Data & Analytics

frankchen021 Skill

Expert system for generating, validating, and optimizing ClickHouse SQL. Use this when the user needs data, queries, or analysis.

mepuka Skill

SQL & Databases

r04943083 Skill

Search indexed documents (PDF, Word, Excel, PPT, TXT) using BM25 keyword search. Use for EDA tools, company docs, bug reports, and technical documentation.

shaheershoaib Bundle

Use when moving or reshaping DATA rather than code - a legacy-system migration, a backfill, a bulk import, an ETL, a re-keying, or a one-off correction script over existing rows. Triggers on "migrate the data", "backfill X", "import from the old system", "reconcile the migration", "why is this row wrong since the migration". NOT for schema-only DDL with no data movement (that is an ordinary schema change, handled by expand/contract), and NOT for code-wide mechanical sweeps like a codemod or rename (that is a mechanical code sweep). Applies to any store - relational, document, key-value, warehouse - and to moves between kinds. The defining property: the correctness of the output cannot be observed from the input, so the whole discipline is about proving it on the destination. Also when only a schema dump or an extract has been handed over and the application code for either side has not.

thierryteisseire Bundle

Administration and automation for the Poffice suite (Mailcow, Seafile, Paperless-ngx). Use for: (1) Creating and managing mail accounts, (2) Sending and receiving emails, (3) Managing calendars and invites (via SOGo), (4) managing documents (Seafile/Paperless), (5) Creating and updating Word, Excel, and PDF documents, (6) Creating and sending calendar events and invites, (7) Automating office workflows.

yao2311 Bundle

Risk data feature analysis Skill — data preview, smart column detection, statistical description, correlation, IV, KS/AUC, feature recommendation, export Excel report and feature list

cognizant-ai-lab Bundle

Analyze and determine career information based on a person's given name

dojoengine Bundle

Run Torii for Dojo/Starknet: configure startup and options, verify endpoints, and query indexed data via SQL, gRPC, GraphQL, MCP, static routes, and metrics.

ukgovernmentbeis Bundle

Use when: updating test cases in General_TestCases.csv, syncing test cases from spec files, adding new test cases to CSV, documenting automated tests, checking for duplicate test cases, updating test case results or status. Maintains Documentation/Test Cases/General_TestCases.csv in sync with Playwright .spec.ts test files. Use for: 'update test cases', 'sync test cases', 'add test case to CSV', 'document this test', 'record test cases from this file'.

mvanhorn Bundle

Full Supabase database toolkit - schema explorer, natural language queries, CRUD, pgvector search, RLS policies, migrations, health checks, data export, Warehouse analytics, auto-embeddings, queues, Realtime, OAuth 2.1, Storage CDN, Edge Functions.

mwddmmde12-del Bundle

专业分镜师：将脚本（PDF/Excel/文本）拆解为电影级分镜方案，并生成 Veo 3.1 英文提示词和即梦 Seedance 2.0 中文提示词。当用户需要分镜、拆镜、storyboard、脚本拆解、视频分镜、AI视频提示词时触发。

useretrace Bundle

Analyze sales or Shopify export data to classify SKUs into A/B/C tiers by revenue or unit contribution, identify Pareto concentration, prioritize high-value inventory, and support decisions about SKU prioritization, assortment trimming, and inventory analysis. Use when an agent needs ABC analysis, Pareto analysis, SKU tiering, revenue concentration review, 80/20 analysis, or inventory prioritization from CSV exports.

useretrace Bundle

Identify dead stock, slow-moving inventory, declining SKU velocity, and carrying-cost waste from Shopify exports or generic sales and inventory CSVs. Use when an agent needs dead inventory analysis, slow-mover detection, catalog rationalization, warehouse waste review, or sales-velocity diagnostics for SKU-level inventory decisions.

