Data And Analytics for AI agents
100 security-reviewed data and analytics listings, skills, MCP servers, and toolkits you can install into Claude Code, Cursor, and other agents with one command.
Keepa MCP
A Model Context Protocol (MCP) server that lets Claude access Keepa's Amazon marketplace data through a conversational interface. This makes product research, sales trends, inventory insights, and competitive analysis easier without navigating Keepa's complex UI.
Multi Agent Syncer
Sync skills across multiple AI coding agents (Claude Code, Cursor, Gemini CLI, Codex, etc.) with CLI and web UI dashboard
Powerbi Analyst
Analyze source data and autonomously build a tailored Power BI project with actual semantic models, DAX, Power Query and report pages. Use when someone provides data and wants a Power BI dashboard, PBIP project or analytical solution, or requests advanced Power BI modeling and code guidance.
Document Quality Review
Review Markdown, Word, PDF, spreadsheet, or presentation deliverables for factual support, internal consistency, completeness, usability, and visible quality before delivery.
Serp Analysis
Analyse the current Google top 10 for one keyword — keyword metrics, search intent, SERP features, the winning content format, and the gap the user can realistically win. Use when the user asks what ranks for a keyword, what the SERP looks like, which format to write, or why competitors outrank them.
Sheet Io
Use a spreadsheet as a data source or sink from Claude Code without wrecking it or blowing the token budget. Works on a local CSV or a PUBLIC Google Sheet (via its CSV export URL, no credentials). Use when the user points at a spreadsheet, a Google Sheets link, or a .csv and wants to read, filter, summarize, or append rows, or asks to 'connect the sheet', '시트 연동', '이 데이터 정리해줘'. Provides a stdlib-…
Dashboard Design
>
Ebay Mcp Remote Edition
Open source MCP server providing AI assistants with comprehensive access to eBay's Sell APIs. Includes 325+ tools for inventory management, order fulfillment, marketing campaigns, analytics, developer tools, and more.
Gtm Intake And Dashboard
Runs once by hand on the first day and once a month after that. On the first run it researches the business from its own public surfaces before asking anything, writes the strategy folder, seeds the launch board, builds the tailored command center, reconciles the schedule table, and registers the recurring jobs. On every monthly run it re-reads the evidence the kit produced, applies what changed,…
Ads Account Intake
Runs once by hand on the first day and once a month after that. On the first run it researches the business from its own public surfaces before asking anything, reads the account structure once, writes the plan folder, seeds the board, creates the creative doctrine, builds the dashboard, and registers the recurring jobs. It asks about exactly two things, the monthly ceiling and the daily cap, bec…
Ads Creative Studio
Weekdays. Produces one creative set per run against evidence rather than taste, reading the standing doctrine for the angles currently earning and the metrics ledger for what has decayed. It writes the images and the exact strings into a dated local set folder with the destination screen named, files one card, and uploads nothing to any account. It never opens an account screen, sends only where…
Cos Charter And Fleet Audit
Runs once by hand on the first day and once a month after that. On the first run it researches the business from its own public presence, writes the charter with a source and a date beside every conclusion, discovers the AI Employees actually installed on this machine within a bounded search, writes the map every other routine in this kit reads, seeds the priorities and the watchlist once, builds…
Ads Account Read
Weekdays. The only routine in this kit that opens a screen inside an account that can spend, and everything it does there is read. It confirms the primary conversion event still fired inside the read window before it trusts any other figure, then reads yesterday's spend, delivery, and result rows at account, campaign, ad set, and creative level and appends one row per object per day to the daily…
Ads Creative Retro
Monthly, on the last weekday. Folds a month of the creative ledger against the daily metrics ledger to score angle, format, hook, and offer framing rather than individual files, tests every line currently in the creative doctrine against what the month actually measured, and rewrites the doctrine where the evidence disagrees with the assumption. It records the fatigue curve it observed, retires w…
LifeOS
An AI-native personal operating system: a plain-text life vault + a static dashboard you own, driven by any AI assistant (Claude, ChatGPT, Gemini, Cursor). Clone, personalize with your AI, deploy.
