Data & Analytics

codex-data Bundle

Use when the user asks about token prices, charts, holders, trending tokens, pair data, prediction markets, or any on-chain analytics from Codex. Also use when building GraphQL queries against https://graph.codex.io/graphql. TRIGGERS: token price, token chart, trending tokens, pair data, holders, prediction markets, Polymarket, Kalshi, event odds, prediction event, prediction traders, trader leaderboard, trader PnL, prediction charts, outcome probability, open interest, prediction categories, betting markets, market resolution, prediction positions, prediction trades

converlyio Bundle

Set up Converly conversion tracking end to end. Use when the user wants to track form submissions as conversions, send leads to an ad platform like Google Ads, Meta or Google Analytics, or set up Converly for the first time.

conversiontools Skill

Convert files between 140+ formats using Conversion Tools. Two surfaces are available - the `ctio` CLI (preferred when shell access is available) and the hosted Conversion Tools MCP server (zero-install, works everywhere). Covers documents (Word, PDF, Excel, PowerPoint), data formats (JSON, CSV, XML, YAML, Parquet), images (PNG, JPG, WebP, AVIF, HEIC, JXL, SVG), audio (MP3, WAV, FLAC), video (MOV, MKV, AVI to MP4), e-books (EPUB, MOBI, AZW), OCR text extraction, AI-powered data extraction, AI text-to-speech (TTS), AI speech-to-text transcription (STT), subtitle conversion (SRT, VTT, ASS), and website screenshots. Plus build custom converters on demand - describe a transformation in plain language and Conversion Tools creates, runs, and returns a reusable converter when no standard one fits.

anbeime Bundle

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When working with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

angus221 Bundle

简历分析与评估技能。从PDF简历中提取信息，按照多个维度对候选人进行打分评估，并生成Excel分析报告。当用户需要分析简历、筛选候选人、评估面试者与岗位匹配度时使用此技能。支持单个简历文件和批量简历文件夹的分析。

antvis Bundle

Comprehensive guide for AntV L7 geospatial visualization library. Use when users need to: (1) Create interactive maps with WebGL rendering (2) Visualize geographic data (points, lines, polygons, heatmaps) (3) Build location-based data dashboards (4) Add map layers, interactions, or animations (5) Process and display GeoJSON, CSV, or other spatial data (6) Integrate maps with AMap (GaodeMap), Mapbox, Maplibre, or standalone L7 Map (7) Optimize performance for large-scale geographic datasets

artemnovitckii Skill

Use when a new user opens this repo for the first time (no data/strong_workouts.csv yet), or says "interview me", "coach me", "build my program", or wants to load their workout data. Onboards them as a cited Jeff Nippard training coach.

aws-samples Bundle

Agent に自然言語で質問を送り、データを SQL で分析した結果を返す。

andreabozzo Bundle

Use when working with Ceres — a Rust harvest-first toolkit and public open data metadata index. Covers harvesting and synchronization, optional embedding and search, CKAN, DCAT udata, and SPARQL-backed DCAT portal support, Parquet snapshot manifests/reports/changelogs, Ollama or hosted providers, CLI commands, REST API endpoints, portal configuration, architecture, extending via traits, release workflow, and contributing to the Ceres codebase.

andreabozzo Skill

Use when publishing a HuggingFace dataset export for the Ceres Open Data Index. Covers the full workflow — data quality checks, Parquet export, snapshot manifest, coverage/quality reports, snapshot changelog, README dataset card update, versioning, and push to HuggingFace.

johnrothan Bundle

Alibaba Java Development Manual (Huangshan Edition) coding standards. Use this skill whenever you write, review, refactor, or evaluate any Java code — covering naming conventions, constant definitions, code formatting, OOP rules, date/time, collection handling, concurrency and multithreading, control statements, comments, exception handling, logging, unit testing, security, MySQL table/index/SQL/ORM design, and application-layering project structure. Whether or not the user explicitly mentions "Alibaba spec / P3C / Huangshan / development manual", proactively apply the rules and severity levels here for any task that produces or vets Java code (e.g. "write a Java class / Service / DAO", "review this Java", "is this code compliant?", "create a MySQL table", "help me name this", "handle exceptions and logging").

belschak Bundle

Curate Google Maps through the user's own logged-in Chrome (Playwright over CDP). Create Saved Lists, set list emoji icons, save places in ranked order, write per-place notes, generate share links, delete lists; fall back to My Maps for custom lat/lng pins, colored layers, and CSV bulk import. Use whenever a task should end with places on Google Maps or touches existing Maps lists, even if the word "Maps" never appears: "make a list of these restaurants", "save these places", "share a map with the group", "pin these spots", "add notes to my saved places", "toggle themed lists", any trip prep whose result belongs on the user's phone. Not for researching or ranking the places themselves; that is the map-scout skill.

