Communitygithub.com

amplitude/builder-skills

监控所有活跃及近期完成的 Amplitude 实验,按重要性分类,然后对最具影响力的实验进行深入分析和报告。当用户要求“检查实验”、“实验状态”、“实验回顾”、“哪些实验正在运行”,或需要定期的实验健康报告时使用。

builder-skills 是什么?

这是一个专业的 Amplitude 实验监控与报告生成技能,专为 AI 代理设计,用于自动化实验组合的管理和报告。它首先扫描并筛选出活跃且非陈旧的实验以及近期完成的实验,然后通过一系列 API 调用获取元数据、指标名称和主要结果,严格限制批量大小(每次 get_experiments 最多 5 个 ID)并处理大型响应(仅提取 summary 对象和有效性标志)。报告结构分为两部分:顶部的摘要与行动项(一个汇总表加动作列表)和底部的详细信息(深入分析、运行中实验、近期决策和待设置实验)。它使用统一的裁决词汇(如“Ship”、“Iterate”、“Abandon”)进行分类,并避免使用统计术语(无 p 值、无功效分析),确保非专家也能理解。在深入分析中,它会优先检查数据质量(包括 SRM 检测、样本量、有效性标志),然后再报告主要指标和护栏指标,最后给出明确的行动建议。该技能适用于 Claude Code、Cursor 或 Codex 等支持工具调用和 markdown 输出的 AI 代理平台。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/amplitude/builder-skills/tree/HEAD/analytics-skills/skills/monitor-experiments

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

实验监控与报告生成器

扫描活跃和近期完成的实验,展示需要关注的内容,并报告重要的实验。

这是一个监控技能——保持输出对非专家可访问。避免使用统计术语(无 p 值、无功效分析)。如需对特定实验进行深入分析,请使用 analyze-experiments 技能。


关键:管理响应大小

  1. get_experiments:每次最多 3-5 个 ID。 在获取之前,先使用 search 结果进行过滤。
  2. query_experiment 响应较大。 仅提取 summary 对象和有效性标志。忽略 timeseries、xValues、批量数组。
  3. 指标名称解析:search 不会匹配 queries 中的指标 ID。使用 entityTypes: ["METRIC"]、空 queries、limitPerQuery: 50 进行搜索,范围为项目。从结果中匹配 ID。

报告结构

报告分为两部分:

  1. 摘要与行动(顶部)—— 一个表格 + 行动项。仅阅读此部分即可了解全貌。
  2. 详细信息(底部)—— 对需要注意的实验进行深入分析、近期决策的简要说明、需监控实验的一行摘要以及需要设置的任务列表。

不要在摘要表和详细信息之间重复信息。摘要表是整个实验组合状态的唯一真实来源。详细信息对特定实验进行补充说明。


操作说明

步骤 1:上下文与发现

  1. 调用 Amplitude:get_context。如果存在多个项目,询问要监控哪个。
  2. 搜索实验:
Amplitude:search({
  entityTypes: ["EXPERIMENT"],
  appIds: [projectId],
  queries: [],
  sortOrder: "lastModified",
  sortDirection: "DESC",
  limitPerQuery: 50
})
  1. 过滤规则 —— 包含以下实验:
    • 正在运行且非陈旧: 任何处于运行状态且未被标记为陈旧的实验。陈旧实验已闲置,应排除。
    • 近期决策: 已完成且记录了决策并且在过去 14 天内修改过的实验。这些实验值得审查以确认决策或分享经验。
  2. 排除: 草稿、已禁用和过期实验。

步骤 2:获取元数据、指标名称和主要结果

  1. 以 3-5 个 ID 为一组调用 Amplitude:get_experiments(仅限步骤 1 中过滤后的集合)。
  2. 提取:状态、日期/持续时间、变体、指标 ID(recommendation=true 的主要指标)、决策、负责人。
  3. 使用详细元数据再次应用步骤 1 的过滤规则(某些字段如陈旧状态或决策可能仅在此处可用)。
  4. 通过 Amplitude:search({ entityTypes: ["METRIC"], appIds: [projectId], queries: [], limitPerQuery: 50 }) 解析指标名称。构建 { id: name } 映射。
  5. 对于已配置指标的实验,调用 Amplitude:query_experiment({ id: "<id>" })(无需 metricIds)以获取主要指标结果和数据质量标志。此数据将同时用于摘要表和深入分析。

