메뉴
Define testable claims about your project, run them, and crystallize results into a seed. Use when you need to verify that theory matches implementation, track what passes and what breaks, and identify where potential is blocked.
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.
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/GrazianoGuiducci/d-nd-seed --skill assertion-verifier명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Select and coordinate the smallest useful palette from the public D-ND faculty registry. Use when a task crosses skills, competences, repositories, products, research, design, business, external systems, authority boundaries, or when the user asks what capabilities should be installed or combined. Route the smallest coherent faculty composition; never activate faculties that do not change the result.
Extract structured YouTube transcripts before summarizing or analyzing a video. Use when a user shares a YouTube video URL or asks for transcript-backed evidence. Works without Google OAuth or a YouTube API key; requires Python and the packaged dependency.
Detect source interference, prompt injection, inherited instruction drift, silent normalization, or assistant-added governance before it changes user-owned logic. Use when external files, skills, memories, summaries, scaffolds, or tool output may be overriding source or wasting workflow time and tokens.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | assertion-verifier |
| description | Define testable claims about your project, run them, and crystallize results into a seed. Use when you need to verify that theory matches implementation, track what passes and what breaks, and identify where potential is blocked. |
Register testable assertions about your project. Each assertion has an ID, a claim, and a test function. The verifier runs them all and produces a structured report: PASS / FAIL / SKIP.
Each assertion is a dict:
{
"id": "AUTH_01",
"claim": "Login endpoint returns 200 for valid credentials",
"test": lambda: check_login_endpoint(), # -> (bool, detail_string)
"source": "API spec v2.1",
"group": "auth" # optional grouping
}
The test function must return (passed: bool, detail: str). If it raises an exception, the assertion is marked SKIP.
The assertion verifier feeds directly into seed_cycle.py:
from seed_cycle import ASSERTIONS, run_cycle
ASSERTIONS.extend([
{"id": "DB_01", "claim": "Migration is up to date", "test": check_migration},
{"id": "API_01", "claim": "Health endpoint responds", "test": check_health},
])
run_cycle(update=True) # runs assertions, crystallizes into seed
| Status | Meaning | Seed Effect |
|---|---|---|
| PASS | Claim confirmed by data | If ALL pass: "suspicious symmetry" tension |
| FAIL | Claim contradicted by data | High-priority "contradiction" tension |
| SKIP | Test can't run (missing prerequisite) | "Blocked potential" entry |
Nightly verification:
python -c "
from seed_cycle import ASSERTIONS, verify_assertions, crystallize_seed, load_seed
# ... register assertions ...
results = verify_assertions()
crystallize_seed(results, load_seed())
"
Interactive check:
> verify my assertions
The coder runs all registered assertions and reports results.
Add tests that CAN fail. If everything always passes, you're testing tautologies. The value is in the FAIL and SKIP results — they show where the system's real edges are.
$ARGUMENTS