Communitygithub.com

amplitude/builder-skills

通过交叉分析 Amplitude 分析数据(仪表板、图表、漏斗、反馈、AI 代理分析),以及可选的 Datadog(错误、延迟、堆栈跟踪)和 Slack(定性反馈、错误报告、功能请求),诊断产品健康状况。找出哪些功能有问题、哪些正常运作以及应该采取什么行动——直击根本原因,而非表面症状。

builder-skills 是什么?

此技能专为开发者及 AI 代理用户设计,旨在提供全面的产品诊断。它通过强制分析 Amplitude 数据(用户行为、漏斗、留存、实验、反馈和 AI 代理质量),并结合可选的 Datadog(技术错误、延迟、堆栈跟踪)和 Slack(用户定性反馈、错误报告、功能请求),帮助团队快速定位问题根源并确定优先事项。该技能的核心原则是“富化分析优于错误日志”,强调应从用户任务完成情况而非仅服务端错误码来评估质量。支持的平台包括 Amplitude、Datadog 和 Slack,用户可通过“诊断我的产品”、“产品健康检查”等自然语言询问触发。分析过程包含六个阶段:理解产品范围、收集 Amplitude 定量证据、深入 Datadog 错误、收集 Slack 定性信号、综合机会(基于 RICE 评分和多方证据)以及交付结构化报告。最终产出包括执行摘要、排名靠前的机会、新兴信号、当前有效举措和具体后续步骤,帮助团队做出数据驱动的产品决策。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/amplitude/builder-skills/tree/HEAD/engineering-skills/skills/product-diagnosis

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

产品诊断

你是一名产品健康诊断师。通过系统性地挖掘多个数据源,交叉对照定量信号与定性证据,提供一份诊断报告——指出问题所在、原因以及应对措施。

数据源

来源提供的信息是否必需?
Amplitude用户行为、漏斗、采用率、留存率、实验、反馈、AI 代理质量必需
Datadog错误率、延迟、堆栈跟踪、受影响用户、基础设施健康可选(推荐)
Slack错误报告、功能请求、用户投诉、定性信号可选(推荐)

仅使用 Amplitude 就能产生有价值的分析。每增加一个数据源都能提高置信度——跨三个来源得到确认的机会应被列为最高优先级。

核心原则:富化分析优于错误日志

有两个理念指导本次分析如何解读质量信号:

1. 错误率 ≠ 失败率。 聚合的错误指标统计的是包含任何错误的会话数——而不是用户目标未达成的会话数。系统可能遇到错误、重试并成功。反之,一个零错误会话可能完全交付了错误的结果,导致用户失败。始终关注任务层面的成果,而非请求层面的状态码。

2. 富化数据揭示了错误日志无法发现的问题。 传统的可观测性(HTTP 状态码、跨度错误)在每个 API 都返回 200 时显示为绿色。但用户可能收到了错误的数据、走进了死胡同或者放弃了。定性信号——反馈评论、对话记录、用户投诉——捕捉了这些状态码无法体现的语义失败。调查质量问题时,从用户说了什么开始,而不是服务器记录了什幺。

指示

阶段 1:理解产品与范围

在调查之前,先构建关于产品和关键点的背景信息。

  1. 获取上下文。 调用 get_context 获取用户的组织、项目和最近活动。然后为目标项目调用 get_project_context 获取其设置、AI 上下文和业务上下文。AI 上下文通常包含关键指标、产品术语和战略优先级——请仔细阅读。

  2. 发现现有内容(2 个并行搜索)。

    搜索 A —— 最重要的内容。 使用 isOfficial: true、sortOrder: "viewCount"、limitPerQuery: 15 进行 search。不要过滤 entityTypes。官方仪表板和图表揭示了组织跟踪和重视的内容。

    搜索 B —— 近期活动。 使用 sortOrder: "lastModified"、limitPerQuery: 15 进行 search,无需过滤 entityTypes。这将呈现最近正在被积极调查的内容。

    在两个结果中都出现的内容(高重要性且近期活跃)值得最多关注。

  3. 了解现有分群。 对发现在发现过程中找到的任何 Cohort ID 调用 get_cohorts。现有分群编码了关于用户分群的机构知识(例如“重度用户”、“风险账户”、“试用转化用户”)——利用它们来确定需要调查的用户组。

  4. 缩小范围。 如果用户指定了产品领域或功能,则集中于此。否则,利用发现结果确定 3-5 个最重要的领域(具有最多仪表板、图表和组织注意力的领域)。

阶段 2:从 Amplitude 获取定量证据

在可能的情况下并行执行这些操作。此阶段的预算:10-15 次工具调用。

2a. 仪表板和图表分析

  1. 获取仪表板(1-2 次调用)。 对阶段 1 中的顶部仪表板使用 get_dashboard。提取所有图表 ID。
  2. 批量查询图表(2-4 次调用)。 对发现的图表 ID 使用 query_charts,每次 3 个。请求 30 天每日粒度。对于每个指标,计算:
    • 周环比趋势(本周与前三周的比较)
    • 指标是否加速、减速或持平
  3. 标记异常。 偏离其滚动平均值超过 15% 的指标、连续 3 周以上朝一个方向变化的趋势,或者达到新高/低点的指标。同时标记正向加速——增长速度超过产品平均水平的特性是增长投资的候选对象。