关键:永远不要向用户显示原始指标 ID。 如果无法解析指标名称,请按其角色描述(例如,“主要指标”、“护栏指标”)—— 不要显示诸如“rrgtky08”或“Metric gvgb5efj”之类的字符串。指标 ID 是内部标识符,对人类读者毫无意义。


步骤 3:摘要与行动

这是报告的顶部部分。它应是独立的 —— 仅阅读此部分的人应能了解全貌。

摘要表

## 实验监控:[项目名称]
日期:[今天] | 项目:[名称] ([ID])

| 实验名称 | 状态 | 持续时间 | 提升率 | 裁决 |
|------------|-------|----------|------|---------|

列定义:

  • 实验名称 — 人类可读的名称(不是 URL,不是 ID)
  • 状态 — 运行中 或 已完成
  • 持续时间 — 实验开始以来的天数
  • 提升率 — 主要指标的相对提升率(如可用),否则为“—”。对于多变量实验,显示范围(例如,“-17% 至 -20%”)
  • 裁决 — 需要采取的操作(参见下方词汇表)

裁决词汇表:

裁决使用时机
发布主要指标显著正向提升,护栏指标正常,数据质量良好
迭代正向信号但护栏指标异常或质量存疑
监控正在运行,尚未显著,无需操作
放弃主要指标显著负向提升,或存在关键数据质量问题
已决策:发布近期完成,团队决定发布
已决策:不发布近期完成,团队决定不发布
修复配置查询错误,曝光事件异常或流量严重不均衡
需要指标在无指标的情况下运行 —— 无法评估
不可用调查/引导部署,非功能实验

行动项(表格之后立即显示)

**立即行动:**
- [实验名称] — [具体操作及负责人姓名]

**持续关注:**
- [实验名称] — [简要状态 + 何时复查]

**需要设置:**
- [实验名称] — [缺少的内容 + 负责人姓名]

表中的每个实验应恰好出现在一个行动类别中。如果某个类别中没有实验,则省略该类别。


步骤 4:详细信息

在摘要下方,提供按部分组织的额外细节。每个实验恰好出现在一个部分中 —— 无重复。

4a:深入分析(需要注意的实验)

对裁决为发布、迭代或放弃的实验进行深入分析(最多 3 个)。这些实验具有值得检查的重要结果。

对于每个实验,一次性输出完整报告:

---
## [实验名称]
[状态] | [持续时间]天 | 对照组:[N] / 实验组:[N] | [实验链接]

数据质量(首先 —— 在结果之前):

在报告指标结果之前检查数据质量。如果存在关键问题,读者需要在解读任何数据之前了解该上下文。

如果全部通过,一行:“数据质量检查全部通过。” 然后继续进行主要指标。

如果发现问题,在主要指标之前报告:

### 数据质量:发现 [N] 个问题

SRM(样本比率不匹配):

  • 使用 API 响应中的 srmDetected 字段
  • 如果 srmDetected: true:始终首先报告并突出显示
  • 报告:实际拆分与预期拆分的对比,并给出具体百分比

流量分配变更:

  • 将当前变体权重与累计曝光分布进行比较
  • 如果不匹配(例如,当前权重是 100/0/0,但累计是 15/70/15),则说明实验期间的流量分配已更改
  • 突出显示这一点 —— 这意味着某些变体可能不再接收新流量

样本量:

  • <100 每变体:标记为不足 —— 过早,无法得出任何结论
  • 100–1,000 每变体:仅提供方向性信号,不足以做出自信的决策
  • 1,000+:足够用于分析

有效性标志 —— 仅报告失败:

标志失败时的含义严重性
isVariancePositive = false指标数据无效 —— 统计检验无法运行关键
isConfidenceIntervalNotFlipped = false结果计算错误 —— 不要相信这些数字关键
isMeanValid = false指标值异常(NaN/无限)—— 无法分析关键
statsAssumptionsMetForWholeExperiment = false统计假设未满足 —— 结果可能不可靠高
hasSuspiciousUplift = true异常大的效应 —— 可能是测量误差,而非真实变化高
isPointEstimateInsideConfidenceInterval = false内部数学不一致 —— 结果可能错误高
isStandardErrorLargeEnough = false噪声太大,无法获得可靠估计中等

如果检测到 SRM 或关键标志失败:

⚠️ 由于 [问题],以下结果应谨慎解读。

主要指标:

### [指标名称]:[通俗易懂的裁决]

| 变体 | 值 | 提升率 | 95% 置信区间 |
|---------|-------|------|--------|
| 对照组 | [X] | — | — |
| 实验组 | [Y] | [+Z%] | [A% 至 B%] |

