Data & Analytics

chainstream-io Bundle

Execute flexible GraphQL queries against ChainStream's on-chain data warehouse (27 cubes in 3 chain groups: EVM, Solana, Trading). Use when user needs custom analytics beyond standard REST/MCP — cross-cube JOINs, custom aggregations, complex WHERE filters, time-series analysis, or SQL-level flexibility on blockchain data. Supports x402/MPP auto-payment. Keywords: GraphQL, query, cube, DEXTrades, DEXTradeByTokens, Pairs, aggregation, join, on-chain analytics, custom query.

sentelabsai Skill

Evidence-first coding workflow. Use this skill for ANY task that writes, modifies, fixes, refactors, or reviews code — bug fixes, new features, refactors, config changes, even one-line edits. Verifies before presenting, attacks its own output with adversarial multi-model review, and tracks every check in a SQL ledger. The skill's own task-sizing scales effort down for trivial changes, so it is safe to apply broadly. Trigger whenever the user asks for code changes, mentions a bug, feature, refactor, or asks you to implement, fix, or improve anything in a codebase.

sketchup Skill

Find common extension issues. Based on the Extension Warehouse review.

slavins-co Bundle

Parse and query CellarTracker data for wine cellar management, inventory analysis, drinking window decisions, purchase history, consumption tracking, wishlist management, and scoring lookups. Uses MCP tools as the primary data source when available, with CSV fallback. Use this skill whenever the user asks about their cellar inventory, wants drinking window guidance, asks about past purchases or consumption history, references their wishlist, needs bottle counts or storage analysis, or asks anything that requires querying their wine collection data. Also trigger when the user says "check my cellar", "what do I have", "what should I drink", "my wishlist", "drinking window", "what have I consumed", "purchase history", or references CellarTracker data. This skill works alongside the wine-purchase-evaluator skill — use both together when evaluating purchases against existing inventory.

danielemosh Bundle

Run a rigorous state of the art literature survey on any STEM topic and deliver a compiled PDF report of about 5 pages. Opens by converging with the user on how deep and granular the survey should go, then produces a DOI verified corpus CSV, open access PDFs with a request manifest, Tufte style seaborn figures, and testable hypotheses mined from the future work sections of the surveyed papers. Use whenever the user asks to survey a field, review the literature, map the state of the art, find who did it best, compare methods or benchmarks across papers, understand what a research area is solving for, or scope the open problems in a topic. Trigger on phrases like "survey the SOTA", "literature review", "state of the art of X", "what is the research on X", "who is leading in X", "map the field".

darvin2802 Bundle

Identify every basin-attributed numeric value in a US/Canada onshore oil & gas report and enter it as a "byte" into the 39-column Skeleton XLSX.

dezxbt Bundle

Drive X/Twitter from the CLI (read, post, DM, lists, communities, Grok, scheduling, analytics). Use when an agent needs to read or act on X/Twitter. Every command prints one JSON envelope.

starrocks Bundle

Propose verified fixes for documentation SQL examples that fail the doc-rot checker (docs/scripts/run_sql_samples.py). Checks all three languages (docs/en, docs/zh, docs/ja) against every supported version (auto-discovered), classifies each FAILing example, and only for genuinely fixable ones proposes a corrected statement, verifies it against a live cluster of each version via the StarRocks MCP server, applies it to every language that carries the example, lints every file it touched with Vale (the same gate CI runs), and opens DRAFT [Doc] PRs whose backport boxes match exactly the versions each fix was verified on. Also emits a cross-language parity report. Never auto-merges.

tathadn Skill

Audits CSV and Excel files for data quality issues and generates a professional PDF report with charts and figures, plus a detailed Excel workbook. Includes bar charts, pie charts, heatmaps, histograms, and trend analysis. Use this skill whenever the user uploads a dataset and asks for a quality check, data audit, data cleaning assessment, data profiling, or wants to know what's wrong with their data — even if they don't use the word 'audit'. Also trigger when users ask for a 'data health check', 'data quality report', or 'what should I clean in this data'.

