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.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Business, outreach and public-relations manager for AI projects and technical teams. Use when an agent must turn a collaboration opportunity, partner request, portfolio update, public claim, outreach message, follow-up, sponsorship path or service proposal into a bounded decision, safe communication package and tracked next action without sending or publishing autonomously.
Deploy paper content from configured site_ready files to d-nd.com VPS. Handles md-to-HTML conversion, bilingual merge, figure path resolution, and pages.json update.
Five mechanical gates for any content publish pipeline with CMS + rendering layers. Prevents false security: 'API returned 200' does not mean 'visitor sees clean content'. Use when writing content to a multi-layer serving system (CMS API, static files, prerendered HTML, cached copies).
Multi-node consultation protocol for high-leverage decisions. Dispatches the same question to N independent LLM/agent nodes in isolation, then synthesizes their responses into a summa that exposes convergence (high-confidence claims), dissensus (real uncertainty zones), and emergent points (insights no single node produced). Reduces single-node training bias. Supports recursive escalation for stable-state convergence. Use for decisions that propagate via A14 cascade — seed updates, crystallizations, advisory→mechanical promotions, high-visibility copy, lab result interpretation.
Closure reflection protocol. After a significant work block concludes (feature shipped, session ending, major commit landed, cross-node coordination resolved), runs a 10-question interview that extracts meaning, impact, and next questions — then emits multiple audience-specific artifacts (changelog, external editorial, AI integration docs, memory crystal, backlog seed). Turns implicit maturation into explicit narrative. Use at the end of meaningful work, not after trivial edits.
Pre-commit check for public-facing copy (knowledge base definitions, page content, docs). Detects apologetic hedging — phrases that declare 'degrees of truth' (possible/necessary, current/future, one-of-many/the) and open a dualistic framing the model transcends. Use when drafting or reviewing any copy that describes the model, its transductions, or its tools.
| 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