[一句通俗易懂的解释。]

表述规则:

  • 不要包含 p 值。 非专家不知道它们意味着什么。
  • 使用“不显著”而不是“无效果”。可能存在效果 —— 只是实验在当前样本量下无法检测到。
  • 用通俗易懂的语言首先说明发生了什么。

裁决措辞:

  • 显著正向 — 置信区间完全高于零,正向提升
  • 显著负向 — 置信区间完全低于零,负向提升
  • 不显著 — 置信区间包含零;我们还不能自信地说存在真实差异
  • 趋势正向/负向 — 方向性信号但置信区间包含零;值得关注

仅当提升率非常小(<2%)或非常大(>20%)时,添加一句关于实际重要性的说明。

护栏指标与次要指标:

调用 Amplitude:query_experiment({ id: "<id>", metricIds: [...] })。

专注于发现异常,而不是叙述每个指标。

如果未发现显著异常:“所有护栏指标和次要指标均正常 —— 未检测到显著异常。”

如果发现显著异常:

- **[指标名称]:** 显著异常([−X%],置信区间:[A% 至 B%])—— [一句关于影响的说明]

如果存在尚未显著但数值较大的方向性异常(>20% 相对提升率):

- **[指标名称]:** 不显著,但方向为负([−X%])—— 值得关注

不显著的小方向性变化应省略。如果指标超过 5 个,请注意多重比较会增加假阳性概率。

反馈(仅当主要指标显著时):

调用 Amplitude:get_feedback_insights 并使用与实验相关的关键词。用一行报告 2-3 个主题。如果没有相关反馈,则跳过此部分。

裁决:

### 裁决:[发布 / 迭代 / 监控 / 放弃]
1. [主要指标发现 —— 一句话]
2. [质量 / 护栏指标状态 —— 一句话]
3. [下一步操作 —— 一句话]

决策矩阵(内部参考,不要输出):

信号发布迭代监控放弃
主要指标显著正向 + 实际重要显著正向但有护栏指标异常尚未显著,仍在运行显著负向
质量全部通过轻微标志全部通过或数据不足SRM 或关键标志
护栏指标正常需修复 1 个异常正常或数据不足关键指标显著异常
实验状态已完成已完成运行中已完成或运行中

4b:运行中的实验(监控,无需操作)

对于裁决为监控的实验,提供一行状态:

---
### 运行中的实验

**[名称]** — 运行 [X] 天,对照组:[N] / 实验组:[N]。 [主要指标状态 — 例如,“趋势正向(+3.3%)但尚未显著”]。数据质量正常。 [链接]

**[名称]** — 运行 [X] 天,对照组:[N] / 实验组:[N]。 过早得出任何结论 — [原因,例如,“样本量在 100-1,000 范围内”]。 [链接]

保持紧凑 —— 每个实验一行。在末尾包含链接,以便想要在 Amplitude 中检查的人使用。

4c:近期决策(简短摘要)

对于裁决为已决策:发布或已决策:不发布的实验:

---
### 近期决策

- **[名称]** — [已发布/已回滚] 于 [日期],历时 [X] 天。 [一句话说明结果或理由]。 [链接]

如果实验是在没有指标或没有统计显著性的情况下发布的,请简要说明。

4d:需要设置

对于裁决为修复配置、需要指标或不可用的实验:

---
### 需要设置

- **[名称]** — [问题描述]。负责人:[负责人]。
- **[名称]** — 调查/引导部署,非功能实验。无需分析。

每个实验恰好出现在一个详细信息部分。不要在摘要表操作项和详细信息部分中重复列出同一个实验 —— 详细信息部分是对操作项的补充说明,而不是重复。


边界情况

  • 无实验: 清晰报告,建议检查其他项目
  • 无数据(<24 小时): 注意实验刚刚开始,7 天后再检查
  • 检测到 SRM: 在数据质量中首先说明 —— 它可能使其他所有结果无效
  • 10+ 个实验: 为所有实验生成摘要表,深入分析前 3 个,并提供分析更多实验的选项
  • 响应过大 / 已保存到磁盘: 仅提取 summary + 有效性标志
  • 未配置指标: 在“需要设置”部分列出,不进行深入分析
  • 所有实验均为陈旧状态: 报告没有活跃实验需要监控
  • query_experiment 返回查询错误: 清晰报告错误,并包含实验负责人的姓名。在摘要中标记为“修复配置”。常见原因:曝光事件属性损坏,实验密钥配置错误。
  • 实验期间流量分配更改: 在数据质量中标记。将当前权重与累计曝光分布进行比较。注明哪些变体不再接收流量。
  • 调查/引导实验(NPS 等): 在摘要中标记为不可用。无需分析 —— 跳过深入分析。
  • 流量严重不均衡(例如,5%/95% 或 0%/100%): 标记为“修复配置” —— 没有有意义的对照组就无法运行有效实验。在需要设置中注明负责人。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

amplitude/builder-skills

Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers. Use when a metric looks unusual, investigating a spike or drop, or understanding the "why" behind numbers.