tathadn Bundle

Generates a professional PDF summary report with charts, figures, and written analysis from a clean CSV or Excel dataset, plus a companion Excel workbook with detailed statistics. Produces bar charts, pie charts, histograms, trend lines, and correlation analysis. Use this skill when the user asks for a data summary report, dataset overview, data profile report, analytics report, or wants a professional document summarizing their data — even if they just say 'summarize this data', 'create a report', or 'analyze this file'.

tconbeer Bundle

What hsql's Agent Skill teaches an agent, and three ways to install it — hsql --skill, the plugin marketplace, or the copy published here.

terrylica Bundle

ClickHouse SQL anti-patterns and performance constraints discovered during Gen200-Gen600 barrier framework. Use when writing ClickHouse SQL, creating new barrier/pattern generations, modifying array functions, window functions, parameter sweeps, forward arrays, or encountering slow queries, OOM, NULL entry prices, wrong barrier detection, arrayFirstIndex returning 0, or aligning SQL results with backtesting.py. TRIGGERS - ClickHouse SQL, barrier SQL, array function, window function, trailing stop SQL, parameter sweep, slow query, OOM, arrayFirstIndex, leadInFrame, groupArray, arrayFold, arrayScan, threshold-relative, anti-pattern, performance constraint, forward arrays, self-join, O(N×M), SQL vs Python, SQL vs backtesting.

ai4mse Bundle

3-in-1 China 12306 query tickets + route stops + transfer plans, zero login. Filter 高铁/动车/火车 by type, time, duration. Pure Python, text/json/csv output. Use for 火车票/余票/经停站/中转换乘.

airbytehq Bundle

Evaluate whether a Stripe credit card dispute (chargeback) is worth fighting, and assemble a ready-to-submit evidence package to fight it. Pulls live context from Stripe plus your configured support, docs, chat, analytics, and order-data sources through Airbyte (Agent MCP or SDK), maps it to Stripe's dispute evidence fields, and produces both a structured JSON payload and a human-readable rebuttal document. Also posts a daily triage digest to your team chat. Use whenever a user mentions a dispute, chargeback, "representment," a Stripe dispute ID (dp_...), a disputed charge (ch_/pi_), asks whether a dispute is winnable or worth contesting, needs to gather or write up evidence for a chargeback, asks to respond to a card network / issuer dispute, wants a daily/recurring summary of disputes posted to Slack, or asks to set up / configure the skill or choose which data sources to connect — even if they don't say "Airbyte" or "evidence package." Always stop for human review before anything is submitted to Stripe.

albert-lsk Bundle

Use when the user wants to install, update, diagnose, or repair alskai-notebank; save, archive, export, migrate, or process WeChat public account (微信公众号) articles; convert them to Markdown; batch import URLs from Excel or Numbers; turn saved articles into reviewable knowledge candidates; or review, approve, reject, and revoke generated knowledge assets.

alchaincyf Bundle

数据分析全流程：体检脏表、清洗、定口径、算指标、对账、出报告。处理 Excel/CSV/系统导出数据，做透视写公式，查两个数为什么对不上，判断一个数靠不靠谱时用。核心是让算出来的数字经得起追问。幻灯片和 PPT 交给 huashu-design。

pynbj1001 Bundle

腾讯文档，提供完整的腾讯文档操作能力。当用户需要操作腾讯文档时使用此skill，包括：(1) 创建各类在线文档（文档、Word、Excel、幻灯片、思维导图、流程图）(2) 管理知识库空间（创建空间、查询空间列表）(3) 管理空间节点、文件夹结构 (4) 读取文档内容 (5) 编辑操作智能表 （6）编辑操作文档。

mims-harvard Skill

Enforce synchronization between Kedro node files and catalog YAML files in the OptimusKG project. Use when editing any Python node file under optimuskg/pipelines/*/nodes/, including modifying run() functions, changing node() inputs/outputs, adding/removing/renaming DataFrame columns, or changing column types. Also use when creating new nodes or deleting existing ones.

