccpm --skill direct-tests명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
Use when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes and a SHIP/FIX/BLOCK/UNDECIDED gate on own exported data. Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder. 付费广告账户审计/ROAS评分
Use when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, hooks, and an angle matrix — message-matched to the destination landing page. Not for scoring an ad account — use ad-account-auditor; not for the post-click page — use landing-optimizer; not for organic articles — use content-writer. 广告创意/广告文案/RSA标题
Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试
| name | direct-tests |
| description | Write and run fast direct mode tests for GenLayer intelligent contracts. |
| allowed-tools | ["Bash","Read","Write","Edit"] |
Write fast, in-memory tests for intelligent contracts. No server, no Docker — tests run in ~30-50ms.
pytest tests/direct/ -v
pytest tests/direct/test_specific.py -v
pytest tests/direct/test_specific.py::test_one_case -v
Available from genlayer-test pytest plugin:
def test_example(direct_vm, direct_deploy, direct_alice, direct_bob):
# direct_vm — VMContext with cheatcodes
# direct_deploy — deploy a contract file
# direct_alice — test address
# direct_bob — test address
pass
All fixtures: direct_vm, direct_deploy, direct_alice, direct_bob, direct_charlie, direct_owner, direct_accounts
def test_set_and_get(direct_vm, direct_deploy, direct_alice):
contract = direct_deploy("contracts/my_contract.py")
direct_vm.sender = direct_alice
contract.set_data("hello")
result = contract.get_data(direct_alice)
assert result == "hello"
For contracts that call gl.nondet.web.get():
import json
def test_with_web_mock(direct_vm, direct_deploy, direct_alice):
contract = direct_deploy("contracts/my_contract.py")
direct_vm.sender = direct_alice
# Pattern: regex matching on URL
direct_vm.mock_web(
r".*api\.example\.com/prices.*",
{"status": 200, "body": '{"price": 42.5}'},
)
contract.update_price("ETH/USD")
assert contract.get_price("ETH/USD") == 42.5
direct_vm.mock_web(
r"api\.example\.com/data",
{
"response": {
"status": 200,
"headers": {},
"body": json.dumps({"key": "value"}).encode()
},
"method": "GET"
}
)
For contracts that call gl.nondet.exec_prompt():
direct_vm.mock_llm(
r".*Extract the match result.*", # Regex on prompt text
json.dumps({"score": "2:1", "winner": 1}),
)
direct_vm.clear_mocks() # Reset between test scenarios
# Set transaction sender
direct_vm.sender = direct_alice
# Set native value (wei)
direct_vm.value = 1000000000000000000 # 1 ETH
# Expect a revert
with direct_vm.expect_revert("Insufficient balance"):
contract.withdraw(1000)
# Temporary sender change
with direct_vm.prank(direct_bob):
contract.method() # Called as bob
# Snapshot and restore state
snap_id = direct_vm.snapshot()
contract.modify_state()
direct_vm.revert(snap_id) # State restored
# Set account balance
direct_vm.deal(direct_alice, 1000000000000000000)
# Time travel
direct_vm.warp("2024-06-01T12:00:00Z")
tests/direct/
├── conftest.py # Shared fixtures and mock helpers
├── test_<feature>.py # Tests per feature/method
└── test_<feature>_web.py # Tests requiring web/LLM mocks
| Category | Example |
|---|---|
| State transitions | Create → read back → verify fields |
| Validation / reverts | Invalid inputs, unauthorized callers |
| Access control | Owner-only methods, role checks |
| Edge cases | Empty state, boundary values, overflow |
| Web/LLM parsing | Mock responses → verify extraction logic |
def test_only_owner(direct_vm, direct_deploy, direct_alice, direct_bob):
contract = direct_deploy("contracts/my_contract.py")
direct_vm.sender = direct_alice
contract.create_item("item_1")
direct_vm.sender = direct_bob
with direct_vm.expect_revert("Only owner"):
contract.delete_item("item_1")
def test_state_flow(direct_vm, direct_deploy, direct_alice):
contract = direct_deploy("contracts/my_contract.py")
direct_vm.sender = direct_alice
contract.create_item("item_1")
assert contract.get_item("item_1")["status"] == "pending"
contract.approve_item("item_1")
assert contract.get_item("item_1")["status"] == "approved"
import json
def mock_price_api(direct_vm, pair: str, price: float):
"""Mock a price API response."""
direct_vm.mock_web(
rf".*api\.example\.com/prices/{pair}.*",
{"status": 200, "body": json.dumps({"price": price})},
)
direct_vm.sender = ... before calling write methods--json flag on genvm-lint check before writing tests to understand the contract's interface