菜单
Build trustworthy A/B-test plumbing: deterministic sticky assignment, exposure logging (who actually saw the variant), Sample-Ratio-Mismatch checks before reading results, pre-registered metric/MDE/duration, and guardrail metrics — leaving significance to applied-statistics.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mcorbett51090/RavenClaude --skill ab-test-plumbing命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Route everyday, well-defined work (single-file edits, test-writing, summarization, mechanical refactors, boilerplate) to a cheaper coding agent (Grok or Copilot CLI) instead of doing it in the main Claude session, escalating multi-file/architecture/debugging/security work to Claude. Opt-in via the `cheap_lane:` comfort-posture knob.
Authors, validates and packages a claude.ai Organization Skill — the intake questions, the trigger and scope exercises, then lint, pack and verify against measured platform constraints. Reach for this when someone wants to publish a Skill to their organization, or when an upload was rejected and the reason is unclear.
Drafts a reply to an inbound customer email, grounded in the account record and the published help-centre articles rather than in recall. Use when a customer emails about billing, a renewal or an outage, when a reply must cite current policy, or when a teammate asks for a first draft to edit.
基于 SOC 职业分类
正在显示 SKILL.md
| name | ab-test-plumbing |
| description | Build trustworthy A/B-test plumbing: deterministic sticky assignment, exposure logging (who actually saw the variant), Sample-Ratio-Mismatch checks before reading results, pre-registered metric/MDE/duration, and guardrail metrics — leaving significance to applied-statistics. |
Primary metric, MDE, duration, guardrails — set before start. No peeking-to-stop, no HARKing.
A winning primary metric that tanks latency/errors/revenue is not a win.
Deliver clean exposure + metric data; significance is applied-statistics'.