Agent Skills
› mohitagw15856/pm-claude-skills
› product-health-analysis
product-health-analysis
GitHub将原始产品指标转化为清晰的健康叙事，通过对比目标与趋势，分析获取、激活、参与和留存四个维度。输出包含状态评级、关键观察、根因假设及优先行动的结构化报告，辅助非数据利益相关者决策。
Trigger Scenarios
分析产品健康状况
审查关键指标表现
调查性能问题
生成健康报告
评估产品市场契合度信号
Install
npx skills add mohitagw15856/pm-claude-skills --skill product-health-analysis -g -y
SKILL.md
Frontmatter
{
"name": "product-health-analysis",
"homepage": "https:\/\/mohitagw15856.github.io\/pm-claude-skills\/skill\/product-health-analysis.html",
"metadata": {
"openclaw": {
"emoji": "📊"
}
},
"description": "Interpret product metrics against goals and surface actionable signals. Use when asked to analyse product health, review key metrics, investigate a performance issue, produce a health report, or assess product-market fit signals. Produces a structured health report with RAG status, trend analysis, root cause hypotheses, and prioritised actions."
}
Product Health Analysis Skill
Transform raw metrics data into a clear health narrative — what's working, what's not, and what needs immediate attention.
Required Inputs
Ask the user for these if not provided:
- Metrics data (current values for key metrics — even rough numbers work)
- Targets or benchmarks (OKR targets, historical baselines, or industry benchmarks)
- Period (week / month / quarter being analysed)
- Product area or segment (are we looking at the whole product or a specific feature?)
Metrics Framework
Analyse across four layers:
- Acquisition — new users, source quality, CAC trends
- Activation — time to first value, onboarding completion rates
- Engagement — DAU/MAU, feature adoption, session depth
- Retention — D1/D7/D30 retention, churn rate, resurrection rate
Process
- For each metric, compare: current period vs. previous period, current vs. target
- Flag anything more than 10% off target as requiring investigation
- Look for correlations — does a drop in activation explain a retention dip 2 weeks later?
- Write a plain-English health summary (no jargon) suitable for sharing with non-data stakeholders
- Recommend top 3 areas for immediate investigation with suggested diagnostic steps
- Validate — Confirm every flagged metric has a plausible root cause hypothesis, not just a raw number, and every recommended action has a specific owner or team
Output Structure
Product Health Report — [Period]
Overall Health: 🟢 On Track / 🟡 Watch / 🔴 Action Required
| Metric | Current | Target | vs. Last Period | Status |
|---|---|---|---|---|
| [metric] | [value] | [target] | [+/-%] | [🟢/🟡/🔴] |
Key Observations: [3-5 bullet observations written in plain English]
Areas Requiring Investigation:
- [Metric + hypothesis + suggested diagnostic]
- [Metric + hypothesis + suggested diagnostic]
- [Metric + hypothesis + suggested diagnostic]
Recommended Actions: [Specific next steps with owners and timelines]
Scoring Rubric (0–40)
Score any output of this skill before handing it over; 32+ is ship-quality.
| Dimension | 0 | 5 | 10 |
|---|---|---|---|
| Target & trend discipline | Metrics shown as bare snapshots; no targets or period-over-period comparison | Most metrics have targets and trends, but some RAG statuses don't follow from the numbers or targets are accepted uncritically | Every metric has target, trend, and a status that follows from both — and at least one target is itself challenged if it's no longer meaningful |
| Root cause depth | Movements listed without explanation ("activation dropped 27pts") | Flagged metrics have hypotheses, but they're generic ("onboarding friction") with no diagnostic to confirm them | Every flagged metric has a specific, falsifiable hypothesis plus a named diagnostic step, and at least one cross-metric correlation (e.g. activation → retention lag) is drawn |
| Segment honesty | Only blended aggregates reported; opposing segment trends invisible | Some segment cuts shown, but the headline observations still lean on averages that hide divergence | Every material aggregate is decomposed where segments diverge, and the divergence itself is surfaced as a finding, not a footnote |
| Verdict & actionability | No overall rating, or a rating asserted without evidence; actions missing or ownerless | Overall RAG present and roughly justified; actions exist but some lack owners, dates, or a link to a flagged metric | Overall rating argued from specific evidence (including against the good news), and every action has a named owner, a date, and traces to an investigation or observation |
Quality Checks
- Every metric includes both a target and a trend (not just a snapshot)
- At least one correlation is drawn between metrics (e.g., activation → retention)
- Every flagged metric has a root cause hypothesis, not just "it dropped"
- Observations are written for a non-technical stakeholder (no raw query language or data jargon)
- Overall health rating is justified with specific evidence
Anti-Patterns
- Do not report a single aggregate metric without segment breakdowns — averages hide opposing trends
- Do not flag a metric as healthy just because it is above the target — check if the target itself is meaningful
- Do not list metric movements without root cause hypotheses — observations without explanations are not analysis
- Do not mix product health metrics with business KPIs without explaining the relationship between them
- Do not omit recommended actions — a health report that only describes problems without prioritised next steps is incomplete
Version History
- 54fad50 Current 2026-07-19 12:28