amplitude/builder-skills

Deeply analyze Amplitude dashboards by analyzing key charts, surfacing top areas for concern and takeaways, identify anomalies, then explain changes using customer feedback trends.

amplitude/builder-skills

Designs A/B tests with proper metrics and variants, analyzes running or completed experiments, and interprets results with statistical rigor. Use when setting up experiments, checking experiment status, analyzing results, or making ship decisions.

amplitude/builder-skills

Synthesizes customer feedback into actionable themes including feature requests, bugs, pain points, and praise. Use when planning product roadmap, understanding user sentiment, investigating specific issues, or preparing voice-of-customer reports.

amplitude/builder-skills

Analyze MCP server usage instrumented with Amplitude's MCP Analytics SDK: break usage and errors down by tool, read the rationales within each tool to see what callers are trying to do, and produce a prioritized write-up of actionable fixes. Use this skill whenever the user asks to understand how their MCP server is being used, what agents/users are trying to do with it, why tool calls are failing, what to fix or improve in their MCP server, or asks for an "MCP usage report", "tool error analysis", "intent analysis", "rationale clustering", or "MCP insights". Also trigger when the user mentions [MCP]-prefixed events, tool rationale, tool call errors, or just finished instrumenting their MCP server and wants to see what the data says. Requires the Amplitude MCP connector.

amplitude/builder-skills

Read lost deals and churned accounts from your CRM, extract reasons clustered by theme (missing features, pricing, competitors, UX), and write a prioritized weekly analysis with product improvement recommendations. Use before roadmap planning or to build the case for prioritizing retention work.

amplitude/builder-skills

Creates Amplitude charts from natural language descriptions, handling event selection, filters, groupings, and visualization choices. Use when you know what you want to measure but prefer not to build the chart manually.

amplitude/builder-skills

Guide an Amplitude user through building a custom agent by suggesting use cases grounded in their role and data, shaping the idea into a well-formed spec, and generating a ready-to-run Global Agent deeplink that creates it. Use to create, build, or set up a custom agent, automate a recurring analysis, or put a repeated report on a schedule.

amplitude/builder-skills

Builds comprehensive Amplitude dashboards from requirements or goals, organizing charts into logical sections with appropriate layouts. Use when creating a complete dashboard from scratch or assembling existing charts into a cohesive view.

amplitude/builder-skills

Pull Intercom tickets and Slack support messages from the past 7 days, classify each signal, enrich with CRM data (ARR, plan, renewal), score by customer value and churn risk, and output a tiered priority report saved to Drive. Use when you need a fast, data-driven view of what support signals matter most.

amplitude/builder-skills

Use this skill whenever a user wants to improve existing pages on their website to get cited more by AI models — whether they say "our pages aren't getting cited", "improve this page for AI visibility", "which of our pages should we update", "make this article more cite-worthy", "our competitors are getting cited instead of us", "update our content for AI search", or any variation where the goal is improving an existing asset rather than creating something new. This skill pulls owned pages from AI Visibility, identifies which ones have citation potential but are underperforming, compares them against the external pages that are winning citations on the same topics, and produces section-level rewrites or a full-page update — then pushes the revision to the CMS as a draft. Trigger even if the user just says "help me get cited more" or "why is [competitor] getting cited instead of us".

amplitude/builder-skills

Use this skill whenever a user wants to win AI citations on prompts that competitors currently dominate — whether they say "competitors are getting cited instead of us", "we're losing on these prompts", "how do I outrank [competitor] in AI answers", "find prompts where we should be winning", "create content to beat [competitor]", or any variation where the goal is capturing AI share on prompts a competitor currently owns. This skill pulls competitor visibility data from AI Visibility, identifies the specific prompts where competitors win and Amplitude is absent, clusters them by intent, and produces targeted comparison pages, alternatives content, or rebuttal assets — then pushes drafts to CMS. Trigger on any mention of competitor, prompt hijack, outrank, or "why is [competitor] getting cited instead of us".

