Data & Analytics

shuotao Bundle

Create or review auditable Revit quantity-takeoff Excel reports for partition walls, baseboards, interior wall finishes, room schedules, and scaffolding. Use when the user asks for 數量計算、算量、輕隔間 Excel、踢腳 Excel、內牆粉刷 Excel、空間表更新 Excel、施工架數量、room perimeter、opening deductions、net height, or wants an existing pyRevit takeoff method reused through RevitMCP.

shuotao Skill

治理 Revit 房間粉刷明細表與材料代碼。當使用者提到粉刷明細表、F/B/W/C 材料編號、跳號、重排、材料表對照 CSV、AE-材料版、room finish schedule、finish code remap、material board family sync、粉刷比對 CSV 時使用。

manhvann Bundle

Design schemas, write queries for MongoDB and PostgreSQL. Use for database design, SQL/NoSQL queries, aggregation pipelines, indexes, migrations, replication, performance optimization, psql CLI.

ganyangyu Bundle

根据客户信息、样品信息、检测时间、测试说明、现场图片及 CSV/TXT 测试数据，生成严格复现“生成报告示范.pdf”可见版式的正式中文检测报告 DOCX。只要用户提到按检测报告示范/PDF/模板生成报告、要求首页陕西电子/长岭电气标识、目录点线与页码、字体字号颜色一致，或提供 RCS、远场扫描、反射损耗、复介电常数、屏蔽效能数据要求生成 Word 报告，就应使用本 Skill。支持六类测试数据部分缺省；遇到缺失、歧义或不一致时必须询问，不得补造数据。

zzh730 Bundle

Query and analyze live US equity/index options data from cvserver. Use when the user asks to fetch option chains, screen contracts, run read-only options SQL, inspect available fields, export options data, or compute gamma levels, ATM IV term structure, vanna exposure, or charm exposure for tickers such as SPY, QQQ, NVDA, TSLA, AAPL, I:SPX, I:NDX, I:RUT, or I:VIX.

zzh730 Bundle

Query ConvexValue (cvforge) market data — live US option snapshots, cross-contract screens, read-only SQL, Research-plan option history, and 157 FMP fundamentals endpoints. Use when the user asks for option chains, IV, Greeks, fair market value, open interest, unusual volume, gamma or ATM IV, option contract bars, stock/ETF/index quotes, price charts, financial statements, ratios, analyst estimates, earnings dates, company profiles, SEC filings, 13F, insider or congressional trades, transcripts, news, treasury rates, economic data, ETF holdings, technical indicators, or DCF.

finografic Bundle

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

telecomsxchangeapi Bundle

Convert any carrier or vendor voice rate deck (price list, rate sheet, A-Z file or rate amendment in xlsx, xls or csv, from any wholesale carrier) into a TelecomsXchange (TCXC) rate upload CSV that can be uploaded directly, and check or repair existing TCXC upload files. Use this whenever someone mentions TCXC or TelecomsXchange rates or routes, the TCXC format, columns like Price 1, Price N, Interval 1, Interval N, Forbidden or Discontinued, or wants a carrier price list turned into an upload file, even if they only say "convert this rate sheet", "prepare this deck for upload" or "check my rates file before I upload it".

suuus Skill

Keep code GDPR- and EU AI Act-compliant by default, and — when the compliance-spine engine is present — enforce it rather than trust judgment. Use when writing, reviewing, or refactoring anything that touches personal data (logging, storage, APIs, auth, transfers, analytics, error handling) or adds an AI/ML feature. Triggers: 'GDPR', 'personal data', 'PII', 'privacy', 'retention', 'consent', 'lawful basis', 'DSAR', 'EU AI Act', 'high-risk AI', 'data protection', 'is this compliant'. Pairs with the compliance-spine gates, evidence ledger, and ZAVA evals.

integrityauthority Bundle

Read and modify the Microsoft Office document the user currently has OPEN on their Windows machine — Word, Excel, or PowerPoint — via COM automation. Use when the user refers to "this document", "the open file", "the sheet I'm looking at", "my selection", or asks for changes to be made in place rather than as a new file. Do NOT use for generating a document from scratch (write a .docx/.xlsx/.pptx file instead), and do NOT use on non-Windows machines.

