Data & Analytics Skills

> Create and manage Kibana Dashboards and visualizations. Use when you need to define dashboards and visualizations declaratively, version control them, or automate their deployment.

> Create Vega and Vega-Lite visualizations with ES|QL data sources in Kibana. Use when building custom charts, dashboards, or programmatic panel layouts beyond standard Lens charts.

Analyze Zephyr test case coverage for a Jira user story and produce a QE management report with metrics, risk scoring, and prioritized recommendations.

Enforce structured JSON logging, OpenTelemetry distributed tracing, and RED metrics across backend services. Use when adding request correlation, setting up tracing spans, defining SLO burn-rate alerts, or instrumenting middleware.

Interpret learning analytics data and translate dashboard findings into actionable teaching decisions. Use when reviewing LMS data, quiz patterns, or engagement metrics.

Takes a curriculum framework and a statutory or accreditation requirement list; produces a coverage table, gap summary, and CSV showing which framework content covers each requirement and where gaps exist.

Authors or reviews Know/Understand/Do charts for competency-based learning targets across developmental bands. Handles seven input types from raw curriculum documents to existing LT sets. Routes to upstream skills when stronger inputs are available.

Synthesise completed KUD charts into a developmental progression matrix and per-competency narrative sections. Use when you need a programme-level view of how knowledge, understanding, and performance develop across bands.

Developer relations - community building, documentation, DevRel metrics.

Develops mathematical understanding through examples, visualization, and analogy

Structured logging with Pino/Winston, OpenTelemetry tracing, metrics collection, Grafana dashboards, and alerting rules.

Product analytics - event taxonomy, funnel analysis, A/B testing, retention metrikleri.

PromQL queries, alerting rules, recording rules, Grafana dashboard JSON, SLO

Turn raw marketing data into actionable insight — analysis by channel, campaign, creative, audience, time. Descriptive → Diagnostic → Predictive → Prescriptive.

Defines a testable hypothesis with clear success metrics and a validation approach. Use when forming assumptions to test or aligning a team on what success looks like, before any experiment is designed. To design the A/B test or experiment that will validate the hypothesis, use measure-experiment-design.

Specifies what questions a dashboard must answer and the metrics, visualizations, filters, and data sources it needs, so data teams build something that informs decisions rather than displaying numbers. Use when requesting a dashboard or formalizing ad-hoc reporting. For the event tracking that feeds the dashboard, use measure-instrumentation-spec instead; instrument first, visualize second.

Designs an A/B test or experiment with variants, success metrics, sample size, and duration for an existing hypothesis. Use when planning an experiment to validate a product change or test an assumption you have already framed. To articulate the hypothesis itself first, use define-hypothesis.

Specifies what analytics events to track, when they fire, and what properties to include, as a contract between product and engineering that prevents undertracked features. Use before engineering builds a feature or when auditing existing tracking for gaps. For the dashboard built on top of these events, use measure-dashboard-requirements instead.

Day 1 afternoon move of a Foundation Sprint. Converts the morning's Basics frame into a defensible strategic position by scoring differentiator candidates against customer-perceived value, choosing two committed differentiators, plotting alternatives on a 2x2 chart, writing decision principles, and producing a one-page Mini Manifesto. Use after Basics is signed; before Approach Options the next morning.

一套模板驱动的单色数据可视化 skill，严格从 Lupi、Basics、Glance 与 Interactive gallery 的真实实现生成 HTML 图表；默认优先 Lupi Editorial 与 Lupi Basics，无合适模板时才使用 Glance。

Compute metrics for Claude Code sessions. Discovers via ccrider, filters trivial, computes friction/opportunity/fingerprint scores. Use for broad session triage.

Analyze trends across session metrics. Computes windowed aggregates, deltas, and compares against MEMORY.md findings. Use periodically for progress tracking.

Analyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), identifies degrading skills, and generates improvement recommendations. Requires session-scan data in metrics.jsonl.

Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement. Triggers on analytics strategy, measurement plan, event taxonomy, tracking plan, KPI framework, dashboard design, north star metric, attribution model, conversion tracking, GA4 setup, Mixpanel setup, analytics audit. Also triggers when the user has data but no clear way to use it, or wants to make decisions but doesn't know what to track.

Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event. Triggers on after-action report, AAR, postmortem, retrospective, retro, post-incident review, what went well what didn't, lessons learned, blameless postmortem, root cause analysis, RCA, five whys. Also triggers when the user has just shipped something or just resolved an incident and wants to capture learnings.

How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media dashboard, attribution analysis, ROAS vs LTV, multi-platform reconciliation, ad incrementality, geo holdout, conversion lift study, ghost bidding, paid media reporting, board-deck paid media metrics, blended CAC, MMM, MTA, last-click attribution. Also triggers when a marketer is about to scale, kill, or rebudget a campaign based on platform metrics, or when reconciling platform reports against warehouse revenue.

Designing conversational flows for website chatbots and AI agents. Intent recognition architecture, branching logic, fallback handling, escalation to human, conversation analytics. Honest about scripted-bot (rigid trees, fail edge cases), hallucinating-bot (LLM without structure, makes things up), and structured-guided-conversation (LLM-powered with intent architecture and fallback discipline) patterns. Distinguishes chatbot DESIGN (this skill) from chatbot IMPLEMENTATION (engineering and platform work). Triggers on chatbot, conversational AI, AI agent, chat widget, intent design, conversational flow, bot escalation, LLM grounding. Also triggers when a chatbot is hallucinating, when a scripted bot is failing edge cases, or when a chatbot is being scoped for the first time.

How to read experiment results without fooling yourself. Confidence intervals, p-values, multiple testing, sequential testing, CUPED, heterogeneous treatment effects, ratio metrics, network effects, dashboard reconciliation, and the interpretation failures that produce confidently wrong shipping decisions.

How to actually instrument product analytics correctly. Event taxonomy, property design, naming conventions, schema versioning, identity stitching, funnel design, retention cohorts, North Star metric selection, dashboard hygiene, instrumentation debt, and the failure modes that produce data nobody trusts. Triggers on product analytics setup, event taxonomy, tracking plan, instrumentation, schema versioning, North Star metric, retention cohorts, funnel design, naming conventions, instrument new feature, audit existing analytics, dashboard reconciliation, instrumentation debt, Mixpanel setup, Amplitude setup, PostHog setup, warehouse-native analytics. Also triggers when the team has data but cannot trust it, or when designing instrumentation for a new feature, or when auditing an existing setup that has drifted.

>- 学术不端/数据造假/统计自洽/结论夸大/幻觉与撤稿 引用/自我抄袭/隐私/版权/署名与 AI 披露/软著专利权属/论文工厂洗稿等风险,把"别造假别夸大"从口头建议 落成**可机检、可阻断、可被总控 run_checkpoint 聚合的机读门**(产 light.findings.v1,Critical fail → exit 1)。 AI 不能自评 → 一律"机读门 + 人工复核";查不到写"待核查/UNRESOLVED",绝不编造;全程在线核实、零本地知识库、零付费 key。

>- Light 科研主线第 7 步·结果分析：不描述好坏、解释「为什么」，把每条结论**绑死到 claim + 证据强度**，并防 p-hacking。 何时用：实验跑完要解读结果 / 问「这些数说明什么」/ 要做显著性检验 + 效应量 + 置信区间 + 多重比较校正 / 担心 p-hacking (多重比较不校正、选择性报告、HARKing) / 要给每条 claim 定证据强度供写作校准措辞 / 判结果支不支撑假设、可不可复现。 触发词：结果分析 / 解读数据 / 这些结果说明什么 / 显著性 / p 值 / 效应量 effect size / Cohen's d / 置信区间 CI / 多重比较 / BH-FDR / Bonferroni / 校正 / p-hacking / 选择性报告 / garden of forking paths / HARKing / 证据强度 / claim 证据绑定 / SHAP / 消融分析 / 切片分析 / 配对检验 / result analysis。 核心纪律：**统计错误 / p-hacking = critical**（spec §4.2，STAGE_GATES[7]=[stat_validity,evidence_strength]）； 过度解读 / 效应量缺失 = warn；**显著性看 q 不看 p**、不显著只能报「未见显著差异」、措辞强度必须匹配证据强度； 统计检查有边界，绝不吹「证明了方法有效 / 因果成立」。本技能是 **7→5（不支撑假设）/ 7→6（不可复现）回炉发起方**。

Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.

> Design, audit, and improve analytics tracking systems that produce reliable, decision-ready data. Use when the user wants to set up, fix, or evaluate analytics tracking (GA4, GTM, product analytics, events, conversions, UTMs). This skill focuses on measurement strategy, signal quality, and validation— not just firing events.

Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations. Use PROACTIVELY for business intelligence or strategic analysis.

Automated news aggregation and reporting agent.

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence. Use PROACTIVELY for data analysis tasks, ML modeling, statistical analysis, and data-driven insights.

Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or building executive presentations.

This FigMirror skill should be used when the user asks to "mirror this figure's style", "copy this figure's style", "make a chart that looks like this paper", "reproduce this figure with my data", "match this paper's aesthetic", "I want a NeurIPS-quality version of this", or any variant where they hand over a cropped or uncropped reference figure AND their own data and want their data rendered in the same visual register. ALSO triggers when the user attaches a paper-figure screenshot plus tabular data and asks for matplotlib output. Does NOT trigger on generic matplotlib chart requests with no reference image — that's a basic matplotlib task, not style transfer.

Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing `output/CONTRACT_REPORT.md`; use for mid-Run coverage snapshots or final delivery completeness, not deep provenance integrity.

| Bind papers to chapter-level sections first, writing `outline/section_bindings.jsonl` and `outline/section_binding_report.md`.

| Instantiate or update a workspace `UNITS.csv` from a selected pipeline and units template (deps/checkpoints/acceptance).

| Use when a CDS change in **cds-web**, **cds-common**, **cds-mobile**, **web-visualization**, or **mobile-visualization** needs a **jscodeshift** migration in `packages/migrator` to update callers or mitigate breaking API or import moves (add or change a transform, tests, or preset entry).

Amazon Brand Analytics interpretation and strategic insights for Brand Registry owners. Decode Search Frequency Rank (SFR) data, analyze Market Basket patterns, interpret Item Comparison reports, and extract demographic insights to optimize product strategy and advertising spend. Works with Brand Analytics data from all Amazon marketplaces. Requires Brand Registry access. Use when: (1) analyzing Search Frequency Rank data for keyword opportunities, (2) interpreting Market Basket data for cross-sell and bundling, (3) understanding Item Comparison competitive positioning, (4) extracting customer demographic insights, (5) optimizing product portfolio based on customer behavior, (6) building data-driven advertising strategies.

Amazon A+ Content strategy and creation. Module layouts, persuasive copy, comparison charts, image briefs, and conversion optimization. Use when the user asks about A+ Content, Enhanced Brand Content, product storytelling, or Amazon listing enhancement.

Premium A+ and Brand Story — module design, lifestyle imagery, comparison charts, mobile optimization

Seller storefront analysis and competitive intelligence for Amazon. Analyzes seller revenue estimation, product portfolio strategy, growth trajectory, and market positioning. Reverse-engineer successful seller strategies and identify expansion opportunities. Use when the user asks about analyzing sellers, competitor seller analysis, seller revenue estimation, storefront analysis, seller strategy, or learning from successful Amazon sellers.

Self-heal + report bugs to make the ecosystem better. When you hit ANY defect in comfyui-mcp / the sidebar panel, OR in a third-party custom node / ComfyUI core, use this: diagnose it, and for OUR repos (comfyui-mcp / comfyui-mcp-panel) **fix it locally FIRST** — patch the code where it actually runs so the user is unblocked immediately — then file a report that includes the diff, so reports arrive as near-PRs, not just tickets. (Attempt the fix exactly ONCE; if it's genuinely upstream-only, mark it and include the precise change needed.) Report it the right way: our intake Worker for our repos; the node's own GitHub for third-party. For OUR repos (artokun/comfyui-mcp, comfyui-mcp-panel, comfyui-mcp-issue-worker) act **autonomously** — fix-then-file and just inform the user, no per-step permission. For THIRD-PARTY / ComfyUI-core it is **offer-and-ask**: propose the workaround/report and act only with the user's go-ahead. **BETA — bias HARD toward fix-then-file (our repos):** trigger on any comfyui-mcp/panel defect you notice — an error, a crash, a tool that returns wrong/misleading/empty output, a silent failure, a confusing result, or a limitation that forced an awkward workaround — EVEN IF you recovered or worked around it. You do NOT need to be blocked. Also on "report this" / "fix this bug". If a future user would hit the same friction, fix-and-file it — the intake Worker dedupes, so over-reporting is cheap and under-reporting costs us the bug. THIRD-PARTY / ComfyUI-core bugs stay offer-and-ask.