菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
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.
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 | no-getbets |
| description | 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. |
| version | 1.0.0 |
The string getbets (case-insensitive) must never appear in any production-facing file on cruisinginthewake.com. This includes the published domain, any path served to users, and any source file that compiles to a served path.
No exceptions for disclaimers, "not affiliated with" notices, comparison tables, or any other framing. The ban is absolute on production surfaces.
getbets.us is an external US online-casino review/affiliate site, flagged as suspect by Scam Detector (reference). It has no legitimate connection to cruise content and no public web page genuinely pairs the two domains.
On 2026-05-28, AI grounding analytics surfaced 226 LLM citations on the queries casino royale royal caribbean getbets.us (196) and casino royale royal caribbean getbets (30). The site's own restaurants/casino.html was clean — zero references. The pattern was identified as one of:
The diagnosis: adversarial co-mention, not organic demand. Any defensive reference to getbets.us added to this site — including a disclaimer — would strengthen the SEO pairing the adversary is trying to create. The right defense is structural absence.
Documentation about the ban itself, and the private admin tooling that defends against it, are the only legitimate contexts for the string getbets in this repo. The following paths are exempt:
.claude/skills/no-getbets/** (this skill).claude/hooks/no-getbets-* (the enforcement hook).claude/standards/no-getbets* (any future standard entry).githooks/pre-commit (the git enforcement)CLAUDE.md, SKILLS.md, AGENT.md (rule discoverability)audit-reports/** (investigation artifacts)admin/check-no-getbets* (any admin tooling for the check)admin/seo/** (Search Console disavow files and related defensive SEO artifacts — never served)The exempt list is duplicated in .claude/hooks/no-getbets-guard.js (EXEMPT_PATH_PATTERNS) and .githooks/pre-commit (path-filter grep). Any new exemption must be added in both places.
| Layer | Where | When it fires | Behavior on hit |
|---|---|---|---|
| Claude Code PreToolUse hook | .claude/hooks/no-getbets-guard.js | Every Write / Edit / MultiEdit | Denies the tool call with a denial reason |
| Git pre-commit hook | .githooks/pre-commit | Every git commit | Blocks the commit with the list of offending files |
| This skill | .claude/skills/no-getbets/SKILL.md | Discovered at session start | Documents the rule and rationale for human + agent readers |
| Cognitive memory | inthewake scope, protected | Semantic recall in any session | Returns the rule when sessions search for related terms |
| Top-level policy | CLAUDE.md "Hard bans" section | Every session reads at start | Declarative rule before any work begins |
getbets to any production file. No disclaimer, no comparison, no defensive notice.EXEMPT_PATH_PATTERNS in .claude/hooks/no-getbets-guard.js AND to the path filter in .githooks/pre-commit. Both must agree.--no-verify for any commit touching production files. The bypass is reserved for cases where the documentation paths themselves are being edited.To confirm the ban is intact across the codebase:
grep -rli 'getbets' \
--exclude-dir=.git \
--exclude-dir=node_modules \
--exclude-dir=audit-reports \
--exclude-dir=.claude/skills/no-getbets \
--exclude=.claude/hooks/no-getbets-guard.js \
--exclude=.githooks/pre-commit \
--exclude=CLAUDE.md \
--exclude=SKILLS.md \
.
A clean run produces no output. Any hit is either a violation or a legitimate documentation file that needs adding to the exempt list.
.claude/hooks/no-getbets-guard.js — Claude Code PreToolUse enforcement.githooks/pre-commit — git commit enforcement (check #5)CLAUDE.md — top-level policy declarationSKILLS.md — skill index registrationinthewake scope — protected entryDefense is structural absence, not defensive presence. The string never appears, so no SEO signal can form.