Communitygithub.com

amplitude/builder-skills

分析使用 Amplitude 的 MCP Analytics SDK 所記錄的 MCP 伺服器使用情況:按工具拆解使用量和錯誤,閱讀每個工具內的請求意圖以了解呼叫者的目的,並產出優先排序的可執行修復摘要。

builder-skills 是什麼?

這個技能幫助開發者和 AI 代理深入分析已使用 Amplitude MCP Analytics SDK 進行儀器化的 MCP 伺服器。它會自動產生一份詳細報告,回答三個關鍵問題:哪些工具被使用且哪些失敗、呼叫者對每個工具的意圖為何,以及團隊應該優先修復哪些問題。支援 Claude Code、Cursor、Codex 等代理平台,透過 Amplitude MCP 連接器運作。核心分析邏輯是「工具定位修復範圍,意圖解釋背後動機」:先按工具找出高錯誤率的工具(例如一個查詢工具失敗率高達 22%),再透過該工具內的請求意圖(rationales)分析失敗原因(例如是儀表板重新整理代理超出批次大小限制),從而精準產生可執行的修復建議。它還會識別目標意圖密度、跨工具工作流程、重複錯誤循環、復原率等,並區分可透過圖表呈現的量化資料(如工具呼叫量、錯誤率)與模型推導的意圖分組。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/amplitude/builder-skills/tree/HEAD/analytics-skills/skills/analyze-mcp-server

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

分析 MCP 伺服器 — 意圖與錯誤分析

生成一份報告,回答關於已使用 Amplitude MCP Analytics SDK 進行儀器化的 MCP 伺服器的三個問題:

  1. 哪些工具被使用,哪些失敗了?(每個工具的使用量 + 錯誤率)
  2. 呼叫者對每個工具想做什麼,以及每個意圖在哪裡出錯?(每個工具內的請求意圖 × 錯誤訊息)
  3. 團隊應該優先修復什麼?(基於錯誤證據的修復,而非直覺)

這項分析的核心價值在於:工具定位修復範圍;意圖解釋背後動機。 整體錯誤率說「4.5% 的呼叫失敗」。按工具拆解後它說「query_chart 失敗了 22% 的時間」— 現在你知道要打開什麼。加上該工具內的意圖後它說「失敗來自儀表板重新整理的代理碰到批次大小限制」— 現在你知道原因,修復方案自動浮現。意圖在很大程度上是工具範圍的(每個工具都有自己的呼叫理由),因此工具是主要軸線,意圖是工具內的第二層切割 — 全域性地對意圖進行聚類只會重新推導出工具的邊界,同時混合了無法比較的意圖。

先決條件

  • Amplitude MCP 連接器必須啟用。如果未啟用,請停止並要求使用者在他們的工具/連接器設定中加入 Amplitude 連接器 — 沒有備用資料來源。

  • 一個包含 SDK 事件的專案。SDK 會發送 SDK 擁有的預設事件,所有事件都以 [MCP] 為前綴,並且 — 關鍵是 — 它們攜帶的每個預設屬性也都以 [MCP] 為前綴,它們可能還有自訂屬性。

    事件:

    • [MCP] Tool Call Response — 主力事件:每次呼叫到達工具回呼(成功或錯誤)時產生一個事件。
    • [MCP] Tool Call Rejected — 在任何工具執行之前就失敗的 tools/call(未知/停用的工具、輸入架構驗證)。這就是幻覺/拼錯的工具名稱出現的地方,其資訊承載於 [MCP] Attempted Tool Name(避免使用保留的 [MCP] Tool Name)。
    • [MCP] Session Initialized, [MCP] Session Ended, [MCP] Tools Listed。

    [MCP] Tool Call Response 上的關鍵屬性:[MCP] Tool Name, [MCP] Client Name, [MCP] Client Version, [MCP] Session ID, [MCP] Auth Type, [MCP] Rationale, [MCP] Is Error, [MCP] Error Message, [MCP] Error Type(returned_error 與 thrown_exception — 區分一個工具報告失敗和一個工具崩潰),[MCP] Response Duration, [MCP] Response Size, [MCP] Request Size。

  • 事件/屬性名稱在不同 SDK 版本之間仍可能變化。永遠不要假設 — 在第 0 階段使用分類工具進行驗證。上述的標準名稱來自 SDK 的 constants.ts(EVENT_PROPERTY_KEYS);如果專案的資料不一致,請相信專案並進行調整。

