AGENT SKILL

experiment-readout

假设 + 指标 + 结果 + 解释 + 决策, 把 A/B 或产品实验转成行动建议

License 许可
MIT
最近更新
2026-11-14
Stars
★ 1.1k
Forks
104

01 前言 Front Matter

od
{ "mode": "prototype", "craft": { "requires": [ "typography", "typography-hierarchy", "color", "anti-ai-slop" ] }, "preview": { "type": "html", "entry": "index.html" }, "platform": "desktop", "scenario": "product", "upstream": "https://github.com/nexu-io/html-anything/tree/553ed98c283f9c0f489902d035416a972d6a9699/next/src/lib/templates/skills/experiment-readout", "design_system": { "requires": false }, "example_prompt": "Turn this A/B test data into an experiment readout: hypothesis, primary and guardrail metrics, results with confidence, interpretation, and a ship / stop / iterate decision." }
name
experiment-readout
tags
[ "experiment", "ab-test", "growth", "product", "data", "实验", "复盘" ]
emoji
🧪
en_name
Experiment Readout
zh_name
实验复盘
category
data
scenario
product
example_id
sample-experiment-readout
aspect_hint
产品实验报告
description
假设 + 指标 + 结果 + 解释 + 决策, 把 A/B 或产品实验转成行动建议
example_desc
把实验假设、样本、指标和结果转成产品决策报告。
example_name
实验复盘 · Onboarding Checklist
en_description
Hypothesis, metrics, results, interpretation and decision: turns an A/B test or product experiment into a ship / stop / iterate recommendation.
example_format
markdown
example_tagline
不是展示数据, 而是判断上线/停止/继续

02 资源文件 1

03 SKILL.md 正文

<!-- Ported from html-anything (https://github.com/nexu-io/html-anything), next/src/lib/templates/skills/experiment-readout/SKILL.md at commit 553ed98c283f. Copyright the html-anything authors, Apache License 2.0 (see packages/content/local/ports/LICENSE-html-anything.txt). Divergences: frontmatter gained an od: block and English description, and lost featured (curation here is local/curated.json); assets/*.html style references now point at the remixable examples ported alongside. -->

【模板: 实验复盘 / Experiment Readout】 【意图】这不是普通数据报告、不是 dashboard。目标是回答: "这个实验说明了什么, 我们下一步应该上线、停止、继续跑, 还是重新设计?"

【适合输入】

  • A/B test、增长实验、定价实验、onboarding 改版、功能灰度、邮件实验
  • 可以是 markdown、CSV、表格粘贴或混合记录

【必须输出的结构】

  1. Header: 实验名称、owner、日期、实验状态、decision。
  2. Hypothesis: 原始假设, 必须改写成可验证句式。
  3. Setup: audience、variant、duration、sample size、primary metric、guardrail metrics。
  4. Result snapshot: primary metric lift、absolute delta、sample、confidence / caveat。
  5. Metric table: Control vs Variant, primary + secondary + guardrail。
  6. Interpretation: 解释结果为什么发生, 区分 signal、noise、unknown。
  7. Decision: Ship / iterate / extend / stop 四选一, 并给理由。
  8. Follow-up experiments: 2-4 个下一步实验, 每个包含 hypothesis、expected impact、effort。
  9. Instrumentation notes: 数据缺口、埋点问题、样本偏差。

【设计要求】

  • 产品数据团队风格: 清楚、可信、行动导向。
  • 首屏必须有大号 decision badge 和 primary metric delta。
  • 图表可以用 CSS/SVG/Chart.js; 如果用 Chart.js, canvas 外层必须固定高度。
  • 不要把结果包装得过度确定; 小样本或缺少显著性时必须明确 caveat。

【可选风格模板 — remixable examples (start from one with remix_open_design_example)】 根据实验语境选择一种, 不要三种混用:

  • remixable example od:prototype:experiment-readout-product-readout: 默认风格。浅色产品实验复盘, 适合 PM / growth / leadership readout。
  • remixable example od:prototype:experiment-readout-lab-notebook: 研究实验室 notebook, 适合 early-stage experiment、定性 + 定量混合、需要保留 caveat 的探索实验。
  • remixable example od:prototype:experiment-readout-growth-console: 深色 growth analytics console, 适合增长团队、实时指标、漏斗 / activation / conversion readout。

如果用户没有指定风格, 优先使用 product-readout; 如果材料强调研究过程和不确定性, 使用 lab-notebook; 如果材料强调增长指标、漏斗、实时监控或运营节奏, 使用 growth-console。

【内容真实性】

  • 只使用用户提供的数据。不要捏造 p-value、confidence、样本量。
  • 如果没有统计显著性信息, 用 "directional" / "inconclusive" / "needs more data" 表达。

04 同仓库更多 Skills

feimacode
feimacode/open-design-agent-kit

youtube-clipper

YouTube clip generation and editing with automated workflows — pull source video, slice highlights, add captions, and export.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

writing-guidelines

Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

★ 1.1k
feimacode
feimacode/open-design-agent-kit

wpds

WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

weread-year-in-review-video-template

WeRead-inspired HyperFrames video template for vertical annual reading reports, personal reading dashboards, book-note recaps, and shareable year-in-review stories. Use when users want a 9:16 HTML-to-MP4 reading report with warm paper texture, editorial Chinese typography, book-page metaphors, data highlights, and deterministic motion.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

web-design-guidelines

Review UI code for Web Interface Guidelines compliance by the Vercel engineering team. Covers layout, typography, color, motion, and accessibility for product UI.

★ 1.1k
feimacode
feimacode/open-design-agent-kit

web-clone

网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支,并强制核对任何 AI 二手分析里的可执行代码。

★ 1.1k