Agent Skillsphuryn/pm-skills › metrics-dashboard

metrics-dashboard

GitHub

用于设计产品指标看板,定义关键指标、数据源、可视化类型及告警阈值。指导用户构建包含北极星指标、输入指标和健康指标的完整监控体系,确保指标可行动且能驱动业务决策。

pm-product-discovery/skills/metrics-dashboard/SKILL.md phuryn/pm-skills

Trigger Scenarios

创建指标看板 定义KPIs 设置产品分析 构建数据监控计划

Install

npx skills add phuryn/pm-skills --skill metrics-dashboard -g -y
More Options

Non-standard path

npx skills add https://github.com/phuryn/pm-skills/tree/main/pm-product-discovery/skills/metrics-dashboard -g -y

Use without installing

npx skills use phuryn/pm-skills@metrics-dashboard

指定 Agent (Claude Code)

npx skills add phuryn/pm-skills --skill metrics-dashboard -a claude-code -g -y

安装 repo 全部 skill

npx skills add phuryn/pm-skills --all -g -y

预览 repo 内 skill

npx skills add phuryn/pm-skills --list

SKILL.md

Frontmatter
{
    "name": "metrics-dashboard",
    "description": "Define and design a product metrics dashboard with key metrics, data sources, visualization types, and alert thresholds. Use when creating a metrics dashboard, defining KPIs, setting up product analytics, or building a data monitoring plan."
}

Product Metrics Dashboard

Design a comprehensive product metrics dashboard with the right metrics, visualizations, and alert thresholds.

Context

You are designing a metrics dashboard for $ARGUMENTS.

If the user provides files (existing dashboards, analytics data, OKRs, or strategy docs), read them first.

Domain Context

Metrics vs KPIs vs NSM: Metrics = all measurable things. KPIs = a few key quantitative metrics tracked over a longer period. North Star Metric = a single customer-centric KPI that is a leading indicator of business success.

4 criteria for a good metric (Ben Yoskovitz, Lean Analytics): (1) Understandable — creates a common language. (2) Comparative — over time, not a snapshot. (3) Ratio or Rate — more revealing than whole numbers. (4) Behavior-changing — the Golden Rule: "If a metric won't change how you behave, it's a bad metric."

8 metric types: Vanity vs Actionable (only actionable metrics change behavior), Qualitative vs Quantitative (WHAT vs WHY — you need both; never stop talking to customers), Exploratory vs Reporting (explore data to uncover unexpected insights), Lagging vs Leading (leading indicators enable faster learning cycles, e.g. customer complaints predict churn).

5 action steps: (1) Audit metrics against the 4 good-metric criteria. (2) Update dashboards — ensure all key metrics are good ones. (3) Identify vanity metrics — be careful how you use them. (4) Classify leading vs lagging indicators. (5) Pick one problem and dig deep into the data.

For case studies and more detail: Are You Tracking the Right Metrics? by Ben Yoskovitz

Instructions

  1. Identify the metrics framework — organize metrics into layers:

    North Star Metric: The single metric that best captures core value delivery

    Input Metrics (3-5): The levers that drive the North Star

    Health Metrics: Guardrails that ensure overall product health

    Business Metrics: Revenue, cost, and unit economics

  2. For each metric, define:

    Metric Definition Data Source Visualization Target Alert Threshold
    [Name] [Exact calculation: numerator/denominator, time window] [Where the data comes from] [Line chart / Bar / Number / Funnel] [Goal value] [When to trigger an alert]
  3. Design the dashboard layout:

    ┌─────────────────────────────────────────────┐
    │  NORTH STAR: [Metric] — [Current Value]     │
    │  Trend: [↑/↓ X% vs last period]             │
    ├──────────────────┬──────────────────────────┤
    │  Input Metric 1  │  Input Metric 2          │
    │  [Sparkline]     │  [Sparkline]             │
    ├──────────────────┼──────────────────────────┤
    │  Input Metric 3  │  Input Metric 4          │
    │  [Sparkline]     │  [Sparkline]             │
    ├──────────────────┴──────────────────────────┤
    │  HEALTH: [Latency] [Error Rate] [NPS]       │
    ├─────────────────────────────────────────────┤
    │  BUSINESS: [MRR] [CAC] [LTV] [Churn]        │
    └─────────────────────────────────────────────┘
    
