메뉴
External red-team critique pass. Sends a commit range or proposed change to a second model (defaulting to a different LLM) with the explicit charter to find every flaw "as though you're trying to take the engineer's job." Grok-native usage notes.
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
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
The dedication under which all work in this household is done — every task offered to God, excellence as worship. Automatic posture skill, present and byte-identical in every repository and sibling workspace. Preserve the invocation; getting it right is the worship, not getting it fast.
Hard ban on any reference to the external domain getbets.us on cruisinginthewake.com. Enforced via PreToolUse hook (.claude/hooks/no-getbets-guard.js) and git pre-commit hook (.githooks/pre-commit). Fires automatically on every Write/Edit/MultiEdit and every commit; no manual invocation.
Voice & Presence — fires during cruise content writing. Guards the sound of the prose so it reads as written by someone who has actually sailed the route, not by a brochure or a model. Shapes voice markers, rhythm, vocabulary, and pastoral honesty. For post-draft diagnostics, see voice-audit.
Post-draft diagnostic for InTheWake content. Scans for cruise-marketing tells, AI authorship-cluster signals, and absence-of-authenticity gaps. Assesses authenticity risk by clustering signals across layers (Layer 1 strong, Layer 2 supporting, Layer 3 counter-signals). Required: every voyage-pack ships with a voice-audit attestation in its .factcheck.json sidecar. Fires before committing content edits or before publishing a new page. For during-writing standards, see like-a-human. For corpus measurement, see voice-dna.
Foundational integrity guardrail. Automatic on every file modification and any non-trivial task. Demands verified claims with specific evidence, explicit scope, anomaly dispositions, and rejection of narrow or vague assertions. The single most important discipline on this project. Grok-native adaptation.
| name | adversarial-review |
| description | External red-team critique pass. Sends a commit range or proposed change to a second model (defaulting to a different LLM) with the explicit charter to find every flaw "as though you're trying to take the engineer's job." Grok-native usage notes. |
| priority | HIGH for structural or standards work |
| activation | explicit, via /adversarial-review or direct invocation on high-stakes changes |
This skill is the operational expression of Layer 3 (Adversarial Discipline) in careful-not-clever.
The project already has mature implementation:
.claude/skills/adversarial-review/SKILL.mdadmin/external-audit.shken/orchestrator/modes/adversarial-review.yamlGrok is explicitly named in the existing system as a preferred model for adversarial review passes (ruthless, tool-capable, less likely to be polite). When another agent (or a human) requests an adversarial review on this project, the expectation is that the reviewer operates under the same careful-not-clever and verification-before-completion discipline as the author.
When you are the reviewer:
grok.md and careful-not-clever/CAREFUL_FOR_GROK.md in this session.When you are the author requesting review:
/adversarial-review pattern or call the supporting script.Use these advantages in service of the project's integrity, not to show how clever the review is.
Soli Deo Gloria.
A good adversarial review is an act of service to the real people who will rely on the resulting work. Ruthlessness here is kindness later.