useretrace Bundle

Clean and normalize messy Shopify CSV exports for products, orders, or inventory by fixing encoding issues, whitespace problems, sparse-row formatting, and common data-quality problems before analysis or re-import. Use when an agent needs Shopify CSV cleanup, forward-fill normalization, encoding repair, spreadsheet damage cleanup, or preparation of messy CSV exports for downstream inventory work.

useretrace Bundle

Generate a per-SKU inventory health report from Shopify exports or generic sales and product CSVs, including safety stock, reorder points, EOQ, stockout risk, overstock signals, and replenishment guidance. Use when an agent needs inventory planning, replenishment analysis, stockout prevention, overstock review, or SKU-level order recommendations from CSV data.

useretrace Bundle

Compare SKU performance across two periods using ABC classification, identify tier movement, detect major risers and declines, review SKU drift over time, and analyze changes in revenue or unit contribution from Shopify or generic CSV exports. Use when an agent needs SKU performance comparison, ABC drift analysis, period-over-period SKU movement, assortment change review, or seasonal SKU shift detection.

timeplus-io Bundle

Use when creating, packaging, or installing a Timeplus app (.tpapp) — converting existing SQL resources and dashboards into an installable app package, writing manifests, applying template variables, or debugging install failures

vfarcic Skill

Refresh the channel analytics block on content/sponsor/_index.md by fetching live numbers from the YouTube Data + YouTube Analytics APIs.

vichhka-git Bundle

Search and access the Tor dark web and .onion hidden services. Use when user asks to search dark web, investigate .onion sites, check for dark web data leaks, fetch onion URLs, hunt ransomware groups, look up leaked credentials, conduct Tor-based OSINT, or monitor dark web activity. Provides 12 search engines, batch scraping, entity extraction, relevance scoring, and export to CSV/JSON/STIX/MISP. Requires Tor running locally (socks://127.0.0.1:9050).

tomstools11 Bundle

Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.

toolbeltai Skill

Toolbelt is a collaborative substrate over your data. Upload any document — entities and relationships extracted automatically, queryable immediately. Ask questions that span structured tables, documents, and relationships in a single call. No stitching databases together. Toolbelt orchestrates semantic, structured, and hybrid retrieval through one MCP server — vector, knowledge graph, SQL, geospatial, streaming. Share the URL and any agent can query the same workspace — like a shared Google Doc for your data. Built by Kinetica. Use this skill at the start of any task where an agent needs to ingest documents and have entities/relationships auto-extracted, query structured + unstructured data together in natural language, or share findings with other agents across sessions. The skill handles first-time setup: provisions a free Toolbelt account if none exists, configures the MCP connection in the agent's client, and hands off to Toolbelt's MCP tools for the actual work. NOT for one-off lookups that don't benefi

tradercjz Bundle

The ONE skill for anything DolphinDB — covers BOTH running queries against the user's live DolphinDB server AND offline reference / syntax lookup. Use this whenever the user mentions DolphinDB, ddb, .dos, DFS, or anything database-related for DolphinDB. Runtime side: the connection info (host/port/user/password) embedded below was written by the `dolphindb-agent-skills` installer and is the user's REAL server — use it verbatim, do NOT fall back to localhost:8848 or any other default. Runtime capabilities: one-shot queries via Python API (`import dolphindb`), executing .dos files, uploading pandas DataFrames, parameterized queries, listing DFS databases/tables (`getClusterDFSDatabases`, `getTables(database(…))`), checking table disk usage (`getTableDiskUsage`), bulk-inserting into DFS tables (`tableInsert`), robust long-lived connections (`keepAliveTime`, `reconnect`), error-safe execution. Reference side: DolphinDB SQL dialect (context by / pivot by / asof join / window join), DFS partitioned tables on TSDB /

trkbt10 Bundle

Inspect, build, and verify Office documents (PPTX, DOCX, XLSX) using the aurochs CLI. Use this skill when: (1) Inspecting existing Office files, (2) Building PPTX/DOCX/XLSX from JSON spec, (3) Previewing slide/document/sheet content in terminal, (4) Extracting text or data, (5) Verifying build results, (6) User asks about ".pptx", ".docx", ".xlsx" inspection or generation.