bouffalolab Bundle

BL616/BL618 低功耗 IO 唤醒（GPIO wakeup）设计引导、配置校验与故障诊断：客户不知道怎么分配唤醒引脚/选触发方式、唤醒配置需核对（xlsx 或口头描述）、唤醒不生效、睡眠电流偏大、误唤醒、ACOMP 唤醒困惑、HBN IO 唤醒，或需要标准唤醒配置模板时使用。

brandonburrus Bundle

Write correct, performant SQL across major data warehouse dialects.

brandonburrus Skill

Concise SQL query generation with minimal explanation.

breakthrough-edu Bundle

Turn the business data the user already has (Airtable, Notion, Google Sheets, Lark Base, Excel, CSV exports, or a database someone once set up for them) into three things in one sitting: a plain-language account of what their database actually records, a findings list of data problems and blind spots, and a one-page dashboard answering the single most urgent money question, with alerts ranked by money at risk. Use when the user wants a dashboard or a read of their data ("build me a dashboard", "turn my spreadsheet into a dashboard", "what is my data telling me", "帮我做仪表板", "分析我的数据/表格"), pastes a link or drops files from one of those products and asks what the data says, or returns with a fresh export to refresh a page built earlier. NOT for designing or restructuring the database itself (that is breakthrough-base-schema-design), NOT for setting up a second brain or vault, and NOT a live auto-updating dashboard: every page is a snapshot of one export.

broomva Bundle

Evaluator-Governed Recursive Improvement (EGRI) framework for turning ambiguous goals into safe, measurable, rollback-capable recursive improvement systems. Use when the user wants to: (1) build a self-improving system for any domain (ML, RAG, workflows, ETL, UI, compiler tuning, etc.), (2) formalize a vague optimization goal into a bounded loop with evaluator, harness, and promotion policy, (3) create an autoresearch-style system beyond ML training, (4) design a mutable-artifact + immutable-evaluator architecture, (5) scaffold a problem-spec for recursive improvement, (6) turn "make X better" into a safe, auditable optimization process. Triggers on: "self-improving", "autoresearch", "autoany", "EGRI", "recursive improvement", "optimization loop", "evaluator-governed", "harness + evaluator", "mutable artifact", "problem compiler", "benchmark loop", "mutation surface".

capsoftware Skill

Always use Cap's CLI or local MCP first when the user mentions Cap, a Cap URL, screen recording, the Cap library, transcripts, chapters, comments, reactions, sharing, analytics, organizations, storage, billing, or developer apps. Cap should be operated without browser automation or computer-use tools whenever its CLI or MCP surface supports the task. Requires the `cap` command from Cap Desktop (https://cap.so).

castorini Bundle

Measure a parquet document corpus - token-length distribution, exact and near-duplicate detection, and how much survives deduplication. Use when asked to analyse corpus statistics, find duplicates, count tokens, compute what dedup would remove, or produce corpus figures for a paper. Triggers include "corpus stats", "duplicate detection", "near duplicates", "MinHash", "dedup", "how many tokens", "document length distribution", "ClimbMix analysis".

crafter-station Skill

Local-first analytics and structural audits for AI agent skills. Use when reviewing skill health, context cost, private local or Tailscale-remote usage receipts, conflicts, coverage, token burn, or pruning.

cxrxhz Bundle

批量提取 LFA / laser flash CSV 中每个编号样品的热扩散率。Use when 用户要提取 LFA、热扩散率、激光闪射结果、#Mean/#Std_Dev、批量整理 LFA 数据，或要把 LFA 原始 CSV 先规范化后再用于 Origin/作图。

dbt-labs Bundle

Connect an AI coding agent to Snowflake, BigQuery, or Databricks so it can run SQL. Use when warehouse access is missing, authentication or connection selection is required, or before using a warehouse-data skill such as agents-schema-search.

dbt-labs Bundle

Use when answering questions about data in a warehouse (BigQuery, Snowflake, etc.) and you have direct SQL access (CLI, driver, or console). Discover metadata and run knowledge search through the warehouse-native AGENTS schema instead of INFORMATION_SCHEMA.

dbt-labs Skill

Use when adding support for a new data warehouse adapter (e.g., Trino, Postgres, Spark) to dbt-query-profiler. Triggers include creating adapter macros, implementing query history/plan/stats, or extending platform support.

gilbarbara Bundle

Audit and optimize Algolia DocSearch setups: diagnose content indexing gaps, fix crawler selectors, add synonyms, create custom records for non-crawlable pages, and verify improvements via analytics. Use when the user mentions DocSearch not returning good results, search gaps, no-result queries, crawler config debugging, search relevance tuning, Algolia analytics, or wants to improve their documentation site's search quality. Also trigger when they mention search audit, missing search results, or want to check if their Algolia index is working correctly.

github Bundle

Analyze C++ build performance using vcperf.exe and ETL traces. Use this skill when the user wants to profile a build, understand compile bottlenecks, identify expensive headers or templates, generate JSON analysis reports, or interpret vcperf output. Covers tracing workflows, the /jsonAnalysis flag, reading the resulting JSON schema, and actionable remediation strategies for each bottleneck category.