genniao-photograph Bundle

为 AI 视频项目（首尾帧提示法）生成标准化的分镜表 Excel，包含「分镜表」与「形象设计」两个子表。负责编写首帧/尾帧/动态提示词、切分旁白与音效、控制景别渐进与形象一致性。当用户给出旁白文案/剧情脚本并需要制作 AI 视频分镜表时使用。不适用于纯剪辑/非线性剪辑工程、或与首尾帧文生图/图生视频无关的视频任务。

hansujab Skill

SprintLens is an engineering team health tool that answers "where is my team slowing down and why?" by JOINing data across GitHub, Linear, Sentry, PagerDuty, and Slack using Coral's cross-source SQL runtime. Use this skill whenever the user asks about team velocity, sprint health, engineering bottlenecks, cycle time, PR review time, who is overloaded, what is at risk, DORA metrics, or wants a weekly engineering report. Trigger phrases include: "sprint:", "velocity", "who is blocked", "what's slowing us down", "cycle time", "PR review", "who's overloaded", "engineering report", "team health", "what's at risk", "DORA", "lead time", "deployment frequency", "change failure rate", "MTTR", "on-call load", "who should I ask to review". Always use this skill when Coral sources (github, linear, sentry, pagerduty, slack) are connected and the user is asking about engineering team performance.

adventure-111 Bundle

影刀RPA平台的Python自动化开发技能。触发：用户提到影刀/xbot/自动化模块/excel网页/OCR，或要求开发新的影刀应用模块、开发xbot自动化脚本。必须激活此skill来处理影刀相关的代码开发任务。

agnostai Bundle

USE to guide an AI agent or CLI tool through adding Agnost AI analytics to a customer Python or TypeScript app from this installed skill directory. Inspect existing telemetry first, preserve a supported OTel path when it produces usable AI spans, otherwise use Agnost SDK/MCP packages, then verify the real conversation data model end to end.

helebest Bundle

Read-only research on Polymarket prediction markets — hot events, keyword search, event detail and tokens, historical price/probability trends, volume trends, plus whale leaderboard, any address's positions and P&L, and trade history, with CSV/JSON export. Use when the user wants market research, current probabilities, position/P&L lookups, whale tracking, time-series review, or data export. To place real buy/sell orders, use the polymarket-trade skill instead.

lili-luo Bundle

Unified task execution protocol for Codex-only work. Supports Single Task, Epic Task, and Batch Task while preserving CSV truth-source, validation gates, context recovery, and Debug-First failure exposure. WHEN TO USE: user asks to "track tasks", "create todo list", "make a plan", "track progress", "long task", "big project", "build from scratch", "autonomous session", "跟踪任务", "自主执行", "长时任务", "从零开始", "任务管理", "做个计划", "大工程", or when a task clearly requires 3+ ordered steps that produce file changes. DO NOT USE: single-step fixes, pure Q&A, code review, explaining code, search/research tasks, tasks with fewer than 3 steps, or tasks that do not produce file changes.

trailofbits Bundle

Print row and column counts for a CSV file

apitally Bundle

Retrieve and investigate API metrics and request log data from Apitally. Fetches aggregated metrics, request logs, consumers, and app metadata via the Apitally CLI, stores data in a local DuckDB database, and runs SQL queries to investigate issues or answer questions. Use when the user mentions Apitally, the Apitally CLI, API metrics, API request logs, or API consumers.

apolloio Skill

This skill should be used when searching for people, companies, employees, job postings, or news, OR when driving CRM data (contacts, accounts, deals), sequences, one-off outreach emails, lists/labels, custom fields, notes, phone calls, tasks, conversations, analytics, or credit/API usage in Apollo.io from the terminal. Activates when the user asks to "find people", "search companies", "enrich a contact", "look up employees", "find jobs at a company", "get company news", "create a contact / account / deal", "log a call", "create a task", "add to sequence", "send an email", "add to a list", "check analytics", "view credit usage", or any task involving Apollo.io data lookup or CRM writes from the terminal.

aradniankou Bundle

Security pre-screening of applications to civil society educational programs in repressive environments. Data-source agnostic (Airtable, Google Sheets, CSV, any form tool). Triggers: "screening", "pre-screening", "скрининг", "проверка заявок", "проверить участников", "check applicants".