tantaman Skill

Analyze files of tabular data (CSV, TSV, JSON exports, bank/credit-card statements, logs, metrics exports) using @source-and-sum/core, so every step is named and recorded and every number in the answer traces back to the raw rows that produced it. Use whenever the user asks to analyze, summarize, categorize, reconcile, or find patterns in data files — and especially when they want to check the work afterwards.

taxueseek Bundle

WorkBuddy 专属生图 Skill（仅在 WorkBuddy 内运行：出图走 WorkBuddy ImageGen，填槽与验收由 Agent 调用 scripts/*.py 完成；同系列另三个技能为通用技能，不绑平台/模型/Agent）。 基准模型 hunyuan-image——全部硬底线与验收阈值在它上面实测；其它模型原则上可用，换模型须重校阈值。 积分：单张约 5-10，每轮改进=一次全新出图=再扣一次，多轮打磨消耗大须先告知。 元提示词库 + 出图工作流，四种类型——类型 A 竖版概念海报（v5.4， 管图文关系与尺度反差）、类型 B 手绘群像插画（管多角色差异化，可数约束已并入主模板）、 类型 C 写实包装 Mockup（棚拍实物做底 + 编辑风单色专色版面，v1.9 新增）、 类型 D 叙事分镜（漫剧切片，双 LOCK 一致性锚跨帧复现，v1.10 新增）。 v1.5 借鉴 taxue-halftone 流水线：fill_meta.py 机械填槽（LLM 不重抄模板、逐字声明自动推导）、 提示词库分层加载、三档评审卡 + 出图配额 1 张。 v1.6 出图后一次调用 postcheck.py：量测 + 文字带目检裁片 + dewm 反解去水印 + runs.csv 记账， 验收路径从 3-4 次工具往返压到 1 次，并建立模板调优的数据反馈闭环。 v1.7 探索模式（explore.py + CSV 驱动）；去水印默认改 pick_wm 三版选最优（v6/v7/v8 各有擅长， 实测 18 张原 v6 漏清/留噪点 5 张占 28%），所有 dewm 脚本接入 dewm_io 覆盖守卫（不覆盖原图）； 新增 audit_wm 残留审计（无原图也能定位 DIRTY 张）。 v1.8 新增 dewm_v10（v9 + 平底自适应融合）：修「平色底上肉眼可见的水印残影」—— amp 判 CLEAN 但人眼仍有痕（形状失配，R² 掉 0 被当纹理放过），平底图上 v9 RMS 5.98 → v10 1.43，纹理图逐位不动零回归。标准水印默认改 dewm_v10.py。 v1.9 新增类型 C「写实包装 Mockup」：棚拍实物做底 + 编辑风单色专色版面 + 单一隐喻图形 AM 网点 + 巨型堆叠品牌字，中文元模板槽位化 （references/packaging-editorial.md，三轮实测 r

teableio Bundle

Operate Teable bases — tables, fields, views, records, SQL queries, automations, apps, and web scraping. Trigger when user mentions Cuppy, Teable, teable CLI, or Teable-style IDs (bseXXX, tblXXX, fldXXX, recXXX, viwXXX), or wants to manage tables/fields/records, build dashboards/apps, generate charts, create automations, import/export data, trigger AI fill, or scrape websites (LinkedIn, Amazon, YouTube, etc.) — even if they don't explicitly say "Teable" but are clearly working with a Teable base.

tekgrlpdx Bundle

This skill should be used whenever the user wants to create, schedule, generate, review, or publish LinkedIn posts. Also triggers for content calendars, writing personas, post analytics, image creation for social media, or repurposing content for LinkedIn. Activate on any mention of LinkedIn posting, social media content, or the specific sub-commands: setup, persona, research, calendar, generate, create-image, repurpose, review, post, analytics.