第 0 階段 — 定位並驗證資料

  1. 呼叫 Amplitude 上下文工具(不帶 projectId)來列出專案。如果有多個看似合理的專案且使用者未指定,請詢問。
  2. 確認所選專案中存在 [MCP] 事件(搜尋事件或列出事件;get_events 僅按精確名稱過濾,因此請使用搜尋來發現 [MCP] 前綴)。
  3. 提取 [MCP] Tool Call Response(和 [MCP] Tool Call Rejected)的事件屬性,以確認確切的屬性名稱 — 記住它們是以 [MCP] 為前綴且採用首字母大寫的格式(例如 [MCP] Rationale,而不是 tool rationale)。將你找到的任何名稱綁定到下方查詢中使用的名稱。
  4. 執行一次使用量/時效性查詢:過去 60 天內 [MCP] Tool Call Response、[MCP] Session Initialized 的總量,按週間隔劃分。這會告訴你可用的日期範圍以及是否有足夠的資料。如果工具呼叫總數少於約 5000 次,請警告使用者每個工具的細項會很稀疏且百分比不穩定 — 但仍繼續進行,但在報告中說明。

記錄:專案 ID、日期範圍、總呼叫量。後續每個查詢都使用相同的範圍,以便數字保持可比性。

第 1 階段 — 按工具細分(主幹)

這是主要地圖;所有其他項目都從這裡深入。

  • 按工具計算使用量: [MCP] Tool Call Response 的總量,按 [MCP] Tool Name 分組,groupByLimit 約 100。
  • 按工具計算錯誤: 同上,但增加過濾條件 [MCP] Is Error is "true"。
  • 按嘗試名稱計算被拒絕的呼叫: [MCP] Tool Call Rejected 的總量,按 [MCP] Attempted Tool Name 分組。這些呼叫從未到達回呼,因此對上述兩個查詢是不可見的 — 但一個高使用量的嘗試名稱如果不是一個真正的工具,就是最有行動價值的發現之一(代理持續猜測的重新命名或幻覺)。

計算每個工具的呼叫量、錯誤計數和錯誤率,並以兩種方式對工具進行排序:按呼叫量(哪些是承載負載的)和按錯誤量(哪些造成最多失敗)。選擇前 3-5 個工具進行深入分析 — 偏向高錯誤量,而不僅僅是高流量,並尊重使用者若指定了特定工具的選擇。一個低流量但錯誤率高達 90% 的工具可能比一個繁忙且健康的工具排名更高。

第 2 階段 — 每個主要工具內的請求意圖(「為什麼」)

對於每個主要工具,對其請求意圖進行取樣 — [MCP] Tool Call Response 的總量,按 [MCP] Rationale 分組,過濾到該特定工具([MCP] Tool Name is "<tool>"),groupByLimit 約 150。然後閱讀這些意圖並按呼叫者嘗試使用此工具完成什麼來分組,而不是按措辭。指導原則:

  • 在單一工具內,你通常會發現 2-5 個意圖群組,而不是九個 — 工具本身已經縮小了目的範圍。用意圖來命名它們(例如,對於一個 query_chart 工具:「即時儀表板重新整理」、「臨時探索」、「排程報表生成」)。
  • 按呼叫量加權(每個請求意圖值都攜帶其總數),而不是按不同的字串。
  • 注意一個垃圾群組:「佔位符」、「忽略」、「無操作」、「測試」、「虛擬資料」、單個字母。其大小是一個意圖衛生(rationale-hygiene)的發現,並且垃圾不得污染真正的意圖。
  • 像「速率限制後重試」/「正在重試 X」這樣的請求意圖表示重試迴圈 — 請註明。
  • 非英文的請求意圖是正常的;按意義分組。
  • 計算每個工具的請求意圖覆蓋率(該工具呼叫中具有非空請求意圖的比例)。如果這個比例很低(<50%),則意圖只能描述一部分 — 請說明,並且「在儀器化階段改善請求意圖覆蓋率」本身就會成為一個建議。
  • 計算每個工具的主要意圖佔比(最大的意圖群組佔該工具請求意圖覆蓋呼叫量的百分比)。這是集中度信號:約 90% 表示該工具服務於一項工作,你可以針對它進行積極的最佳化(圍繞該路徑收緊架構/描述);均勻分佈(主要意圖約 30%)表示該工具過載,可能需要拆分,或者其錯誤將分散在不同的意圖之間。報告這個數字,當主要意圖佔主導地位時,在工具旁邊命名它。

跨工具工作流程(次要): 一些請求意圖描述了一個多工具目標(「在重新整理儀表板之前解析圖表 ID」)。當一個意圖明顯跨越工具時(例如 search_events → create_chart → create_dashboard),在跨領域章節中將其作為一個工作流程指出 — 這是純粹按工具檢視唯一會遺漏的事情。

第 3 階段 — 每個工具的錯誤深入分析

對於每個主要工具,執行(過濾到該工具 + [MCP] Is Error is "true"):

