Data & Analytics

vrtalex Skill

Безопасность сайтов на «1С-Битрикс: Управление сайтом» — модуль «Проактивная защита» (проактивный фильтр/WAF, веб-антивирус, панель безопасности, OTP/двухфакторка), безопасная разработка (XSS-экранирование htmlspecialcharsbx, CSRF/check_bitrix_sessid, защита от SQL-инъекций, LFI, права доступа), аудит безопасности. Используй для задач безопасности на сайте Битрикс (не Битрикс24).

vstorm-co Bundle

PostgreSQL production patterns — safe migrations, indexing strategies, connection pooling, schema design, and query optimization. Use this skill when the user is working with PostgreSQL, writing database migrations (Alembic, Django migrations, raw SQL), designing database schemas, optimizing queries, setting up connection pooling (PgBouncer, asyncpg), or asks about database best practices. Triggers on SQL files, migration files, SQLAlchemy models, Django models, or Prisma schemas that target PostgreSQL.

zhengyunhui123-dev Bundle

根据调研报告、对话上下文、解决方案或原有功能清单进行需求功能化，生成能指导开发的项目功能清单。适用于 product-requirements-researcher 完成需求挖掘后，把需求转成功能点，并补充为支撑业务闭环所需的系统功能。先生成 MD 供确认，确认后导出为 XLSX。Use when the user wants to convert requirements into development-ready feature points from research reports, current context, solution documents, or existing feature lists.

databrickslabs Skill

Write TSAL (Time Series Analytics Language) expressions in Impulse — select measurement channels by metadata tags, derive virtual signals with arithmetic, express conditions as time windows, detect edges, resample, integrate, and build histograms. Use when the user wants to "select a channel", "build a virtual/derived signal", "detect when signal > X", "compute distance from speed", "find rising edges", or asks what a TSAL expression evaluates to. Covers `QueryBuilder.channel()`, operators, all signal methods, and the four result types (SampleSeries, Intervals, PointsInTime, PointsInTimeSeries).

databrickslabs Skill

Run ad-hoc Impulse analysis in a notebook — evaluate TSAL expressions directly through the query engine and get a Spark or pandas DataFrame back, with no gold-layer write and no reporting setup. Use when the user wants to "explore signals interactively", "get a DataFrame from Impulse", compute a quick per-container mean/histogram, or prototype expressions before wiring them into a report. Covers building a query on a MeasurementDB, `select()`, `solve()` / `toPandas()`, and choosing the solver.

datus-ai Skill

Generate, review, and understand TiDB SQL. Use for TiDB queries and DDL where MySQL compatibility, unsupported constructs, silently-ignored clauses, or write-hotspot avoidance can affect correctness or performance.

datus-ai Skill

Generate, review, and understand Apache Doris SQL. Use when the target engine is Apache Doris (not StarRocks or MySQL) for queries, OLAP DDL with the Duplicate/Unique/Aggregate key models, bucketing and partitioning, synchronous and asynchronous materialized views, multi-catalog addressing, and loading through Stream Load, Routine Load, or INSERT INTO SELECT over a TVF or catalog.

datus-ai Skill

Generate, review, and understand Oracle Database 19c SQL and PL/SQL. Use for Oracle queries, DDL, DML, stored procedures, functions, packages, anonymous blocks, profiling, transfers, and SQL rewrites where namespace, identifier, pagination, data type, alias, procedural, or write syntax differs from other dialects.

datus-ai Skill

Generate, review, and understand GaussDB / openGauss SQL. Use for GaussDB queries, DDL, DML, table design, and SQL rewrites where PostgreSQL compatibility, A/B/PG database compatibility modes, distributed deployments, or version-specific syntax matter.

datus-ai Skill

Generate or review Google BigQuery Standard SQL, especially when project.dataset qualification, nested data, time semantics, partition pruning, or BigQuery-specific DDL affect correctness or cost.

datus-ai Skill

Generate, review, and understand Snowflake SQL. Use for Snowflake queries, DDL, DML, MERGE, semi-structured data, stages, COPY operations, materialized views, profiling, transfers, and rewrites where identifiers, namespaces, data types, functions, constraints, or loading syntax differ from other dialects.

datus-ai Skill

Generate, review, and understand StarRocks SQL. Use for StarRocks queries, OLAP table DDL, DML, materialized views, catalogs, S3/GCS imports with FILES() or Broker Load, Stream Load, Routine Load, and rewrites where MySQL compatibility, table types, distribution, functions, or loading semantics can affect correctness.

deepmodeling Bundle

Guide for adding new resources (materials, bottles, carriers, decks, warehouses) to Uni-Lab-OS (添加新物料/资源). Uses @resource decorator for AST auto-scanning. Covers Bottle, Carrier, Deck, WareHouse definitions. Use when the user wants to add resources, define materials, create a deck layout, add bottles/carriers/plates, or mentions 物料/资源/resource/bottle/carrier/deck/plate/warehouse.