InsightTrack
Self-hosted, privacy-first web analytics — the open-source alternative to Google Analytics
Aso Skills
AI agent skills for App Store Optimization (ASO) and app marketing. Built for indie developers, app marketers, and growth teams who want Cursor, Claude Code, or any Agent Skills-compatible AI assistant to help with keyword research, metadata optimization, competitor analysis, and app growth.
Outreach Verify
Verify the email addresses you brought yourself before you send to them: a CSV, an export from another tool, an old CRM extract, a contact base that has been sitting for a year. Sorts each address into send, drop or hold, detects catch-all domains with a control test, keeps the projected bounce rate under the threshold that protects sender reputation, and writes the verdicts into outreach/leads.c…
Outreach
Universal B2B outreach skill. Define an ICP, build and clean a lead list, find and verify professional emails and mobile numbers, write and personalize a multichannel sequence, check deliverability, launch the campaign, handle replies, and read the results. Works with the Emelia MCP server or REST API, the Basile API for French B2B data, or a plain CSV. Triggers on: outreach, cold email, prospect…
Outreach Filter
Clean and segment a lead list before a single credit is spent on it. Deduplicates by email, by company domain and by LinkedIn profile, handling the awkward cases (subdomains, plus aliases, apostrophes and accents in names, Sales Navigator URLs that never string match a public profile), excludes existing customers, competitors and blacklisted addresses using find_contact and the Emelia blacklist e…
Outreach Find Phone
Find direct mobile numbers for the people on a lead list with Emelia's phone finder, from their LinkedIn profile URL, one at a time or in bulk. States the credit cost before spending, polls each job to completion, handles found and not found honestly, and writes the numbers into outreach/leads.csv and outreach/enrichment.json. Emelia does not place the calls: the number goes to your phone or your…
Outreach Enrich
The full enrichment waterfall on a lead list: filter first, find the missing emails, verify only the addresses that came from somewhere other than Emelia's finder, find mobile numbers only where they are worth 50 credits, then decide row by row who is sendable, who is on hold and who is dropped. Ends by routing the rows to separate destinations, one list per destination: addresses found go to the…
Outreach Find Email
Find professional email addresses for the people on a lead list, one at a time or in bulk, with Emelia's email finder. Runs the three attempt fallback cascade that recovers the rows a single lookup misses: the domain first, then the company name, then the trade name. States the credit cost before spending anything, polls each job to completion, and records what was found, what was not and which a…
Genoffice
Create, convert, read and edit Office documents locally with GenOffice's command line. Build a new presentation (pptx) from a brief through a checked outline, per-page spec and render pipeline, a new spreadsheet (xlsx) from CSV or JSON data with formulas, a new Word document (docx) from Markdown or HTML, or a PDF; convert between pdf, docx, xlsx, pptx, md, html and csv; read the structure and tex…
Mulmoclaude
Nurture your own AI assistant on your own computer. Local-first and MIT: memories, data and apps stay as plain files in your workspace. Chat summons the right GUI — wiki, spreadsheet, chart, form, 3D. Build small apps for an audience of one, no programming required.
Simvyn
Operate iOS Simulators, Android Emulators, and connected mobile devices with Simvyn. Use for device discovery, app installation and launch, screenshots, logs, deep links, location simulation, app data inspection, device settings, and reusable device workflows through the Simvyn CLI or dashboard.
Mezura
Counts the lines of a codebase quickly and accurately, along with user-defined keywords like classes and structs. Tracks how the figures move between runs, and between any two git revisions. Command line program, library and MCP server.