voltagent Bundle

Manage EveryFeed social channels, posts, media, AI generation, scheduling, analytics, and connection workflows through EveryFeed MCP or CLI. Use when a user asks to inspect channels, create or adapt social content, generate media, validate drafts, publish or schedule posts, manage existing posts, connect providers, or review publishing performance in EveryFeed.

wanghel2020 Bundle

SSH远程连接Linux服务器进行全量巡检的技能。支持单机和批量巡检，覆盖系统基础信息、CPU负载、内存&Swap、磁盘空间、网络状态、进程&服务、日志、用户与安全、硬件状态、数据库/中间件、备份&业务、资源阈值告警、Java 宕机分析、MySQL深度诊断（23项）、数据库健康诊断、数据库安全审计、数据库锁分析、数据库备份调度、SQL审核执行，全面支持 MySQL/PostgreSQL/Oracle 三大数据库。 ⚠️ 安全要求：SSH密钥认证登录，禁止密码登录；仅执行只读命令，禁止修改服务器配置；数据库仅允许SELECT查询，禁止INSERT/UPDATE/DELETE/DROP/ALTER等任何写入操作。 🚀 性能优化（2026-06-04）：模块级多线程并发执行，默认5线程并发巡检，单机全量巡检从20+分钟压至1-2分钟；阻塞模块自动跳过不卡死。 新增数据库模块（2026-05-30）：db_health（健康诊断）、db_security（安全审计）、db_locks（锁分析）、db_backup（备份调度）、db_sql（SQL审核执行），均支持 MySQL/PostgreSQL/Oracle 三库。 使用场景包括但不限于： - "帮我巡检XX服务器" - "检查192.168.26.66的系统状态" - "批量巡检所有服务器" - "Linux服务器巡检报告" - "服务器负载过高排查" - "运维巡检" - "一键巡检所有指标"

tomevault-io Bundle

Database (PostgreSQL) SQL best practices for clean, performant, and maintainable queries. Use when writing or reviewing SQL, schema changes, or database-related guidance. Use when this capability is needed.

tomevault-io Bundle

Use this skill for spreadsheet creation, editing, analysis, formatting, formula modeling, charting, or workbook review. Triggers include requests to create or modify an .xlsx file, build a model or tracker, format a workbook, add formulas or charts, or prepare a shareable spreadsheet deliverable.

tomevault-io Bundle

ALWAYS USE THIS SKILL when user mentions ANY database-related keywords including "db", "database", "SQL", "query", "PostgreSQL", "Postgres", "psql", "MySQL", "SQLite", "Redis", "orders", "users", "tables", "records", "data", "check data", "get data", "fetch data", "select", "insert", "update", "delete", "from database", "in database", "query table", "check records", "look up", "retrieve". This skill provides safe database access with mandatory schema exploration before queries. Supports MySQL, PostgreSQL, SQLite, and Redis via CLI. Use when this capability is needed.

tomevault-io Bundle

Simple Pomodoro timer for focused work sessions with session tracking and productivity analytics. Use when users request focus timers, ask about productivity patterns, or want to track work sessions over time. Demonstrates the System Skill Pattern (CLI + SKILL.md + Database). Use when this capability is needed.

tomevault-io Bundle

Use when reviewing code for security vulnerabilities (SQL injection, XSS, hardcoded secrets, CSRF), performance issues (N+1 queries, memory leaks, blocking async), or code quality concerns (complexity, error handling, type safety).

tomevault-io Bundle

SQL database queries, joins, aggregations, subqueries, and optimization. Use for .sql files and database operations. Use when this capability is needed.

tomevault-io Bundle

Use this skill when designing Excel or Google Sheets workbooks with formulas, named ranges, pivot tables, charts, and data validation, or when creating financial models, trackers, and dashboards in spreadsheet format. Not for database design or SQL queries. Not for generating CSV files without workbook structure.