grooverlab Skill

Find and load the right skill from the user's stash warehouse for the task at hand, then do the task under it. Invoke as /stash <task>. User-invoked only.

handsontable Bundle

Use this skill when the user works with HyperFormula (HF) — a headless, open-source TypeScript spreadsheet calculation engine. Use it when the user: mentions HyperFormula or HF; wants to integrate Excel-like formulas into a JS/TS app; evaluate formulas programmatically in a browser or Node.js; simulate spreadsheet or Excel calculation behavior server-side; run calculations over data parsed from XLSX files (e.g. via SheetJS) in code; build a pricing engine, financial model, or what-if analysis in code; define custom spreadsheet functions or named expressions outside of a UI context. Do NOT use this skill for: general Excel questions unrelated to HF; general Google Sheets questions; generic spreadsheet formula-syntax questions outside an HF context; formulas used inside Handsontable (use the "handsontable" skill instead).

harrycain72 Skill

Excel (XLSX) Skill

luoling8192 Skill

Designing Data-Intensive Applications (DDIA) distilled reference guide by Martin Kleppmann. MUST be loaded when: designing database schemas, choosing storage engines, implementing replication or partitioning, handling distributed transactions, building batch/stream processing pipelines, choosing consistency models, implementing consensus, designing data flow architectures, evaluating trade-offs between availability and consistency, encoding/serialization decisions, data modeling (relational vs document vs graph), building fault-tolerant systems, or any system design and architecture discussion involving data-intensive applications. Trigger on: database design, replication, partitioning, sharding, transactions, isolation levels, consistency, consensus, CAP theorem, batch processing, stream processing, MapReduce, Kafka, event sourcing, CDC, OLTP, OLAP, B-tree, LSM-tree, data warehouse, schema evolution, encoding formats, distributed systems, fault tolerance, leader election, quorum.

maojiebc Bundle

会员数据顾问·马甲实战版（majia-huiyuan）。当核心交付物是会员指标口径、RFM、复购/留存/流失公式、核销率、客单价、会员分层/分群、人群圈选、标签体系、CDP、OneID 身份打通、Cohort、CRM/私域数据分析、会员数仓（DIM/DWD/DWS/ADS）、SQL/DDL、字段词典、数据质量、会员看板或观远 BI 复刻时使用。用户提出召回、提频、防流失、流失预警、新客转化、渠道迁移（外卖↔堂食）、导购任务分派等会员运营动作时，动作背后的数据依据（圈谁/何时/力度/派给谁/怎么回收）由本 Skill 负责；动作的执行内容（朋友圈、群发、欢迎语、社群 SOP、企微操作）与私域整盘经营诊断走 majia-siyu——同一动作的两半，先数据后执行。全部数值为模拟数据，仅结构与口径可引用。

marcelocruzrpa Bundle

Build UiPath Studio projects, REFramework scaffolds, XAML workflows, and VB/C# expressions via 104 deterministic Python generators (plus plugin generators). ALWAYS use this skill — never hand-write .xaml files. TRIGGER when the user mentions UiPath, REFramework, XAML, RPA, Orchestrator, UiPath Studio, dispatcher, performer, queue items, robot, ACME (test app), .xaml, project.json, Config.xlsx, or asks to build/generate/scaffold/automate anything resembling RPA. SKIP only when the task is explicitly Power Automate, n8n, Zapier, or non-UiPath RPA.

innei Bundle

Use when AI encounters Slack permalinks (https://*.slack.com/archives/...), Slack IDs (C.../U.../D.../F...), thread 讨论上下文, 搜索 Slack 历史消息, 按邮箱/handle 反查用户, 浏览频道最近动态, 下载 Slack 附件（截图/日志/CSV/PDF), 或需要把 @handle / #name / ^subteam 解析成 ID 时.

insforge Skill

Use when working on the @insforge/cli codebase itself — adding or modifying commands under src/commands/, touching src/lib/api or src/lib/analytics, changing package.json version, wiring telemetry, or preparing an npm release. Covers code conventions, PostHog analytics, agent-skills sync, and the tag-triggered publish workflow.

jaredlander Bundle

R-first data science and statistical analysis with SQL as secondary language. Use when the user asks to analyze data in R, write R scripts, create tidyverse pipelines, build statistical models, work with time series (fable/tsibble), run machine learning workflows (tidymodels), query databases from R (DuckDB, dbplyr), build reproducible pipelines (targets), or parallelize computations (crew/mirai). Triggers on R, tidyverse, dplyr, ggplot2, targets, tidymodels, DuckDB, time series forecasting, or statistical modeling requests.

jeffsenso Skill

Dolibarr ERP/CRM developer skill. Use for: building or extending Dolibarr modules (external/custom), implementing hooks, triggers, DAO classes, SQL tables, menus, permissions, tabs, boxes, PDF templates, cron scripts. Covers both core contributor and external module developer workflows. Applies coding rules (PSR-12, SQL norms, MVC pattern, Active Record).