Scout
Scout a topic on YouTube. Searches YouTube Data API v3 for the most relevant videos, ranks them by views (or engagement, likes, recency, momentum, breakout), and writes a research workbook in the OWT-Social-Ads layout with Videos, Channels, and Summary sheets, plus optional Comments and Transcripts (hooks, replay hotspots) sheets. Can also append into an existing sheet. Use when the user says "sc…
Short Drama
基于文件系统初始化和继续短剧或漫剧项目，提供 creator-first 五文档路由、本地 Dashboard、制作形态与 Look Development 决策。用户提出“创建/继续短剧项目”“看进度/下一步”“做 Look Development”“打开 dashboard/短剧创作台”“导出制作资料”，或任务跨多个创作阶段时使用；明确的写作、资产、提示词、分镜、剪辑或审查请求由对应子 skill 直接处理。
Story
网络小说工具箱主入口。根据用户需求自动路由到对应 skill，并可管理作者习惯、启动本地 Dashboard。触发方式：/story、$story、/story dashboard、/网文、「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」。
Sealeap Amazon Eu Amc Audience
Diagnose and plan privacy-safe Amazon Marketing Cloud (AMC) analytics and audience activation, especially for European and peak-season accounts, including journey/time-to-conversion analysis, reach/frequency, overlap, new-to-brand, rule-based and lookalike audiences, no-code audience templates, and SP/SB/SD/DSP activation. Use for AMC, 亚马逊营销云, 欧洲站 AMC, 旺季高潜人群, 购物车/浏览未购, 高价值新客, 潮汐人群, 转化路径, 购买周期, 受…
Sealeap Amazon Listing Optimizer
Audit, diagnose, rewrite, creatively brief, test, and safely prepare updates for Amazon product detail pages using live marketplace and product-type requirements, verified product facts, Brand Analytics, Search Query Performance, Ads search terms, customer feedback, competitor observations, and optional third-party estimates. Use when asked to improve or evaluate Amazon titles, bullets, descripti…
Sealeap Amazon Acos Diagnostics
Diagnose Amazon Ads ACOS with reconciled CTR, CPC, CVR, AOV, ROAS, TACOS, placement, search-term, benchmark, attribution, and contribution-margin evidence, then produce a single-variable optimization experiment. Use for ACOS 高低判断, 广告亏损, CTR/CVR/CPC 异常, 盈亏平衡 ACOS, 广告报告诊断, Benchmark 基准, placement 浪费, 搜索词不精准, Listing 转化问题, 广告利润优化, or converting the authorized Amazon Ads metrics course into an accoun…
Full Crm
Use when the user wants to move already enriched contacts into a CRM and has a separate CRM MCP connected. Orchestrates that separately connected CRM MCP: confirms the connector, proposes field mapping, checks duplicates, requests explicit confirmation, then calls only the CRM MCP's tools. FullEnrich MCP itself only searches, enriches, and exports CSV/JSON; it does not write CRM records. Triggers…
Full Csv
Use when the user uploads a CSV file containing contacts (LinkedIn URLs, names + companies, or any combination) and wants to enrich them with verified emails and phone numbers via FullEnrich. Parses the CSV, validates structure, runs bulk enrichment with user confirmation, and presents enriched results as a table in chat with a download option. Triggers on: \"enrich this CSV\", \"enrich my file\"…
Warm Path Workspace
Build an interactive Deal Workspace artifact for one or more target accounts - an auto-researched account brief, a buying-group map with deal roles, per-stakeholder dossiers (priorities, talking points, likely objections, a grounded opener) mined from each person's LinkedIn activity, live deal signals, prioritized plays, and a weighted warm-intro chain map that traces every route from your team's…
Chart
做「統一又漂亮」的資料圖表 / 視覺化。觸發場景：需要畫柱狀圖 / 折線圖 / 趨勢圖 / 占比圖（甜甜圈、圓餅）/ 分組或堆疊柱 / 目標vs實際 / dashboard / 週報圖表 / 行銷數據圖 / KPI 圖；或使用者說「做個圖表 / 畫個 chart / 視覺化這組數據 / 弄成圖 / 加個趨勢圖 / 占比圖」。用 @unovis（單一圖庫）+ 一份 design token 出統一風格、各圖型共用視覺語言的漂亮圖表。涵蓋獨立 HTML demo 與專案內 Vue 兩種交付。注意：這是「資料視覺化原語」skill；若是整份報告/文件要圖文版面，搭配 html-visualizer。
Html Visualizer
把長文件 / 報告 / 規格 / 設計決策（ADR）/ 架構說明 / 研究結論 / PR review / 教學 / 儀表板 / 互動式探索界面 / 決策追認 / marathon 收尾簡報 / prototype 預設用 HTML 而非 Markdown 呈現給人類看。觸發場景包含但不限於：使用者說「整理成文件 / 做一份報告 / 給我份視覺化 / 圖像化呈現 / 給人看的版本 / 報告我老闆 / 做個 dashboard / review 用 / 教我這個概念 / 做個解釋 / 寫個 spec 給我看 / 給我幾個選項拍板 / 列待確認的決策 / marathon 結束追認 / sprint 收尾 / 我醒了回報狀況」、或內容超過 50 行 markdown、或累積 2+ 條待使用者拍板的選項、或內容適合用對比圖 / 流程圖 / 表格 / 卡片視覺化呈現時。即使使用者沒明說 HTML…
Rseng Community Metrics
>-
Query Peerlytics Data
Query ZKP2P protocol data using the @peerlytics/sdk — rates, orderbooks, deposits, maker portfolios, live activity, and vault analytics. Use when asked about P2P exchange rates, USDC liquidity, maker stats, or protocol analytics on Base.