  • 按 [MCP] Error Message 分組 → 為什麼失敗
  • 可選地按 [MCP] Error Type(returned_error 與 thrown_exception)拆分,當訊息不明確時 — 崩潰和格式良好的拒絕都會引發 [MCP] Is Error,但只有一個是該工具中的錯誤。

當一個工具具有來自第 2 階段的主導意圖群組時,通過請求意圖(加入 contains 過濾器)來限定錯誤,以獲得「此意圖以這種方式失敗」的句子。

將每個顯著的錯誤訊息分類為一個原型 — 原型決定修復方式:

原型特徵修復模式
過時/幻覺的工具名稱[MCP] Tool Call Rejected 且 [MCP] Attempted Tool Name = 一個重新命名或聽起來合理的工具名稱為重新命名的工具提供伺服器端別名;拒絕回應中命名最接近的真實工具,以便代理一次性自我修正
缺少必要參數驗證錯誤,「Required」,路徑命名字段放寬架構(接受單一值或陣列,加上預設值),或使工具描述說明要求,以便代理在呼叫前就能做對
架構形狀不匹配「Expected object, received string」等在伺服器端加入強制轉換,或在工具描述中加入內聯範例
硬限制衝突「Maximum of N …」, 「too_big」提高限制,在伺服器端自動分塊,或在參數描述中說明限制 — 代理目前只能透過失敗來了解限制
範圍/保留違規「time range too large」, 「does not retain data before …」自動強制轉換(例如降低粒度)而不是報錯;在上下文負載中宣告保留/範圍限制
因果循環參數一個上下文/發現工具需要它本身存在的 ID 才能提供使發現工具在沒有必要參數的情況下也能工作,從驗證權杖中獲取預設值
權限被拒絕角色/權限相關語言不同的錯誤類別,以便「不允許」與「損壞」可區分;通常也表明文件/入門教程存在缺口
重複排程錯誤每天在同一個工具上重複相同的訊息如果是內部工具,修復任務的呼叫端;對於產品,標記為默默退化的自動化 — 沒有人會監看對話視窗
瞬態/上游錯誤5xx, 逾時, 速率限制在錯誤正文中提供重試後提示;檢查重試是否實際發生(參見迴圈漏斗)

最佳的錯誤訊息會說明修復方式(「請使用 start >= … 重新執行」)。將每個高使用量的錯誤訊息以此標準衡量 — 「讓這個錯誤訊息和你最好的那個一樣可執行」通常是個合理的建議。

第 4 階段 — 可選的上下文指標

如果時間允許則加入;它們能讓故事更清晰:

  • 重複錯誤迴圈: 3 步驟漏斗,每個步驟都是 [MCP] Tool Call Response 且 [MCP] Is Error is "true",保持 [MCP] Tool Name 不變,轉換視窗約 1 小時。顯示有多少比例報錯的使用者會在同一個工具上陷入迴圈。(步驟不必是連續的事件 — 指「一小時內同一個工具上的 3+ 錯誤」,而不是「3 個連續事件」。)
  • 錯誤 → 復原: 2 步驟漏斗,先錯誤後成功,保持工具名稱不變。高復原率 + 高迴圈率加在一起表示成本是浪費的權杖/延遲,而不是使用者放棄 — 這是一個實質上不同的結論。
  • 客戶端組合: 按 [MCP] Client Name 分組的不重複數量。大量的「未知」佔比或幾乎重複的客戶端名稱(大小寫、插件前綴變體)是值得報告的儀器化發現。

第 5 階段 — 驗證,然後撰寫

在撰寫之前,至少用第二種方法重新驗證一個標題數字(例如,透過一個單獨的兩個事件總量查詢來驗證整體錯誤率)。從原始總數重新計算你引用的每一個百分比。如果一個數字無法驗證,則刪除它或將其標記為估計值。

報告結構

使用此範本 — 以工具為優先組織:

# MCP 伺服器分析 — <伺服器/專案名稱>

資料:<專案>, <日期範圍>, <N> 次工具呼叫,整體錯誤率 <X>%。
方法說明:工具細項是精確的查詢結果;工具內意圖是從請求意圖經由模型推導得出的(方向性)。被拒絕的呼叫名稱來自 [MCP] Tool Call Rejected。

## 工具一覽
<table: 工具 | 呼叫數 | 錯誤數 | 錯誤率 | 主要意圖 (佔比 %) | 請求意圖覆蓋率>
<如果顯著,請用一行說明被拒絕/嘗試的工具名稱;如果顯著,請指出垃圾請求意圖>

## 深入分析:前 3-5 個工具(按錯誤量排序)
針對每個工具:
**工具:<名稱> — <呼叫數>, <錯誤率> — 用途:<一句話說明>**
- 意圖(此工具內的請求意圖):<群組 : 佔比>, …
- 編號的 1-4 條建議。每條都說明證據(錯誤訊息 + 計數)、原型和具體的修復方法。從能消除最多錯誤量的修復開始。