deusyu Bundle

Natural language bookkeeping — parse Chinese/English expense descriptions and append to QianJi CSV. Trigger phrases: 记账, 记一笔, add expense, spent, 花了, 买了, lunch, dinner, 打车, 咖啡, or any input that looks like "[item] [amount]" or "[amount] [item]".

bgevorkian Bundle

Query and execute Microsoft SQL Server SQL through a JSON CLI. Use when the user explicitly asks to inspect MSSQL/SQL Server or run a confirmed DDL, DML, or administrative statement. Access is limited by the configured SQL Server account grants.

bgevorkian Bundle

Query and execute Trino or Iceberg SQL through a JSON CLI. Use when the user explicitly asks to inspect Trino/Iceberg or run a confirmed DDL, DML, or administrative statement. Access is limited by the configured Trino account and catalog grants.

bgevorkian Bundle

Query and execute PostgreSQL SQL through a JSON CLI, including bounded read-only fan-out across hosts. Use when the user explicitly asks to inspect PostgreSQL/Postgres or run a confirmed DDL, DML, or administrative statement. Access is limited by the configured PostgreSQL role grants.

bgevorkian Bundle

Query and execute ClickHouse SQL through a JSON CLI. Use when the user explicitly asks to inspect ClickHouse or run a confirmed statement such as CREATE, ALTER, INSERT, DELETE, DROP, RENAME, or OPTIMIZE. Access is limited only by the configured ClickHouse user grants.

kaito41418-ux Bundle

Skill: regression-analytics

kaito41418-ux Bundle

Skill: advanced-data-analytics

kgelster Bundle

Use when a store owner is doing bulk data work through the Matrixify (formerly Excelify) app: bulk import/export, "migrate my catalog", "bulk update prices", "bulk edit metafields", CSV or Excel import, "my import deleted my metafields", "my import wiped my tags", MERGE vs REPLACE vs UPDATE, "how do I undo an import", building a Matrixify sheet by hand or programmatically, or a data migration between stores/platforms. Covers products, variants, metafields, collections, redirects, customers, and menus. Not for minting category (taxonomy) metafields, which Matrixify cannot do (use shopify-category-taxonomy); not for one-off single-record edits via the Admin API (use the relevant entity skill).

kgelster Bundle

Use when you assign the Shopify Standard Product Taxonomy category, "set the product category", "categorize the catalog", or fill the category / taxonomy metafields: the admin "Category metafields" panel (Color, Size, Material, Caffeine content), a.k.a. product category attributes / taxonomy attributes, including the attributes a Google feed asks for. Covers bulk classification, discovering a category's attributes and allowed values, minting the reserved value metaobjects, and writing them safely. Also: "category metafields show blank/null", "my Color attribute won't save". Not for bulk CSV data loads (Matrixify can't do this; see shopify-matrixify for bulk data).

kochellenk-afk Skill

The single skill for all Google Ads negative keyword and search term work, with three modes: Audit (find wasted spend in a search terms report), Leakage (find systematic gaps in existing negative lists), and Mine (proactively build a comprehensive negative list for new campaigns or overhauls). Use this skill whenever the user wants to analyze, audit, or clean up search terms, find wasted ad spend, identify irrelevant queries, build or expand a negative keyword list, audit their negatives, or asks anything like "why is my CPA bad", "where is my budget leaking", "review my search terms", "what negatives should I add", "what should I be blocking", "negative keyword gaps", or uploads a Google Ads search terms report (CSV/Excel). Trigger even when the user doesn't say "negative keywords" explicitly: any request involving search terms data, PPC waste reduction, or blocking irrelevant traffic qualifies.

konstruktoid Bundle

Authors and modifies Python source code with security best practices that static analysis alone does not fully cover, including input handling, deserialization, secrets, subprocess/SQL/crypto usage, SSRF, and dependency hygiene, layered on the ruff/ty quality gate. Use when writing or editing Python, and especially for changes touching user input, subprocess/OS calls, SQL or other query construction, templating, cryptography, secrets/credentials, or access control.

lavidrori0702 Bundle

Acquires the data for a tableau-dashboard-plugin project and writes the DATA-MODEL.md handoff artifact. CSV mode (the default, zero-credential path) profiles the analyst's data/*.csv into documented field names + types and validates that headers match exactly; the scaffold/sample-data/ demo CSVs are the fallback. The published-ds route (datasources.json + .env) samples published sources through the VizQL Data Service into data/*.csv. Use when the user wants to acquire or model dashboard data, build DATA-MODEL.md, or when tableau-route reports data is next. Step 3 of 8 in the workflow.

mx-space Skill

Author and review Drizzle SQL migrations safely for rolling deploys. Triggers when editing apps/core/src/database/schema/*.ts or apps/core/src/database/migrations/*.sql, when the user runs drizzle-kit generate, when "lint-migrations" reports a violation, or on prompts like "迁移", "改 schema", "alter table", "add a column", "drop column", "migration safety". Enforces the expand-contract pattern because mx-core ships rolling deploys (Dokploy, 2 replicas) where new and old pods coexist for tens of seconds during cutover.

