Business Root Cause Analysis
Use when diagnosing business metric changes or anomalies such as GMV decline, conversion drop, retention loss, churn increase, revenue change, lead decline, or active user fluctuation with a structured root cause analysis plan. 中文触发词:指标归因、为什么下降、异常排查、GMV 下滑、指标波动原因。
Install
npx skills add shisuidata/ss-data-skills --skill business-root-cause-analysisgit clone --depth 1 https://github.com/shisuidata/ss-data-skills.git /tmp/ss-data-skills
mkdir -p ~/.claude/skills
cp -r /tmp/ss-data-skills/skills/business-root-cause-analysis ~/.claude/skills/business-root-cause-analysisPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Business Root Cause Analysis ## 目标 把“某个业务指标变差了”拆成可验证的归因假设、数据检查路径和行动建议。 这个 Skill 不负责凭空给出唯一原因,而是帮助用户建立一套可执行的排查框架。 ## 使用场景 使用这个 Skill,当用户需要: - 分析 GMV、转化率、留存、活跃、收入、线索、续费等指标异常 - 把老板的一句“为什么下降了”拆成分析任务 - 为业务复盘准备归因树和验证路径 - 判断是流量、转化、结构、供给、价格、产品体验还是数据口径问题 - 给数据分析师或业务负责人输出下一步排查清单 ## 不适用场景 不要使用这个 Skill 处理: - 没有任何指标、时间范围或对比基准的泛泛讨论 - 只做单一有序路径转化,应使用 `funnel-analysis` - 只做留存矩阵,应使用 `retention-cohort-analysis` - 只写最终报告,应使用 `data-analysis-report-writer` - 需要判断 SQL 是否算错,应使用 `sql-reviewer` - 有随机分组的实验结果,应使用 `ab-test-analysis` - 指标口径本身有争议,先用 `metric-definition-reviewer` - 数据能不能用还不清楚,先用 `exploratory-data-analysis` - 需要行业或竞品的外部信息,应使用 `market-research-analyst` ## 输入信息 最少输入: - 异常指标 - 异常时间范围 - 对比基准:环比、同比、上周同期、实验对照等 - 已知现象或初步数据 推荐输入: - 指标口径和计算逻辑 - 可用维度:渠道、地区、端、用户类型、商品、套餐、内容类型等 - 相关业务事件:活动、改版、投放、价格、库存、算法、系统故障 - 历史波动范围 - 数据表、看板或 SQL 结果 - 日粒度时间序列 CSV、按时期和维度汇总的 CSV(可以直接用脚本计算) - 业务方已经排除或怀疑的原因 ## 上下文建议 优先使用这些模板准备上下文: - [分析上下文模板](../../context/templates/analysis-context.md):适合指标异常和专题归因 - [指标上下文模板](../../context/templates/metric-context.md):适合口径不清或指标争议 - [报告上下文模板](../../context/templates/report-context.md):适合后续沉淀成复盘报告 如果问题明显属于某个行业,建议补充行业上下文: - [电商行业上下文](../../context/industries/ecommerce.md) - [SaaS 行业上下文](../../context/industries/saas.md) - [内容社区行业上下文](../../context/industries/content-community.md) 上下文不足时,先输出假设树和验证数据需求,不要直接断言原因。 ## 分析流程 1. 确认异常是否真实:口径、数据延迟、采集、分母变化、节假日和自然波动。 2. 拆解指标公式,识别核心驱动因子。 3. 按时间、结构、人群、渠道、地域、产品、供给、体验等维度定位异常集中点。 4. 将可能原因分成数据问题、流量问题、转化问题、结构问题、供给问题、产品问题、外部因素。
Details
- Skill name
business-root-cause-analysis- Repository
- shisuidata/ss-data-skills
- Path
skills/business-root-cause-analysis/SKILL.md- License
- MIT
- Repo updated
- 8 November 2026
FAQ
What does the Business Root Cause Analysis skill do?
Use when diagnosing business metric changes or anomalies such as GMV decline, conversion drop, retention loss, churn increase, revenue change, lead decline, or active user fluctuation with a structured root cause analysis plan. 中文触发词:指标归因、为什么下降、异常排查、GMV 下滑、指标波动原因。
How do I install the Business Root Cause Analysis skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add shisuidata/ss-data-skills --skill business-root-cause-analysis. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Business Root Cause Analysis popular?
It lives in shisuidata/ss-data-skills, which has 9 GitHub stars and 0 forks.
Related skills
Ab Test Analysis
9shisuidata/ss-data-skills
Use when designing, checking, or interpreting A/B tests and experiments. Computes significance, confidence intervals, sample ratio mismatch, power, CUPED, and sample size with a bundled zero-dependency script, then judges validity risks, guardrails, and ship/iterate/rollback decisions and renders an HTML experiment report. 中文触发词:A/B 实验、AB 测试、实验解读、显著性、样本量计算、能不能全量。
Daily Report Writer
9shisuidata/ss-data-skills
Use when writing a concise daily report, daily worklog, standup update, shift handoff, or end-of-day summary for data analysis, data development, BI, governance, or operations work. 中文触发词:日报、日终同步、站会发言、值班交接。
Dashboard Reviewer
9shisuidata/ss-data-skills
Use when reviewing whether a BI dashboard, management dashboard, metric board, or data product page can support business decisions with clear metrics, trustworthy definitions, and actionable drill-down paths. 中文触发词:看板审查、BI 看板优化、经营看板改版、报表没人看。
Paddle Customer Portal
9PaddleHQ/paddle-agent-skills
Mint a Paddle customer portal session URL from a Next.js Server Action — the portal-vs-custom-billing-screen trade-off, auth, ownership, URL structure (overview vs deep links), and the security model.
Apify Competitor Intelligence
9huytran1120/vietnam-agentic-skills
Analyze competitor strategies, content, pricing, ads, and market positioning across Google Maps, Booking.com, Facebook, Instagram, YouTube, and TikTok.
Paddle Pricing Pages
9PaddleHQ/paddle-agent-skills
Render country-localized prices on a Next.js pricing page using Paddle.js PricePreview — country detection, billing frequency toggle, and currency formatting.
Browse the most popular Claude skills, all marketing, sales & business skills, or write your own with the skills generator.