arcadia-1 Bundle

Use when working with EVAS/evas-sim: installing or running the EVAS Verilog-A behavioral simulator, checking whether a voltage-domain Verilog-A/Spectre testbench can run in EVAS, verifying or building the required evas-rust core, or interpreting EVAS outputs such as tran.csv and strobe.txt.

aresbit Bundle

数据库内核 SQL 内置函数合成（SQLite / PostgreSQL / DuckDB / ClickHouse）。 覆盖各库的函数注册入口与模式、四大开发规范（功能准确/代码集成/鲁棒性/内存安全）、 各库错误处理与内存管理 API、以及编译/测试命令。用于给数据库写 C/C++ 原生函数、 扩展 SQL 能力时。知识提炼自 SIGMOD 2026 DBCooker/OpenCook 论文与源码。

arkohut Skill

Search the user's local Pensieve screenshot archive by text, app, or time range. Use when the user asks to find a screenshot ("find that thing I looked at last week", "show me when I was working on the Mastra integration", "find screenshots of the YouTube video about X"), or to locate a specific moment in time across captured activity. Returns ranked entity_ids with filepaths, timestamps, OCR snippets, and VLM-extracted structured metadata (app, topic, workspace). Can open the image locally for the user. Skip when the user wants aggregated stats, time-series analytics, or cross-day project rollups — those need separate tools.

artificialanalysis Bundle

High-performance data analysis using Polars - load, transform, aggregate, visualize and export tabular data. Use for CSV/JSON/Parquet processing, statistical analysis, time series, and creating charts.

cicbyte Bundle

影刀RPA平台的Python自动化开发技能。当用户需要开发影刀xbot自动化脚本、使用xbot API进行网页/桌面/移动端自动化、Excel/Word操作、数据库操作、AI集成、PDF处理等功能时使用此技能。

clasen Skill

Instructions for working with DeepBase, a multi-driver persistence library for Node.js. Use when the user needs to store or retrieve data, add persistence to a project, set up a key-value store, work with SQLite/MongoDB/Redis/JSON storage, migrate data between backends, handle multi-driver failover, or says things like "save data", "persist data", "I need a database", "store user data", "set up storage", or "integrate DeepBase". Do NOT use for full ORM/relational query needs or raw SQL work.

buildkit-ai Bundle

Head-to-head team and player comparison with statistical breakdowns, trend analysis, and structured matchup reports for NBA, MLB, and Soccer covering strengths, weaknesses, and historical context. Triggers: matchup analysis, head-to-head, team comparison, player comparison, sports analytics, stat comparison, pregame analysis, game preview, matchup trends, who will win, team strengths.

buluslan Bundle

review-analyzer-skill是由buluslan（公众号：新西楼.AI）研发的电商评论深度分析Skill（VOC 客户之声分析），他会帮你把一堆产品评论变成一份能落地的决策依据——22 维 AI 打标提炼用户画像、痛点和真实需求，输出 15 章深度洞察报告和可视化看板，从差评里挖出产品优化机会点、从好评里找到爆款基因。 更多跨境电商 AI 实战内容，请关注公众号「新西楼.AI」。 Deep-dive e-commerce review & VOC analysis: 22-dimension AI tagging, 15-chapter insight report with anomaly signal cards, 6 themed visualization dashboards, CSV-primary multi-source input (SellerSprite optional), Feishu sync. 当用户需要以下功能时触发：分析电商产品评论（Amazon等平台）/ 从评论中提取用户画像、痛点和VOC（客户之声）/ 生成产品洞察报告和机会点分析 / 创建可视化分析看板 / 通过卖家精灵获取评论数据（可选增强；CSV为主源）/ 将分析结果同步到飞书文档。 触发关键词：电商评论分析、评论分析、竞品分析、用户洞察、VOC分析、产品优化、市场调研、评论数据挖掘、卖家精灵、sellersprite。 NOT for 关键词调研/选品雷达类任务（那些有专门工具）。