Echarts Bigscreen
一句话生成可直接交付的数据可视化大屏(单文件 HTML + ECharts)。触发词:大屏、数据大屏、可视化大屏、监控大屏、驾驶舱、数据看板、一张图、big screen、data dashboard、cockpit。适用政务、交通、工业、公安、校园、电力、商业监控等场景。深色科技风,1920×1080 等比自适应,国内 CDN,支持内网离线部署。
Laradashboard
⚡ Lara Dashboard - CMS by Laravel - All In One solution to start your Laravel Application from Basic to Enterprise. Manages Users, Roles, Permissions, Modules, Settings, Translations, Contents, Monitoring and every actions of your Laravel application. Complete solution for Laravel application with Tailwind, Livewire, Rest API, Unit-Tests and more.
Renpho Mcp Server
MCP server that provides access to body composition data from Renpho smart scales. Query your weight, body fat, muscle mass, and other health metrics directly from Claude, Cursor, or any MCP-compatible client.
Alteryx Designer
Inspect, build, edit, run, repair, and validate local Alteryx Designer workflows, macros, and analytic apps. Use for `.yxmd`, `.yxmc`, and `.yxwz` work involving data preparation, reconciliation, compliance reporting, operational analytics, governed calculations, file transformations, joins, filters, summaries, formulas, macro/app interfaces, execution failures, or output validation. Prefer insta…
User Personas Behavior
Define who a product is for, what they're trying to accomplish, how success is measured, and what to instrument to know if it's working. Covers user personas (goal- and behavior-based, not demographic), jobs-to-be-done, success metrics/KPIs, and an analytics/event-tracking plan. Use before or alongside requirements gathering so "who is this for and how do we know it's working" is answered explici…
Postey Analytics
>
Analytics
>
Excel Live Control
Control an open Microsoft Excel workbook in a connected live session. Do not use for standalone spreadsheet files.
Spreadsheets
Create, edit, analyze, and verify standalone spreadsheet files and workbooks. Do not use for a live Microsoft Excel session.
Template Creator
Create or update a reusable artifact template from a reference presentation or spreadsheet. Do not use for one-off creation.
Cognitive Security Resilience Metrics Design
Define measurable indicators of an information ecosystem's resistance to manipulation.
Experiment Design
Design experiment plans with progressive stages — initial implementation, baseline tuning, creative research, and ablation studies. Plan baselines, datasets, hyperparameter sweeps, and evaluation metrics. Use when planning experiments for a research paper.
Table Generation
Generate publication-quality LaTeX tables from experimental results. Convert JSON/CSV data to booktabs-styled tables with bold best results, multi-row layouts, and proper captions. Use when creating result tables, comparison tables, or ablation tables for papers.
Xxd Data Viz
Create chart and data visualization palettes from Chinese traditional colors. Use when a user needs categorical, sequential, diverging, highlight, dashboard, map, ECharts, D3, Chart.js, or colorblind-aware data palettes with Chinese traditional color identity.
