Communitygithub.com

amplitude/builder-skills

Analiza en profundidad paneles de Amplitude mediante el análisis de gráficos clave, la identificación de las principales áreas de preocupación y conclusiones, la detección de anomalías y la explicación de cambios utilizando tendencias de comentarios de clientes.

¿Qué es builder-skills?

Esta habilidad para agentes de IA, como Claude Code, permite a los usuarios analizar en profundidad paneles de Amplitude. Al recibir una URL o ID de un panel, la herramienta recupera la estructura del panel y los datos de todos los gráficos asociados. Utiliza un proceso paso a paso para priorizar los gráficos KPI principales, detectar patrones (como cambios de tendencia en series temporales, caídas en embudos o concentraciones en gráficos de barras) y contextualiza los hallazgos con comentarios de usuarios cuando se detectan anomalías significativas. La habilidad sintetiza los resultados en un resumen estructurado que incluye el estado general del panel, áreas de preocupación, conclusiones clave y recomendaciones accionables con prioridades. Sigue las mejores prácticas para ser exhaustivo pero conciso, referenciar gráficos específicos y evitar inferencias a partir de datos incompletos.

Compatible con~Claude Code~Codex CLI~Cursor
Part ofDesign & UI
npx skills add https://github.com/amplitude/builder-skills/tree/HEAD/analytics-skills/skills/analyze-dashboard
Ver original→Ver todas las habilidades

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentación

Analizar Panel

Cuándo Usarlo

  • Preparación de reuniones: Sintetiza un panel en puntos de discusión antes de una revisión o reunión ejecutiva
  • Detección de patrones entre gráficos: Encuentra correlaciones entre múltiples gráficos que son difíciles de ver manualmente
  • Investigación de paneles: Un número clave se movió en un gráfico dentro de este panel y deseas explicar por qué
  • Conectar cuantitativo con cualitativo: Comprende si los comentarios de los usuarios explican las tendencias que estás viendo
  • Incorporación a paneles desconocidos: Ponte al día sobre lo que rastrea un panel y su estado actual

Instrucciones

Paso 0: Identificar el ID del Panel

Si el usuario proporciona una URL, usa Amplitude:getting_data_from_url para obtener el ID del panel

Paso 1: Recuperar el Panel

Usa Amplitude:get_dashboard con el ID del panel para obtener la estructura completa y los IDs de los gráficos.

Paso 2: Consultar Todos los Gráficos

Usa Amplitude:query_charts para obtener datos de hasta 3 gráficos a la vez. Prioriza:

  1. Gráficos KPI principales (generalmente en la parte superior)
  2. Gráficos con cambios recientes
  3. Visualizaciones basadas en tendencias

Paso 3: Analizar Patrones

Al analizar gráficos, enfócate en las señales más relevantes para la toma de decisiones de cada tipo:

  • Fichas KPI: Contexto (período de tiempo, tipo de usuario) y % de cambio si se muestra.
  • Línea / Serie temporal: Tendencias, cambios de pendiente o eventos notables (no ruido en el borde derecho).
  • Embudo: Pasos principales de abandono o retención inesperada. Usa el marco de conversión (barras sólidas), no el marco de abandono, a menos que sea explícitamente relevante.
  • Barras / Categórico: Concentraciones, vacíos o distribuciones sorprendentes.
  • Área apilada: Cambios en el volumen total y composición cambiante a lo largo del tiempo.
  • Retención por intervalo: Compara segmentos en intervalos clave (Día 1, Día 7, Día 30).
  • Retención a lo largo del tiempo: Las cohortes recientes pueden mostrar períodos incompletos (líneas punteadas) porque aún no han completado la ventana de retención; esto NO significa que la retención esté disminuyendo.
  • Tablas: Principales contribuyentes, jugadores dominantes, desequilibrios en la distribución.

Paso 4: Contextualizar con los Comentarios de Usuarios (Opcional)

Si se detectan cambios significativos o anomalías, verifica si los comentarios de los usuarios pueden explicarlos:

  1. Usa Amplitude:get_feedback_insights con:

    • El mismo projectId que el panel
    • dateStart y dateEnd que coincidan con el período de análisis
    • Filtra por tipos relevantes: request, complaint, lovedFeature, bug, painPoint

  2. Busca temas en los comentarios que se correlacionen con los cambios en las métricas:

    • Quejas sobre funciones que coinciden con caídas en el compromiso
    • Reportes de errores que coinciden con caídas en la conversión
    • Funciones amadas que coinciden con aumentos en el uso

  3. Si se encuentra un insight relevante, usa Amplitude:get_feedback_mentions con el insightId para obtener citas específicas de usuarios que ilustren el patrón.

Omite este paso si:

  • No hay fuentes de comentarios configuradas para el proyecto
  • No hay insights que coincidan con el período de tiempo o los cambios observados
  • Los cambios en el panel son menores o esperados

Paso 5: Sintetizar los Hallazgos

Presenta un resumen estructurado:

  1. Estado General: Una línea concisa, procesable y fácil de entender sobre la principal conclusión o conjunto de conclusiones clave del análisis del panel.
  2. Áreas de Preocupación 🚩: Las 1-3 principales urgencias que vale la pena investigar o tendencias de métricas negativas. Si no hay problemas urgentes, es bueno reconocer de forma concisa que no hay áreas urgentes de preocupación para que el lector tenga menos ruido que filtrar.
  3. Conclusiones Clave 💡: Las 1-3 ideas más importantes o sorprendentes del análisis que no se incluyan en las áreas de preocupación.
  4. Recomendaciones: Sección muy concisa que resume hasta las 3 principales recomendaciones accionables específicas (a menos que se indique lo contrario) para hacer seguimiento. Incluye [p0],[p1],[p2],[p3] delante de cada título para ayudar a dimensionar la prioridad, siendo p0 la más urgente y p3 la menos.

Mejores Prácticas

  • Sé exhaustivo en tu investigación y análisis, pero conciso, procesable y respaldado por métricas en tu respuesta.
  • No repitas la misma conclusión varias veces en diferentes secciones.
  • Siempre enlaza los gráficos referenciados usando markdown (por ejemplo, [DAU](https://app.amplitude.com/...)). En modo terminal, no compartas tus fuentes para mantener la respuesta limpia, pero si se te pregunta específicamente, agrupa todas las referencias y enlaces en una sección "Fuentes" al final en el mismo formato markdown (por ejemplo, [DAU y principal conclusión donde se referencia la métrica](https://app.amplitude.com/...)) para mantener la respuesta principal limpia.
  • No cites enlaces exactos completos de Amplitude en las secciones principales. En su lugar, referencia de forma concisa el nombre del gráfico, métrica o entidad para que sea fácil leer las secciones principales.
  • Señala las métricas que cambiaron más del 10% semana a semana
  • Anota cualquier gráfico con problemas de calidad de datos
  • Siempre atribuye los hallazgos a gráficos específicos cuando sea posible
  • Para la sección de Recomendaciones, cada recomendación debe ser solo un punto conciso y procesable, no una visión general larga del tema
  • No recapitules lo que hiciste al final y simplemente termina después de las recomendaciones priorizadas y concisas
  • No infieras tendencias a partir de períodos incompletos o datos no fiables

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

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

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.

Skills relacionados

steipete/sag

ElevenLabs text-to-speech with mac-style say UX.

community

steipete/oracle

Oracle CLI second-model review/debug/refactor/design with selected files, dry-run token checks, API or browser engine.

community

steipete/peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

community

mattpocock/design-an-interface

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

community

mattpocock/prototype

Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route.

community

mattpocock/grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

community