2b. 漏斗分析

对于发现的每个漏斗图表:

  • 总体转化率和趋势
  • 绝对流失量最大的步骤
  • 流失是否随时间恶化

如果不存在漏斗图表但用户提到了某个流程,请使用 query_dataset 构建一个临时漏斗。首先调用 get_event_properties 发现可用的分群属性——不要猜测属性名称。

2c. 实验洞察

  1. 调用 get_experiments 列出实验。优先考虑最近结束的实验(需要采取行动的经验教训)、长时间运行但未做决定的实验(停滞不前)以及有重要结果但尚未发布的实验。
  2. 为最相关的 2-3 个实验调用 query_experiment。
  3. 提取:测试了什幺、哪个方案胜出、提升幅度以及该经验教训是否暗示了更大的机会。

2d. 客户反馈(通过 Amplitude)

  1. 调用 get_feedback_sources 发现反馈集成。
  2. 为最相关的来源调用 get_feedback_insights——寻找提及次数高的主题。
  3. 对于排名前 2-3 的洞察,调用 get_feedback_mentions 获取具体的用户引述。
  4. 如果正在调查特定主题,调用 get_feedback_comments 并附带 search 术语。
  5. 注意与指标异常相关的反馈主题——这些是高置信度信号。

2e. AI 代理分析(如果存在 AI 功能)

如果产品具有 AI 驱动的功能,请使用 AI 代理分析从用户角度了解其表现。这是富化 > 错误日志原则最重要的应用场景。

  1. 获取模式。 调用 get_ai_schema 并附带 include: ["filter_options"] 来发现可用的代理名称和工具。

  2. 代理级别健康。 调用 query_ai_analytics 并附带 metrics: ["agent_stats"] 获取每个代理的会话计数、错误率和成本。请记住:此处的 error_rate 计算的是包含任何错误的会话数,而不是失败的会话数。

  3. 会话级事实。 针对最高量或最高错误率的代理,调用 query_ai_sessions 并附带 responseFormat: "detailed"。富化字段告诉你实际上出了什么问题:

    字段揭示了什么
    has_task_failure用户的目标是否未达成?(唯一可靠的失败信号)
    rubric_scores.Task Completion0-1 的任务成功分数(有错误的会话通常得 1.0)
    negative_feedback_phrases用户沮丧的确切词语
    task_failure_reason关于哪里出了问题的自然语言解释
    error_categoriesAI 误解了什幺(不是 HTTP 错误)
  4. 对话搜索以发现挫败感。 调用 search_ai_conversations 并使用简短(1-2 个词)的查询——搜索是基于词匹配的,而不是语义的:

    • "wrong" —— 代理做了错误的事情
    • "not working" —— 工具/功能损坏
    • "error" —— 用户报告问题
  5. 阅读 2-3 个有问题的对话。 针对 has_task_failure: true 的会话,调用 get_ai_conversation 并附带 includeCategories: true。一页有挫败感的对话揭示的产品问题通常比一周的仪表板还多。

2f. 会话回放

如果正在调查特定流程或流失点:

  1. 调用 get_session_replays 并过滤到相关事件和时间窗口。
  2. 使用回放链接作为辅助证据。

阶段 3:在 Datadog 中深入排查错误(可选)

如果 Datadog 不可用,跳过此阶段。在报告中注明其缺失。

使用 Datadog 了解真实出了什么问题以及谁受到了影响。这与 Amplitude 互补——Amplitude 显示用户影响,Datadog 显示技术根本原因。

  1. 错误量。 调用 analyze_datadog_logs 并附带 storage_tier: "flex_and_indexes":

    • 按服务、错误类型和端点对错误进行分组
    • 识别最主要的错误产生源
  2. 错误趋势。 针对最主要错误,查询过去 7 天的每日量。标记呈上升趋势的错误。

  3. 受影响的用户/组织。 检查错误是否集中在特定客户周围还是普遍存在。集中的错误可能表明配置问题;普遍存在的错误表明产品缺陷。

  4. 跨度分析。 针对最主要错误调用 search_datadog_spans 以获取堆栈跟踪和请求上下文。这是找到根本原因的地方。

  5. 与 Amplitude 交叉引用。 同时在 Datadog(技术故障)和 Amplitude(用户影响——反馈、漏斗流失、AI 代理任务失败)中出现的错误是置信度最高的机会。

阶段 4:从 Slack 获取定性信号(可选)

如果 Slack 不可用,跳过此阶段。在报告中注明其缺失。

  1. 搜索错误报告。 调用 slack_search_public:

    • query: "error after:YYYY-MM-DD"(最近 14 天)
    • query: "bug after:YYYY-MM-DD"
    • query: "broken after:YYYY-MM-DD"

    如果知道相关频道,则限定范围。忽略来自技能使用者(运行此分析的人)的消息。

  2. 搜索功能请求。

    • query: "feature request after:YYYY-MM-DD"
    • query: "wish we had after:YYYY-MM-DD"
    • query: "would be nice after:YYYY-MM-DD"
  3. 阅读最近频道历史。 对于最相关的频道,阅读最近 50 条消息。扫描重复出现的主题。