PFC Vedo Postprocess
Post-process and visualize ITASCA PFC/PFC2D/PFC3D DEM results with vedo. Use this skill whenever the user mentions PFC/DEM post-processing, particle rendering, force chains, crack visualization, displacement or velocity fields, shear-band slices, exported .npz/.vtp/.csv PFC data, or making publication-quality DEM figures and animations with vedo.
Safe Csv Cleaner
Clean and normalize CSV rows for analysis. Safe fixture for scanner smoke tests.
Self Evolving Skill Instructor
Onboard a new Agent developer after repository setup, then guide them through this repository's eight-step, executable-evaluation workflow for improving a Skill. Use after they ask to pull or install this repository, or when they say “我要学习 Skill 自进化”, want to start or resume Skill self-evolution, ask what to do next, or need help interpreting its local dashboard and evidence.
Kpi Tree Dashboard
Scores every metric red, amber, or green against its target via a bundled calculator, and specifically flags when a leading indicator is already red while the lagging outcome it predicts still shows green, catching a problem before it shows up in the number everyone's watching. Use whenever the user wants a KPI dashboard or scorecard, needs to connect leading indicators to the lagging outcomes th…
Snowflake Writer
A Claude skill from vagabondshun/snowflake-writer.
Brainstorm Prd
Interviews users and generates `PRD.md` with scope, outcomes, metrics, rollout, business rules, and traceability. Use only when the user explicitly wants to define a new product or create/recreate its PRD.
Prd Success Metrics
Draft the Success Metrics of a PRD by defining the key metrics used to measure success. Drives discovery through the primary outcome metric, leading indicators, guardrail metrics that must not regress, and the instrumentation source for each. Writes to `.trogonai/project/{projectid}/prd/success-metrics.prd.md`. Use when the user wants to define how success will be measured before building.
Otel Name Metric
Review or create OpenTelemetry metric names following semantic conventions. Validates naming format, units, instrument selection, and attribute placement. Use when designing new metrics, reviewing existing instrumentation, or auditing metric naming consistency. Do not use for: (1) span or trace naming, (2) OTel collector configuration, (3) SDK installation or setup, (4) alerting or dashboard desi…
Otel Name Span
Review or create OpenTelemetry span names following semantic conventions. Validates naming, cardinality, attribute placement, and protocol-specific patterns. Use when designing new spans, reviewing existing instrumentation, or auditing span naming consistency. Do not use for: (1) metric naming, (2) OTel collector configuration, (3) SDK installation or setup, (4) alerting or dashboard design.
Prd Getting Started
Initialize a new project with the six default Product Overview Documents (business problem, current state, personas, product description, success metrics, technical requirements). Scaffolds stubs and walks the user through running each section skill in priority order. Use when the user is starting a project and there are no PRD files yet.
Datadog Design Dashboard
Design new Datadog dashboards, redesign existing ones, or audit dashboards for operational readiness. Covers widget selection, layout organization, template variables, group structure, tab organization, alert threshold validation, and zero-knowledge readability. Uses pup CLI for inspecting dashboards and validating designs. Use when designing new dashboards, redesigning existing ones, auditing be…
Creator Analytics
>
Prd To Ralph
Use when converting PRD/requirements into JSON format for Ralph Wiggum autonomous loops. Extracts user stories, orders by dependency (schema first, then backend, then UI, then dashboard), auto-adds standard criteria (typecheck, build, lint, tests), outputs structured JSON ready for autonomous iteration.
Data Tables
Tables, grids, charts and dashboards — sorting, filtering, pagination, selection, KPIs, data fetching. Use when the UI is tabular or data-dense — data tables, lists, grids, pagination, sorting, filtering, row selection, KPI cards, charts, analytics dashboards, admin panels. TanStack Table or Query route here.
Exploratory Data Analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.
Benchling Integration
Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.
Gsc Mcp
MCP server for Google Search Console — access search analytics from any AI tool
Logisheets Mcp
give your AI agent a spreadsheet it can actually think in: deterministic Excel-compatible math + structured memory (blocks), real .xlsx out. Open source, self-hostable.
