Data & Analytics
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
-
posit-dev Skill R Databricks ComputeStarting, stopping and inspecting Databricks clusters and SQL warehouses from R with brickster, without surprise billing. Covers the check-before-start rule, access modes and which ones permit R, cluster library installation, getting binary rather than source packages onto a cluster, and why a colleague's dedicated cluster returns HTTP 403. Load before any operation that could start compute.
-
posit-dev Skill R Databricks Unity CatalogFinding and querying Unity Catalog data from R. Covers browsing catalogs, schemas and tables with brickster, writing dbplyr pipelines rather than SQL strings (including why spatial ST_ functions and the odbc BINARY bug are not reasons to drop to SQL, and why an st_ call above collect() is the server's function and not sf's, which models the Earth differently unless the coordinates are projected), in_catalog() for three-part names, glimpse() without collect(), deciding where the collect() line goes, and using dplyr::sql() for expressions dbplyr cannot translate or tbl(con, sql()) to start from a whole hand-written query. Load when locating a table or writing a query; load r-databricks-connections first to choose a connection path.
-
posthog Bundle MCP Data WarehouseBuild and run a curated layer of PostHog data-warehouse views (saved queries) with the view-* MCP tools. Covers the tool contracts (query JSON shape, edited_history_id, incremental settings, sync_frequency buckets), write-path mechanics (timeouts that still commit, inference limits, rename semantics), how to tier a layer (materialized bases, grain spines, live tops, naming, join keys, materialization order, declared vs effective cadence, staleness), HogQL traps that give wrong numbers silently (LEFT JOIN type defaults, NULL NOT IN, JSON nulls, the 100-row default limit), workflows (create, change, add or rename a column, rename a view, change cadence, debug staleness, retire), and a template for documenting a layer as its own skill. Use when creating or materializing views over MCP, structuring views into a layer, debugging a stale view or a wrong number, or changing a schedule. Trigger on 'create a view', 'materialize', 'saved query', 'view is stale', 'sync_frequency', 'warehouse view layer'.
-
posthog Bundle Web Analytics TriageInvestigate a sudden change in web traffic. Use when a user reports a spike or drop in pageviews, sessions, or conversion and wants to find the likely cause (channel, device, referrer, or release) before escalating.
-
btcelectrician Bundle Construction Etl Hardening LoopHarden construction-document extraction when source content is missing, misassigned, or silently omitted. Use for cross-trade drawing, schedule, table, and final-query failures. Preserve model-native semantics and generic evidence capture; do not use this skill as authority for Oracle V3 workbook procedures or as a reason to add trade-specific parsers.
-
btcelectrician Bundle Oracle V3 Review Workbook HardeningRepair Oracle V3 construction review packets when source PDFs, extracted CSVs, ground-truth fields, Excel workbooks, or emitted production facts disagree. Use only for explicit Oracle V3 review and synchronization work; do not use as Anvil compiler architecture guidance.
-
cookieshaha Skill Param XLSX SyncHPS3/HPC 工作站 param 表更新工作流:把手动整理的 xlsx(含删除线标记的待删记录)转换为项目里的 param_*.md 数据文件,与 workstation-review 等规格文档逐条比对差异,整理成更新清单交用户审批,审批通过后才写入 param 表,并把变更过程同步到本地与飞书的 param_change_history 文档。触发关键词:param更新 / xlsx转md / 更新param表 / 对比workstation-review / param version history。
-
planetscale Skill Planetscale Pscale CLI AutomationUse the PlanetScale CLI (pscale) from automated agents with --format json, auth check, pscale sql, and per-command --force. Run before other PlanetScale skills when driving pscale directly. Use when the user asks to automate pscale, run CLI commands headless, or verify pscale auth from an agent.
-
halukerenozlu Bundle Golang SecuritySecurity best practices and vulnerability prevention for Golang. Covers injection (SQL, command, XSS), cryptography, filesystem safety, network security, cookies, secrets management, memory safety, and logging. Apply when writing, reviewing, or auditing Go code for security, or when working on any risky code involving crypto, I/O, secrets management, user input handling, or authentication. Includes configuration of security tools.
-
cylixlee Bundle Golang Gin DatabaseIntegrate PostgreSQL databases with Go Gin APIs using GORM or sqlx. Covers repository pattern, connection retry with backoff, cursor/keyset pagination, context-based transactions, TLS/sslmode, migrations, and dependency injection. Use when adding database support, creating models, writing queries, implementing repositories, setting up migrations, or wiring database layers into a Gin project. Also activate when the user mentions GORM, sqlx, database connection, SQL queries, repository pattern, or database migrations in a Go/Gin context.