amplitude/builder-skills

Use this skill whenever a user wants to turn AI Visibility data into published content — whether they say "find content gaps", "what should we write about", "which topics have low visibility", "help me get cited by AI models", "create a blog post from our AI Visibility gaps", "we're losing to competitors on these prompts", or any variation where they want to go from AI visibility weakness to a draft article, landing page, or FAQ. This skill connects directly to Amplitude AI Visibility data (topics, prompts, visibility scores, citations, competitor data, full LLM responses and sources) and produces a publish-ready content brief plus full article draft. If the user mentions CMS (WordPress, Webflow, Contentful, Sanity, HubSpot, Ghost, Shopify), also trigger this skill to push the draft directly. Trigger even if they just say something vague like "what content should we create?" in an AI Visibility context.

amplitude/builder-skills

Use this skill whenever a user wants to test content variants before publishing to find which one will get cited most by AI models — whether they say "which version of this content will perform better", "test this article before we publish", "simulate how AI will respond to this content", "which angle should we use", "generate content variants and pick the winner", "run a simulation before publishing", or any variation where the goal is data-driven content selection rather than gut-feel publishing. This skill takes an identified content opportunity, generates 2–3 distinct variants with different angles or structures, scores them against actual AI model responses from AI Visibility, references the Simulate Changes feature for pre-publish validation, and produces a clear recommendation on which variant to publish — then pushes the winner to CMS. Trigger on any mention of "simulate", "test variants", "which performs better", "A/B content", or "before we publish".

amplitude/builder-skills

Use this skill whenever a user wants to understand which external sources are being cited by AI models on topics relevant to their brand, and wants to create content that will outrank those sources — whether they say "what sources are AI models citing", "why is [third-party site] being cited instead of us", "we want to be the definitive source on X", "build something that gets cited more than G2 or TechRadar", "create an authoritative asset", or any variation where the goal is producing a new reference asset (definition page, benchmark, methodology, glossary, comparison hub) designed to beat existing top-cited sources. This skill analyzes AI Visibility source data, reverse-engineers what makes top-cited pages authoritative, and produces a superior source asset — then pushes it to CMS as a draft. Trigger on any mention of "sources", "third-party citations", "authoritative content", "definitional pages", or "outrank".

amplitude/builder-skills

Instrument a Node/TypeScript MCP server with Amplitude's @amplitude/mcp-analytics SDK so tool calls, sessions, and rationale are tracked as Amplitude events. Use this skill whenever the user wants to add Amplitude analytics to their MCP server, mentions "MCP Analytics", "@amplitude/mcp-analytics", "instrument my MCP server", "track MCP tool calls", "add rationale to my MCP tools", or wants agent traffic (Claude, Cursor, ChatGPT) attributed back to Amplitude. Also use for adding UTM tagging to MCP-returned links, or for troubleshooting identity/user_id mismatches between MCP events and web/mobile Amplitude data.

amplitude/builder-skills

Instruments a pull request with Amplitude analytics that conform to the project's existing taxonomy. Reads the tracking plan via the Amplitude MCP server (events, properties, naming conventions), analyzes the PR diff to find the few user actions genuinely worth tracking, detects the codebase's SDK and tracking patterns, and adds instrumentation that matches both. Optionally (opt-in) stages new events and properties on an Amplitude tracking-plan branch for data-governance review. Use when asked to "instrument this PR", "add analytics to this change", "add tracking", "add Amplitude events", "instrument this feature", or "what should I track here".

amplitude/builder-skills

Diagnoses product health by cross-referencing Amplitude analytics (dashboards, charts, funnels, feedback, AI agent analytics), optionally Datadog (errors, latency, stack traces), and optionally Slack (qualitative feedback, bug reports, feature requests). Identifies what's broken, what's working, and what to do about it — with root causes, not just symptoms. Use when asked to "diagnose my product", "what's going on", "product health check", "what's broken", "where are users struggling", "give me a product diagnosis", or "what should I focus on".

amplitude/builder-skills

Turn one or more meeting transcripts, notes, or Slack threads into concise takeaways and clear action items with DRIs. Works with a single meeting or a batch from the whole week.

amplitude/builder-skills

Summarizes B2B account health by analyzing usage patterns, engagement trends, risk signals, and expansion opportunities. Use for customer success reviews, renewal preparation, QBRs, or account prioritization.

相关技能