Data Report
把 CSV、Excel 或 JSON 数据生成包含 KPI、图表和洞察的完整可视化报告页。当用户说“数据报告、CSV/Excel 转报告、做 KPI 看板、生成可视化报告页”时使用。单张图表用 chart-visualization；信息图或 GIF 动画图表用 infographic。
Infographic
将数据或文字内容转化为可视化信息图，支持静态（AntV）和动画 GIF 两种模式。当用户需要制作信息图、数据可视化、流程图、对比图、动画图表、GIF 图表、思维导图、SWOT 分析图时调用。本地渲染信息图/GIF 动画；要单张静态图片 URL 用 chart-visualization，要 CSV/JSON→整页报告用 data-report
Chart Visualization
将数据可视化为图表。当用户需要生成柱状图、折线图、饼图、散点图、雷达图、桑基图、思维导图、流程图等图表时调用此技能，通过 curl 工具调用 AntV API 生成图表图片。产出静态图片 URL（25+ 类型）；要本地渲染的信息图/GIF 动画图表用 infographic，要 CSV/JSON→整页报告用 data-report
Activation Flow Design
Designs the first-run path that carries a brand-new user from signup to their aha-moment fast — defines the activation event, maps the current first-run, diagnoses the drop-off, and re-sequences the steps with triggers, nudges, and empty states. Use when a PM says "design our onboarding", "improve activation", "get users to the aha moment", "redesign first-run", "new-user flow", "why aren't new u…
North Star
Defines a North Star Metric that captures delivered customer value and decomposes it into 3-4 movable input metrics. Use when you need to "pick a North Star metric," "we're optimizing for revenue and it's hurting us," "build an input metric tree," "what should the team actually move," "align the roadmap to one number," or "our metric is a vanity metric.
Launch Plan
Builds a go-to-market launch plan for a feature or product, scaled to a launch tier. Use when someone asks to "plan the launch", build a "go-to-market plan" or "GTM for the new feature", needs a "launch checklist for X", or asks "how should we launch this". Produces audience, messaging, channels, a pre/launch/post timeline with owners, assets, success metrics, and a launch-day runbook.
Metrics Review
Reviews product metrics with trend analysis and turns raw numbers into a scorecard with actions. Use when the user asks to "review our metrics", "run a weekly/monthly/quarterly metrics review", "why did signups drop", "why did this spike", "build a metrics scorecard", or "compare against target". Works with pasted numbers or a CSV; pulls from Amplitude/Mixpanel/GA if connected.
Tracking Plan
Designs the event tracking plan for a feature or product area — the event taxonomy, naming convention, properties, and QA checklist that make a metric answerable later. Use when a PM says "what should we instrument", "write a tracking plan", "what events do we need", "we can't answer that from the data", "define the analytics for this feature", or is about to ship something with no way to tell wh…
Business Model
Fills a complete Lean Canvas (or Business Model Canvas) across every block — problem, customer segments, unique value proposition, solution, channels, revenue, cost, key metrics, and unfair advantage — then flags the single riskiest block to validate first. Use when you say "map our business model," "fill a lean canvas," "what's our UVP," "how do we make money," "where's the riskiest assumption,"…
Rka Core
Research Knowledge Agent — MCP server + REST API + React dashboard for AI-assisted research orchestration
Otel Guides
Curated map of the official OpenTelemetry documentation by language. Use when planning or implementing OpenTelemetry instrumentation for a codebase - pick the language, open its reference file, and follow the linked official docs for traces, metrics, logs, instrumentation libraries, exporters, and SDK configuration. Covers C++, .NET, Erlang/Elixir, Go, Java, JavaScript, Kotlin, PHP, Python, Ruby,…
Wicked Garden Data Engineer
ETL pipeline design, data quality assessment, schema validation, and performance optimization as a delegated fork worker. Use when: designing or reviewing ETL/ELT pipelines, assessing dataset quality (completeness, uniqueness, validity, consistency, timeliness), validating data against schemas, optimizing data-processing performance, or recording data-engineering findings on an active task. For i…
Analytics Tracking
Use when auditing, planning, or debugging marketing measurement, conversion tracking, GA4, GTM, UTMs, pixels, CRM attribution, funnel reporting, or dashboard trust.