-
daloopa Skill UpdateRefresh existing research note and Excel model with latest data
-
daloopa Skill InitiateInitiate coverage — generate both research note (.docx) and Excel model (.xlsx)
-
daloopa Skill Comp SheetBuild an industry comp sheet Excel model with deep operational KPIs
-
daloopa Skill Build ModelBuild a multi-tab Excel financial model
-
harumiweb Bundle Exstruct CLIUse ExStruct CLI to validate, inspect, create, and edit Excel workbooks safely. Trigger when an agent needs `exstruct patch`, `exstruct make`, `exstruct validate`, `exstruct ops list`, or `exstruct ops describe`, especially for create-vs-edit decisions, dry-run workflows, backend constraints, or safe workbook-edit guidance.
-
ianlkl11234s Skill Supabase Optimize為 Supabase RPC 產生 pre-aggregate pattern SQL 範本。當響應時間 > 1s、rows > 10k、或含 string_agg/ST_Union 時使用。依照 Mini Taiwan Pulse 專案的「普通 table + per-day refresh function + pg_cron + 薄 RPC」架構產生完整 SQL,含 advisory lock、cleanup、cron 排程。
-
jhd3197 Skill DashboardInternal tool / analytics dashboard — sidebar nav, KPI cards, charts placeholder, a data table.
-
baidubce Skill Famou Data AnalysisA data analysis skill for understanding datasets, analyzing data, building data processing pipelines, and summarizing analytical results. Use this skill when the user mentions "analyze data", "data processing", "data exploration", "statistical analysis", "data cleaning", "data summarization", "create a data report", "understand this dataset", or "take a look at this CSV/Excel/dataset". Even if the user simply says "help me look at this data" or "analyze this", trigger this skill whenever the context involves a data file or dataset. Also invoke this skill if data analysis is required during Famou problem definition.
Audited -
baidubce Skill Medical Bill Organizer医疗票据整理助手,用于自动分类、OCR识别和信息抽取。当用户需要处理医疗票据时使用,支持文件夹或压缩包输入,自动分类存放到不同文件夹,抽取病历信息(住院日期、医院名称),生成发票汇总CSV表格。
Audited -
percival-labs Bundle ShopkeepDigital asset storefront management bot for the Vouch platform. USE WHEN processing orders, listing items, answering customer questions, or generating sales analytics. Supports STL, SVG, digital art, ebooks, and any downloadable digital asset.
-
rivo2026 Skill Wc望川学员版内容创作工具箱入口。帮助用户在短视频 CSV 整理、抖音开头、小红书标题、思想家研究圆桌与学习、人设定位、工具箱更新中选择合适的 Skill。 用户询问有哪些工具、不知道该用哪个工具、要求开始内容创作与知识研究,或说“帮我更新 wcskill”时使用。
-
rivo2026 Bundle Wc Organize将短视频文案 CSV 整理成保留各项原始数据的 Markdown 断行稿,按口播气口换行、分出开局/交付/收束,并用片段对照表标出首拍截停机制。用户要求整理短视频 CSV、转换带数据的断行版时使用;不处理 Markdown 输入、账号拆解或文案创作。
-
skillmedev Skill Spreadsheet Model BuilderStructures spreadsheet models a second analyst can audit - separated input/calc/output sheets, one-formula-per-row hygiene, built-in error checks, and a documented cover sheet. Use when someone asks "how should I structure this model", "clean up this spreadsheet before the board sees it", "why does my model break when I insert a column", or is building any forecast or calculator others will review. Do NOT use for the SaaS revenue logic itself - use revenue-modeling instead; for a full FP&A operating model use fpa-model; for personal or department budgets use budget-builder; for cash timing use cash-flow-forecast; for GAAP statement construction use financial-statement-builder.
-
skillmedev Skill Pii ScrubberDetects and redacts personally identifiable information from text, logs, datasets, and LLM prompts using layered pattern, checksum, and NER detection, then picks the right redaction mode for each downstream use. Use when someone asks "scrub PII from these logs", "redact personal data before sending it to the LLM", "is this dataset safe to share", or is wiring up logging, analytics, or third-party exports that might carry user data. Do NOT use for leaked API keys, tokens, or credentials - use secrets-hygiene instead.