  4. Set review cadence:

    • Daily: Operational health (errors, latency, critical flows)
    • Weekly: Input metrics and engagement trends
    • Monthly: North Star, business metrics, OKR progress
    • Quarterly: Strategic review and metric recalibration
  5. Define alerts:

    • What thresholds trigger investigation?
    • Who gets alerted and through what channel?
    • What's the expected response time?
  6. Recommend tools based on the user's context:

    • Amplitude, Mixpanel, PostHog for product analytics
    • Looker, Metabase, Mode for SQL-based dashboards
    • Datadog, Grafana for operational health

Think step by step. Save the dashboard specification as a markdown document.


Further Reading

Version History

  • 18468a9 Current 2026-07-25 10:32

Same Skill Collection

pm-ai-shipping/skills/intended-vs-implemented/SKILL.md
pm-data-analytics/skills/ab-test-analysis/SKILL.md
pm-data-analytics/skills/cohort-analysis/SKILL.md
pm-data-analytics/skills/sql-queries/SKILL.md
pm-execution/skills/brainstorm-okrs/SKILL.md
pm-execution/skills/create-prd/SKILL.md
pm-execution/skills/dummy-dataset/SKILL.md
pm-execution/skills/job-stories/SKILL.md
pm-execution/skills/outcome-roadmap/SKILL.md
pm-execution/skills/pre-mortem/SKILL.md
pm-execution/skills/prioritization-frameworks/SKILL.md
pm-execution/skills/release-notes/SKILL.md
pm-execution/skills/retro/SKILL.md
pm-execution/skills/sprint-plan/SKILL.md
pm-execution/skills/stakeholder-map/SKILL.md
pm-execution/skills/strategy-red-team/SKILL.md
pm-execution/skills/summarize-meeting/SKILL.md
pm-execution/skills/test-scenarios/SKILL.md
pm-execution/skills/user-stories/SKILL.md
pm-execution/skills/wwas/SKILL.md
pm-go-to-market/skills/beachhead-segment/SKILL.md
pm-go-to-market/skills/competitive-battlecard/SKILL.md
pm-go-to-market/skills/growth-loops/SKILL.md
pm-go-to-market/skills/gtm-motions/SKILL.md
pm-go-to-market/skills/gtm-strategy/SKILL.md
pm-go-to-market/skills/ideal-customer-profile/SKILL.md
pm-market-research/skills/competitor-analysis/SKILL.md
pm-market-research/skills/customer-journey-map/SKILL.md
pm-market-research/skills/market-segments/SKILL.md
pm-market-research/skills/market-sizing/SKILL.md
pm-market-research/skills/sentiment-analysis/SKILL.md
pm-market-research/skills/user-personas/SKILL.md
pm-market-research/skills/user-segmentation/SKILL.md
pm-marketing-growth/skills/marketing-ideas/SKILL.md
pm-marketing-growth/skills/north-star-metric/SKILL.md
pm-marketing-growth/skills/positioning-ideas/SKILL.md
pm-marketing-growth/skills/product-name/SKILL.md
pm-marketing-growth/skills/value-prop-statements/SKILL.md
pm-product-discovery/skills/analyze-feature-requests/SKILL.md
pm-product-discovery/skills/brainstorm-experiments-existing/SKILL.md
pm-product-discovery/skills/brainstorm-experiments-new/SKILL.md
pm-product-discovery/skills/brainstorm-ideas-existing/SKILL.md
pm-product-discovery/skills/brainstorm-ideas-new/SKILL.md
pm-product-discovery/skills/identify-assumptions-existing/SKILL.md
pm-product-discovery/skills/identify-assumptions-new/SKILL.md
pm-product-discovery/skills/interview-script/SKILL.md
pm-product-discovery/skills/opportunity-solution-tree/SKILL.md
pm-product-discovery/skills/prioritize-assumptions/SKILL.md
pm-product-discovery/skills/prioritize-features/SKILL.md

Metadata

Files
0
Version
18468a9
Hash
fa74abf4
Indexed
2026-07-25 10:32

Главная - Вики-сайт
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-20 08:59
浙ICP备14020137号-1 $Гость$