Communitygithub.com

amplitude/builder-skills

在發佈前,此技能可產生 2–3 個內容變體,根據實際 AI 模型回應進行評分,並推薦最有可能獲得引用的版本,再將優勝者推送至 CMS。

builder-skills 是什麼?

這是一項專為內容團隊設計的 AI 代理技能,旨在終結「憑感覺發佈」的決策模式。它會先透過 CMS 探索與連線步驟確保工作流程順暢,然後利用 AI Visibility 工具發掘主題機會,並實際抓取 AI 模型對相關提示的回應作為「評分基準」。接著,它會從不同角度(如教育性、競爭性或使用案例)生成 2–3 個內容變體,並根據提示對齊度、答案直接性、具體性、差距覆蓋率和結構匹配度等五個維度進行評分,產生推薦結果。在推送至 CMS(支援 Sanity、Contentful、HubSpot、WordPress、Ghost 與 Webflow)之前,它會引用「模擬變更」功能讓使用者先行驗證。最終,它會將優勝者的完整文章(包含中繼欄位)建立為草稿並推送至指定的 CMS,同時保留亞軍變體作為未來 A/B 測試的素材。這項技能可與 Claude Code 等工具整合,為資料驅動的內容選擇提供端到端的自動化流程。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/amplitude/builder-skills/tree/HEAD/content-marketing-skills/skills/simulation-backed-publisher

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

模擬驅動的發佈者

你正在幫助一個內容團隊停止猜測。與其發佈一篇內容然後希望它被引用,這個技能會生成 2–3 個截然不同的變體,針對 AI 模型在該主題上實際的發言進行評分,並在一個字都還沒發佈之前,推薦最有可能獲得引用的版本。


步驟 0 — CMS 探索(每次會話開始時執行一次)

在做任何其他事情之前,先找出優勝內容將落腳何處。這可以避免工作流程結尾出現複製貼上的死胡同。

檢查已連接的 CMS 工具

掃描你當前上下文中的可用工具。已知的 CMS MCP 模式:

CMS要尋找的工具名稱模式
Sanitysanity, create_documents_from_markdown, patch_document_from_markdown
Contentfulcontentful, create_entry, update_entry
HubSpot CMShubspot, update_blog_post, create_blog_post
WordPresswordpress, wp_update_post, wp_create_post
Ghostghost, update_post, create_post
Webflowwebflow, update_cms_item, create_cms_item

如果 CMS MCP 已連接: 用一行文字確認: 「我看到 [CMS] 已連接 — 完成後我會將優勝變體以草稿形式推送過去。聽起來不錯吧?」 然後繼續步驟 1。

如果沒有任何東西連接: 簡潔地問一次:

「在我們開始之前 — 你發佈到哪個 CMS?我可以將優勝變體以草稿形式直接推送進去,而不是只給你一段文字貼上。」

提供選項:Sanity · Contentful · HubSpot · WordPress · Webflow · Ghost · 其他 · 「只要給我內容就好」

然後根據他們的回答提供量身打造的設定建議(與 prompt-gap-to-publish 中的指引相同)。不要因為設定而卡住 — 立即開始分析,並說明在他們連接完成時你已經準備好推送。


步驟 1 — 識別要模擬的機會

使用 list_ai_visibility_org_brands 來識別品牌(或使用使用者指定的品牌)。

使用者可能已經帶著一個機會來到這裡(例如,從執行 prompt-gap-to-publish 或 competitor-prompt-hijacker 得來)。如果是這樣,直接使用那個機會。

如果不是,使用 get_ai_visibility_topics 搭配所選的 orgBrandId,按照標準評分啟發法:相關性 > 60% 且能見度 < 40% 的主題,來呈現前 3–5 個機會。簡要地呈現它們,並詢問要模擬哪一個。

在建立變體之前,與使用者確認機會:

「我將為 [機會標題] 生成變體。目標提示是:[2–3 個範例提示]。這符合你想測試的內容嗎?」


步驟 2 — 載入 LLM 回應上下文

針對所選的機會,使用以下方式拉取實際的 AI 模型回應:

  • 使用相關的 topicId 呼叫 get_ai_visibility_prompts 來獲取提示列表
  • 為 responseCount 最高的前 5–8 個提示,呼叫 get_ai_visibility_prompt_responses

仔細閱讀每個回應。這是基本事實 — 正是 AI 模型在回答這個領域的問題時目前所說的話。你的變體將根據這個上下文進行評分。

從回應中提取:

  • AI 模型使用了什麼語言和框架?(詞彙、問題格式、關鍵術語)
  • 他們提出了什麼主張?(統計數據、產品功能、命名工具)
  • 什麼東西缺失或薄弱?(AI 回應含糊、迴避或引用弱來源的領域)
  • 哪些品牌出現在答案中?(不該被引用卻出現的競爭對手)
  • 回應使用的是什麼格式?(項目符號列表、散文、表格 — 你的內容應該匹配)

這個上下文是你將建立的變體的評分標準。

同時呼叫 get_ai_visibility_sentiment 以了解語氣:AI 對該主題的品牌情緒是正面、中性還是負面?變體應設計來強化正面情緒或反擊負面框架。


步驟 3 — 生成 2–3 個變體

建立 2–3 個截然不同的內容變體。每個變體應採用有意義的不同角度或結構 — 而不只是用不同引言包裝的相同內容。小幅改寫對學習沒有幫助;真正的替代方案才有。

變體區分軸線

選擇與機會最相關的軸線:

角度:教育性(「X 如何運作」)vs. 競爭性(「Amplitude 與替代方案」)vs. 使用案例(「[特定客群] 的最佳 X」)

開頭:數據優先(以基準或統計數據開頭)vs. 問題優先(以痛點開頭)vs. 答案優先(以核心問題的直接答案開頭)

深度:全面指南(長篇,涵蓋所有內容)vs. 精準具體(針對單一問題的焦點回答)vs. 互動/結構化(大量使用表格、比較矩陣、常見問題)

框架:品牌主導(「這是 Amplitude 如何做 X」)vs. 類別中立(「這是產品分析如何運作 — 以及 Amplitude 的位置」)vs. 競爭性(「X 工具的誠實指南」)

變體格式

對於每個變體,請撰寫:

  1. 完整的 H1 和開頭段落(AI 模型權重最高的部分)
  2. H2 大綱,包含每個區段內容的 1–2 句描述
  3. 一個完整撰寫的區段 — 最重要的 H2,完全寫好
  4. 完整的常見問題區塊 — 4–6 組問答,使用步驟 2 中的確切提示語言
  5. 中繼欄位:metaTitle、metaDescription、slug

清楚地標記它們:變體 A、變體 B、變體 C。


步驟 4 — 針對 LLM 上下文為每個變體評分

現在根據步驟 2 中實際的 AI 模型回應來評估每個變體。這就是模擬。在以下維度上為每個變體評分(1 到 5 分):

提示對齊度(1–5):變體的 H1、開頭和常見問題是否直接匹配 AI Visibility 提示中使用的語言和問題格式?如果變體緊密反映提示語言則給 5 分;如果使用不同的術語或埋藏答案則給 1 分。

答案直接性(1–5):變體是否在前兩句就回答了核心問題?如果是則給 5 分;如果答案出現在開頭段落內則給 3 分;如果讀者需要滾動則給 1 分。

具體性(1–5):變體是否做出了具體、可驗證的主張(「Amplitude 在不到 100ms 的會話中捕獲憤怒點擊、滾動深度和熱圖」)而不是一般性的主張?如果每個主要主張都很具體則給 5 分;如果主張大多是一般性的則給 1 分。

差距覆蓋率(1–5):變體是否涵蓋了當前 AI 回應薄弱或缺失的領域?如果它填補了所有已識別的差距則給 5 分;如果它基本上重複了 AI 模型已經說過的話則給 1 分。

結構匹配度(1–5):變體的格式是否匹配 AI 模型呈現此主題的方式?如果結構反映了回應格式(例如,AI 模型使用項目符號列表,則變體也突出地使用它們)則給 5 分。

將分數以表格呈現:

維度變體 A變體 B變體 C
提示對齊度453
答案直接性345
具體性534
差距覆蓋率443
結構匹配度354
總計192119

清楚地說明建議:「變體 B 得分最高(21/25)。其常見問題區塊反映了來自 AI Visibility 的確切提示語言,並且在第一句就回答了核心問題。建議發佈變體 B。」


步驟 5 — 模擬變更檢查點

在推送至 CMS 之前,參考 AI Visibility 內建的「模擬變更」功能:

「AI Visibility 有一個『模擬變更』功能,它會針對即時 AI 模型提示運行你的內容,並在發佈前預測引用改善情況。以下是你要貼上的內容:[優勝變體的開頭 + 常見問題區塊的完整文字]

要執行它:打開 AI Visibility → 選擇你的品牌 → 進入模擬變更 → 貼上內容 → 運行模擬。我會等待,或者現在就推送草稿,你可以並行進行模擬。」

讓使用者決定。如果他們想先模擬,暫停並提供要貼上的確切文字。如果他們準備好推送,繼續步驟 6。

如果模擬結果出來後,他們改變了關於使用哪個變體的想法,請在推送前完整生成修改後的變體。


步驟 6 — 完整建立優勝者

一旦選擇了變體(無論是否使用模擬結果),撰寫完整的文章:

  • 從完整的 H1 到最終的行動呼籲 — 無佔位符,無「[在此新增區段]」
  • 大綱中的所有 H2 區段,完整撰寫
  • 完整的常見問題區塊(4–6 組問答)
  • 中繼欄位:metaTitle、metaDescription、slug
  • 中繼資料中的「最後更新:[當前月份/年份]」備註

同時將亞軍變體儲存為結尾的 Markdown 區塊 — 清楚地標記為替代方案。這些可用於發佈後的 A/B 測試,或改編用於不同的渠道。


步驟 7 — 推送至 CMS

使用你在步驟 0 中發現的資訊。這是一個新文件(建立操作,不是更新),除非使用者指定他們正在更新現有頁面。

Sanity — 使用 create_documents_from_markdown 搭配優勝變體。設定 _type 以符合部落格/文章結構。如果不確定,詢問:「你的 Sanity 結構中文章的文件類型是什麼?」未經明確指示,切勿使用 publish_documents。

Contentful — 使用 create_entry,contentType 匹配他們的文章類型。設定 fields.title、fields.slug、fields.body。保留 published: false。

HubSpot — 使用 create_blog_post,搭配 state: DRAFT。包含中繼描述和 slug。

WordPress — 使用 wp_create_post,搭配 status: draft。將 H1 對應到 title,正文對應到 content。

Ghost — 使用 create_post,搭配 status: draft。包含 slug、title、html 或 lexical,以及 meta_description。

Webflow — 使用 create_cms_item,目標是部落格集合。將欄位對應到集合的結構(如果不明顯,請詢問使用者欄位名稱)。

推送後,確認:「完成 — [文章標題] 已儲存為 [CMS] 中的草稿。這是 ID/URL:[連結]。亞軍變體在下面的 Markdown 中 — 保留下來以備將來使用或用於 A/B 測試。」

即使 CMS 推送成功,也始終輸出優勝變體的 Markdown 備份,以及亞軍替代方案。


為什麼要在發佈前模擬

每一篇內容都是一個賭注。模擬驅動的發佈將這個賭注變成一個合理的選擇:

  • 提示對齊度是引用最強的單一預測因子。 反映 AI 模型在提示中使用的確切語言的內容,將比以通用 SEO 語言撰寫的內容更可靠地被檢索和引用。
  • 答案直接性會隨時間累積。 頁面的第一句話被 AI 檢索賦予了不成比例的權重。在第一句回答的變體將持續勝過需要三段才能切入主題的變體。
  • 差距覆蓋率是最快的引用勝利。 如果某個主題的 AI 回應在特定子問題上薄弱或含糊,第一個具體回答它的頁面將成為首選引用。
  • 變體暴露假設。 撰寫同一內容的三個版本迫使團隊明確表達他們真正相信的受眾需求 — 而評分結果往往讓他們感到驚訝。

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 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