-
skillmedev Skill User Persona BuilderSynthesizes interview notes, surveys, support tickets, and analytics into evidence-based user personas that drive design decisions, with every claim traced to source data. Use when someone asks "build personas from our research", "turn these interview notes into personas", "how many personas do we need", or "are our personas evidence-based". Do NOT use for sales-targeting ideal customer profiles with filterable firmographics and buying committees - use icp-persona-builder instead. Do NOT use for extracting jobs-to-be-done from research - use jtbd-extractor instead.
-
viryazheng Bundle Acp FeedExports merchant catalog data to an OpenAI Agentic Commerce Protocol product feed shape. Use when preparing products for ChatGPT Commerce, Instant Checkout readiness, or OpenAI ACP feed/API onboarding after catalog data has been mapped from Shopify, CSV, JSON, or UCP catalog JSON.
-
viryazheng Bundle Ucp CatalogMaps merchant product data from Shopify products.json, CSV, or existing JSON into the repo's UCP-style catalog JSON. Use after ucp-audit when product data needs to be normalized before UCP checkout work or OpenAI ACP feed export.
-
lingyichen-ai Bundle Excel Processor处理 Excel 文件,支持读取、分析、统计和导出 xlsx 数据
-
artemiimillier Bundle Analytics TrafficСобирает публичные метрики трафика (views, comments, likes) для опубликованных постов. Парсит публичные страницы vc.ru; Дзен/Telegram — stub'ы. Не использует приватные admin API.
-
bitrix24 Bundle B24jssdk RecipesEnd-to-end mini-apps built on the canonical b24jssdk actions.v{2,3}.* surface — CRM analytics, ERP sync, Telegram bot, mass mailing, task automation, AI assistant, web search + LLM, Disk files, webhook handler, error-handling cookbook, event registration, OAuth install handshake. Each recipe is a single TypeScript program using B24Hook on the server side. Load when the user asks for a working example or a starting template.
-
deepgram Skill Deepgram Dotnet Audio IntelligenceUse when writing or reviewing C# code in this repo that enables Deepgram intelligence overlays on Speech-to-Text requests. Covers `PreRecordedSchema` analytics flags such as `Summarize`, `Topics`, `Intents`, `Sentiment`, `DetectLanguage`, `DetectEntities`, `Diarize`, and `Redact`, plus the smaller live-streaming subset on `LiveSchema`. Use `deepgram-dotnet-speech-to-text` for plain transcription and `deepgram-dotnet-text-intelligence` for analytics on already-transcribed text.
-
deepgram Skill Deepgram Go Speech To TextUse when writing or reviewing Go code in this repo that transcribes prerecorded audio with Listen v1 REST or streams live audio with Listen v1 WebSockets. Route text generation to deepgram-go-text-to-speech, text analysis to deepgram-go-text-intelligence, audio analytics overlays to deepgram-go-audio-intelligence, and Flux or other v2 conversational work to deepgram-go-conversational-stt.
-
deepgram Skill Deepgram Java Speech To TextUse when writing or reviewing Java code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live transcription. Covers `client.listen().v1().media().transcribeUrl` / `transcribeFile` (REST) and `client.listen().v1().v1WebSocket()` (WebSocket). Use `deepgram-java-audio-intelligence` for analytics overlays, `deepgram-java-conversational-stt` for Flux `/v2/listen`, and `deepgram-java-voice-agent` for full-duplex assistants. Triggers include "transcribe", "speech to text", "STT", "listen v1", "nova-3", "live transcription", and "websocket transcription".
-
dtsong Bundle Bank RecPerforms bank reconciliations between a bank statement export and GL cash detail. Use when the user provides a bank statement file (CSV, XLSX, or PDF) and a GL cash detail file and asks to reconcile, match transactions, identify outstanding items, or produce a bank rec workpaper. Outputs a matched/unmatched workbook, aged reconciling items, proposed adjusting JEs, and an evidence table.
-
duneanalytics Skill Review SpellReview Spellbook spell contributions for config blocks, schema YAML, SQL style, Jinja, performance, seeds, architecture, and compile/test readiness.
-
duneanalytics Skill Run Dbt CommandsRun dbt CLI commands (compile, ls, test, run, etc.) in the spellbook repo. Use when the user asks to compile, list, test, or run dbt models, or when you need to validate SQL by compiling a model.
Frequently asked questions
What are Data & Analytics agent skills?
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
Which Data & Analytics skills are most installed?
Popular Data & Analytics skills on SkillMD right now include r-databricks-unity-catalog, famou-data-analysis, Web analytics triage. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Data & Analytics skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.