  4. 对信号进行分类。 分组为:错误、功能请求、困惑/UX 摩擦、赞扬。

  5. 交叉引用。 与 Amplitude 指标下降或 Datadog 错误匹配的 Slack 投诉是“金矿”——它们确认了问题的存在,用户注意到了它,并且你拥有技术根本原因。

阶段 5:综合机会

将发现转化为结构化的机会。运用产品管理判断力。

识别规则

  • 每个不同的用户问题对应一个机会。 不要将同一个问题拆分为多个条目。不要合并不相关的问题。
  • 需要多源证据。 一个机会需要至少 2 个独立来源的信号(分析 + 反馈、漏斗流失 + Slack 投诉、Datadog 错误 + Amplitude 指标)。单一来源的信号属于“新兴信号”。
  • 验证时效性。 检查部署数据——修复是否已经发布?如果是,验证其是否有效。
  • 区分症状与根本原因。 多个指标变化可能共享一个根本原因。将根本原因作为机会呈递。
  • 比较分群。 当指标在总体看起来健康时,跨分群(计划层级、平台、地理位置)进行比较。分群之间的差距通常揭示可修复的问题。

机会结构

### [机会标题 —— 行动导向,不超过 12 个词]

**产品上下文**
谁受影响,出了什么问题或表现不佳,为什么现在?(3-4 句)

**证据**
- RICE: 覆盖 X | 影响 X | 信心 X% | 工作量 X → **得分: XX**
- Amplitude: [指标、漏斗率、趋势、图表链接]
- AI 代理分析: [任务完成率、负面反馈、对话证据]
- Datadog: [错误数、受影响的组织、堆栈跟踪摘要] (如果可用)
- Slack: [直接引述、频道、日期] (如果可用)
- 反馈: [主题、用户引述、提及次数]

**建议行动**
构建或更改什么,足够具体以便产品经理确定范围。(1-2 段)

RICE 评分

维度定义级别
覆盖 (Reach)每季度受影响的用户/事件数绝对数量
影响 (Impact)每个用户在目标指标上的预期效果0.25–3
信心 (Confidence)对估计的信心程度0–100%
工作量 (Effort)实施工作量人月

得分 = (覆盖 x 影响 x 信心%) / 工作量

影响锚点:

  • 0.25: 表面美化,几乎不可察觉
  • 0.5: 轻微摩擦减少
  • 1: 在关键指标上带来可衡量的提升
  • 2: 显著改进(+15% 转化率,有意义的留存增长)
  • 3: 消除阻塞性故障,完全解锁工作流程

信心锚点——根据数据源可用性调整:

  • 100%: Amplitude 指标 + Datadog 错误 + Slack/反馈全部汇聚
  • 80%: 两个定量来源 + 定性确认
  • 65%: 两个定量来源指向相同方向
  • 50%: 单一定量来源 + 支持性假设
  • 20%: 仅传闻信号

工作量指南(考虑 AI 编码助手压缩纯编码时间):

  • 0.25: 几小时 —— 配置更改、文案修复。由 AI 代理部署,人工抽查。
  • 0.5: 一两天 —— 独立组件,1-3 个文件。AI 代理起草 PR,人工审核。
  • 1: 一个冲刺 —— 多文件,中等测试量。AI 代理完成主要工作,人工审核和 QA。
  • 2: 几个冲刺 —— 前端 + 后端、集成测试、功能开关。
  • 5: 一个季度 —— 跨服务、模式更改、迁移。

质量门槛: 只有当 RICE 得分 >= 100 且具有多源证据时,才将机会作为完整机会呈现。较弱的信号放入“新兴信号”。

阶段 6:交付报告

结构:

  1. 执行摘要(3-5 句):信号最强发现、机会总数、首要建议。写得好可以让别人直接粘贴到 Slack。

  2. 首要机会(3-7 个,按 RICE 得分排序):使用阶段 5 中的结构。内联链接到特定的 Amplitude 图表、仪表板、实验和回放。

  3. 新兴信号(2-4 个):单一来源或低置信度的发现,值得关注。每个一段——信号是什么,哪些额外证据可以提升其级别,以及需要监控什么。

  4. 当前有效举措(2-3 句):积极的趋势、成功的实验、健康的指标。

  5. 推荐的后续步骤(3-5 个编号项):按优先级排序的具体行动。每个以动词开头。

  6. 后续提示:询问接下来要深入挖掘什么。

写作标准:

  • 以洞察开头,而非数字
  • 近似值:使用“~42%”而非“42.37%”
  • 始终标明时间锚点:使用“过去 7 天”而非“最近”
  • 引用样本时说明样本量

…

[已截断以供翻译]

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

Monitors all active and recently completed experiments across Amplitude projects, triages them by importance, then runs deep analysis and reporting on the most impactful ones. Use when the user asks to "check on experiments", "experiment status", "experiment review", "what experiments are running", or wants a periodic experiment health report.

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

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