narrative-io Bundle

Translate a fuzzy analytical question into a rigorous investigation plan. Interrogates the ask, grounds the plan in the available data dictionary, applies analytical best practices, and produces a structured brief of query specifications for a downstream query-writing skill. Plans, does not write SQL. Use when: "why did X drop", "is there a relationship between A and B", "who are our highest-value customers", "what's driving the change in Y", "investigate this trend", "design an analysis for", "scope this analytical question". (narrative-common)

akovalion Skill

Test case authoring per QA best practices, with CSV export for Zephyr Scale import (Option 1) or direct creation via your TMS MCP. Use when the user asks to generate, write, or prepare test cases, checklists, or CSV for TMS import.

allium-labs Bundle

Query blockchain data using the allium CLI. Two products: Explorer (SQL analytics on Allium's data warehouse — any table, any timeframe, 150+ chains) and Realtime (3-5s freshness lookups for prices, balances, transactions, PnL, positions across 80+ chains). Supports API key, x402 micropayments, and Tempo MPP.

allium-labs Skill

Methodology playbook for analyzing DEX/AMM trade, liquidity, and pricing data on Allium — Uniswap, PancakeSwap, PumpSwap/Pump.fun, Orca, Pendle, aggregators (0x, 1inch), and perp DEXs like Hyperliquid. Use whenever a question touches swap volume, trade counts, liquidity positions, impermanent loss, aggregator fee/routing analysis, or DEX-derived token prices — even if the user just names a protocol or asks why a number "looks off" compared to a known reference. Covers the per-hop double-counting, protocol-vs-project grouping, and fee-leg reconstruction pitfalls that come up repeatedly before you write the SQL.

allium-labs Skill

Methodology playbook for analyzing cross-chain bridge and messaging-protocol data on Allium — CCTP, LayerZero, Wormhole, Across, canonical/application bridges, and general lock-and-mint flows. Use whenever a question touches bridge transfer volume, net flows between chains, tracing a specific cross-chain transaction, or attributing bridge activity to a protocol/integrator — even if the user just names a bridge or asks to "trace this transfer across chains." Covers the direction/double-counting mechanics and non-EVM tracing gap that come up repeatedly before you write the SQL. Distinct from a formal third-party coverage benchmark (see bridge-protocol-coverage-assessment for that) — this is the lighter-weight reference for getting an individual bridge query right.

allium-labs Skill

Methodology playbook for analyzing DeFi lending protocol data on Allium — Aave, Morpho, Fluid, Euler, Maple, Compound-style forks, and per-chain lending markets. Use whenever a question touches deposits, borrows, liquidations, collateral swaps, utilization, TVL, or leverage on a lending protocol — even if the user just names a protocol/asset or asks to compare two lending metrics tables. Covers the table-per-event-type join gotchas, column-naming inconsistencies, and liquidation-fill double-counting that come up repeatedly before you write the SQL.

allium-labs Skill

Methodology playbook for analyzing stablecoin volume, supply, holders, and geographic usage on Allium — USDC, USDT, DAI, USDS, RLUSD, USDG, JPYC, and other fiat/crypto/ algorithmic-backed stablecoins. Use whenever a question touches stablecoin transfer volume, circulating supply, wallet/holder counts, geo splits, or cross-chain deployments — even if the user just names a specific stablecoin, asks for "adoption" or "usage" numbers, or asks to compare volume to a chart/number they already have. Covers the raw-vs-adjusted volume distinction, chain-specific double-counting mechanics, and address/case-sensitivity gotchas that come up repeatedly before you write the SQL.

endearqb Bundle

技术讨论群成员画像与评估 Skill。当用户提供群聊记录（文本粘贴、截图、JSON/CSV 均可）并要求分析成员、给成员打分、评估社区健康度、 找出核心贡献者/潜水者/活跃用户/KOL、生成成员影响力排名、识别僵尸用户、分析群运营健康度、总结群聊内容等时，必须触发本 Skill。 适用场景：运营决策（KOL筛选、低价值成员风险评估）、个人研究（社区生态分析）、团队协作管理（成员贡献评估）。 触发关键词：群画像、成员分析、社区分析、影响力评估、活跃度分析、群运营分析、KOL识别、技术贡献者分析、群聊记录分析、僵尸用户、聊天总结。 即使用户只说"帮我分析一下这个群"或"看看谁最活跃"或"总结一下群里聊了什么"，也应触发本 Skill。

foundationdb Skill

This skill provides context for working in `fdb-relational-core`, the SQL processing layer

busirocket Bundle

Enforces Rust language and module standards for maintainable codebases. Use when writing Rust code, structuring modules, separating SQL/prompts from code, and enforcing one-thing-per-file discipline.