## 跨領域發現
<跨工具工作流程、迴圈/復原率、客戶端名稱衛生、請求意圖衛生、內部測試流量、…>

## 一句話總結
<能消除最多失敗量的單一變更,並附上數字>

風格:每個主張旁邊都要有數字;逐字引用錯誤訊息(可截斷)以便工程師可以 grep;建議以行動形式表述(「為 query_chart → query_charts 提交別名」),而不是觀察(「工具命名可以改進」)。

輸出中的圖表

在客戶端支援的情況下,使用即席圖表查詢 + 渲染工具(建立一個 eventsSegmentation/funnels 定義,然後渲染它)來渲染支援性的 Amplitude 圖表。要審慎判斷什麼可以、什麼不可以做成圖表:

  • 可製圖 — 任何由查詢支援的內容。 這些是真實的 Amplitude 分段/漏斗結果,因此請渲染它們:按工具劃分的呼叫和錯誤(按 [MCP] Tool Name 分組)、隨時間變化的錯誤率、按 [MCP] Attempted Tool Name 劃分的被拒絕呼叫、每個工具的重複錯誤迴圈和復原漏斗,以及按 [MCP] Client Name 劃分的客戶端組合。工具細項是自然的主角圖表。
  • 不可製圖 — 工具內的意圖群組。 將請求意圖分組為意圖是在此模型中完成的;這些分組在 Amplitude 中並不存在作為一個屬性,因此沒有儲存的「按意圖劃分的呼叫」圖表。將意圖作為一個從請求意圖總數建立的表格來呈現,並清楚地說明意圖數字是模型推導的(方向性),而你渲染的圖表是精確的查詢結果。不要暗示渲染的圖表支援意圖分組。

查詢食譜

所有查詢都是針對第 0 階段的專案 ID 的 eventsSegmentation 或 funnels 定義。將事件/屬性名稱調整為第 0 階段驗證的名稱。已知可行的形狀:

工具細項(第 1 階段):

{"type":"eventsSegmentation","app":"<PROJECT_ID>","name":"[MCP] 按工具劃分的呼叫",
 "params":{"range":"Last 30 Days",
  "events":[{"event_type":"[MCP] Tool Call Response",
    "group_by":[{"type":"event","value":"[MCP] Tool Name"}]}],
  "metric":"totals","countGroup":"User","groupBy":[],"interval":"day"}}

工具錯誤(第 1 階段):

{"type":"eventsSegmentation","app":"<PROJECT_ID>","name":"[MCP] 按工具劃分的錯誤",
 "params":{"range":"Last 30 Days",
  "events":[{"event_type":"[MCP] Tool Call Response",
    "filterType":"event","filters":[{"subprop_type":"event","value":"[MCP] Is Error","op":"is","clause":"true"}],
    "group_by":[{"type":"event","value":"[MCP] Tool Name"}]}],
  "metric":"totals","countGroup":"User","groupBy":[],"interval":"day"}}

被拒絕的呼叫(第 1 階段):

{"type":"eventsSegmentation","app":"<PROJECT_ID>","name":"[MCP] 按嘗試工具名稱劃分的被拒絕呼叫",
 "params":{"range":"Last 30 Days",
  "events":[{"event_type":"[MCP] Tool Call Rejected",
    "group_by":[{"type":"event","value":"[MCP] Attempted Tool Name"}]}],
  "metric":"totals","countGroup":"User","groupBy":[],"interval":"day"}}

工具內請求意圖(第 2 階段): 在 events 中加入一個 filterType 和 filters 陣列,設定 "value":"[MCP] Tool Name","op":"is","clause":"<tool>"。將 group_by 中的 value 改為 "[MCP] Rationale"。

工具內錯誤(第 3 階段): 加入兩個過濾器([MCP] Tool Name 和 [MCP] Is Error),按 [MCP] Error Message 分組。

重複錯誤迴圈漏斗(第 4 階段): 使用 type: funnels,三個步驟(每個步驟:[MCP] Tool Call Response 過濾到同一個工具名稱 + [MCP] Is Error is "true"),轉換視窗 3600 秒。

錯誤 → 復原漏斗(第 4 階段): type: funnels,兩個步驟:場景 A 是錯誤,場景 A 是成功(同一個工具名稱)。轉換視窗 3600 秒。

客戶端組合(第 4 階段): eventsSegmentation,事件 [MCP] Tool Call Response,按 [MCP] Client Name 分組,metric: uniques。

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

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

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.

相關技能