FeatureFusion
a .NET lab of production building blocks (Mediator, OpenTelemetry, Aspire/SigNoz, Mcp and etc) plus a runnable showcase. More packages, a frontend on the way.
Hotline Switchboard
Live read-only HTML dashboard of hotline conversations — 'open/stop the switchboard', 'watch the hotline calls', 'is the switchboard running?
Esports Theorycrafting Meta Analysis
Esports Meta-Game Analysis & Theorycrafting Optimization - evidence-backed analysis harness with quality-gated, risk-disclosed output. Use this skill whenever the user asks about esports meta analysis, theorycrafting, hero tier lists, build optimization, counter-strategies, patch analysis, competitive gaming strategies, or wants authoritative esports analytics with academic backing.
Agent Evals
Build and maintain evaluation suites for AI agents: bootstrap 20-50 tasks from real failures, pick code-based vs model-based vs human graders by agent architecture (coding, conversational, research, computer-use), write unambiguous tasks with reference solutions, and keep suites alive via ownership and transcript reading. Use when creating evals from zero, adding graders or eval cases, debugging…
Data Engineering
Builds and operates data pipelines — ingestion, transformation, orchestration, quality testing, and reliability of data delivery. Use this to design or debug a pipeline, decide batch versus streaming, add data quality checks, handle late or duplicate data, or work out why a dashboard's numbers changed without anyone changing the dashboard.
Marketing Analytics
Sets up, audits, and reports on marketing measurement — tracking plans, event schemas, attribution models, and the dashboards built on them. Use this to instrument a site or product, audit tracking nobody trusts, choose or interpret an attribution model, build reporting that answers a specific question, or reconcile numbers that disagree between tools.
Service Desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets still frustrates everyone.
Support Operations
Designs and runs the support function — channels, queues, routing, staffing, service levels, quality, and the metrics that show whether it is working. Use this to set up or fix support operations, choose channels, size a team, set or renegotiate service levels, reduce cost per contact, diagnose long queues or poor quality, or decide what to automate.
Data Governance
Establishes ownership, definitions, quality, access, and lineage for the organization's data. Use this when metrics disagree between teams, when nobody knows which dataset is authoritative, when setting up data ownership or access policy, when data quality is unreliable, or before opening a dataset to a wider audience.
Business Intelligence
Builds reporting and self-serve analytics that people actually use — metric trees, dashboard design, distribution, and the discipline that stops dashboards proliferating. Use this to build a dashboard or report, design a metrics framework, set up self-serve analytics, decide what to measure, or diagnose why reporting exists but nobody uses it or trusts it.
Chief Data Officer
Owns data as an asset — governance, quality, the warehouse and semantic layer, analytics capability, and the governance of models built on top. Use this for a decision about how data is collected, stored, defined, or shared; when numbers disagree between teams; when deciding what to build in-house versus buy; when standing up a data function; or when an AI or model decision needs governance rathe…
Data Modeling
Designs the warehouse and semantic layer — source-to-mart structure, dimensional modeling, grain, slowly changing dimensions, and the metric layer analytics reads through. Use this to design or restructure a warehouse, model a new source, decide on grain or table structure, build a semantic or metric layer, or diagnose why queries are slow, wrong, or impossible to write.
Observability Patterns
Use when reviewing code for observability correctness — covers Structured Logging, Log Levels, Distributed Tracing, Metrics (counters/gauges/histograms), Health Checks, Alerting, Correlation IDs, and Audit Trails with red flags and fix strategies across TypeScript, Python, Java, and Go
Analyzing Codex Sessions
Use when analyzing Codex CLI raw session logs, parsing rollout JSONL files, investigating Codex subagent behavior, extracting metrics from Codex threads, or debugging why a Codex agent failed. Triggers on ~/.codex/sessions paths, rollout-*.jsonl filenames, Codex thread IDs, or requests to understand what happened in a Codex run.
Analyzing Cc Sessions
Use when analyzing Claude Code raw session logs, parsing JSONL transcripts, investigating agent behavior, extracting metrics from session data, debugging subagent dispatches, or building session analysis tools. Triggers on session IDs, JSONL paths, ~/.claude/projects references, or requests to understand what happened in a CC session.