santoshhundekar-qa Bundle

Generate sample/test datasets (valid, invalid, and boundary values) for a field, entity, or API payload, in CSV, JSON, or SQL insert format. Always use this skill when asked to generate test data, create fixtures, produce sample records, or build seed data for testing — even when phrased casually (e.g. "give me some sample users for this form", "I need dummy orders to test with", "generate 50 rows for the customers table"). Never use real customer/PII data — always synthetic.

moli-lihuashi Bundle

在本地目录中按文件名、扩展名、内容关键词检索文件。Use when 用户提到"找文件"、"搜索文档"、"查找 Excel"、"locate file"、"哪个文件里有"、文件名/路径检索。不要用于网络搜索或打开文件内容分析。

moli-lihuashi Bundle

对 CSV/Excel 表格做描述性统计与分组汇总。Use when 用户提到"统计表格"、"算平均值"、"数据汇总"、"分析 Excel/CSV"、"summarize data"、"按某列分组"。不要用于生成长篇报告正文或写邮件。

nuanyuqingfeng Bundle

文明6 mod 玩法侧总入口：Lua（UI + GamePlay）、ForgeUI XML 布局、.civ6proj / .modinfo 注册、数据库 XML/SQL、事件系统与全量 API 参考。内含决策树、任务工作流、XML 模板、验证清单，以及离线数据库目录（934 ModifierTypes / 761 EffectTypes / 327 RequirementTypes；1051 条 Requirements / 982 条 RequirementSets）+ SQLite 查询工具。专项章节：总督编写、城邦编写、平衡补丁（差分覆盖）、议程与领袖 AI、素材转换管线。发布：Steam 创意工坊上传/更新（release.md）。工具：7 个零依赖校验器（SQL 可执行性 / 引用完整性 / Types.Kind / SQL 语义反模式 / 内容清单闭合 / .lua 加载路径 / pantry 卫生）+ 双目录一致性比对。触发词：文明6、Civ6、modding、Lua、ForgeUI、UI 面板、按钮、弹窗、modinfo、civ6proj、数据库、Modifier、Requirement、PROPERTY、事件、GameEvents、LuaEvents、总督、governor、城邦、city-state、平衡补丁、balance patch、议程、agenda、创意工坊、workshop、上传、发布、校验、rgn_validate。

eric-hunt Bundle

Reference for designing Echo 525 liquid handler methods and Echo Cherry Pick pick lists — instrument transfer limits, source-plate/calibration selection by fluid composition, source-well selector notation, and the pick list CSV header. Use when the user asks to design a method for an Echo 525, create or format a pick list for the Echo, choose a source plate type or calibration code, or troubleshoot Echo transfer volumes, dead volume, or well notation.

olbartek Skill

Analyze a codebase and generate quantitative reports (LOC stats, dependency graph, module coupling, largest files, service/interface inventory, third-party dependencies). Outputs markdown reports to docs/codebase-analytics/. Use when the user asks to analyze, profile, or get an overview of a codebase.

hanns111 Bundle

Control previo administrativo y financiero de expedientes de pago de Ordenes de Servicio (OS) y Ordenes de Compra (OC) del MINEDU. Aplica las Pautas para la Remision de Expedientes para el Tramite de Devengado y Pago, la Ley 32069 y la Ley 27444. Usar cuando se mencione orden de servicio, orden de compra, OS, OC, carta contrato, expediente de pago, recibo por honorarios, RHE, factura, devengado, proveido, conformidad, entregable, armada, suspension de cuarta categoria, detraccion, contratacion menor a 8 UIT o locacion de servicios. Produce el veredicto, las observaciones con su base normativa y la matriz de coherencia. El formato del informe Excel lo define informe-control-previo-os-oc, Protocolo v1.1 de siete hojas.

hanns111 Bundle

Control previo de expedientes de rendicion de viaticos MINEDU. Entregable unico: un Excel de tres hojas con cabecera fija, veredicto en rojo o verde, gasto diario por dia, checklist de documentos y firmas, y comprobantes. Aplica la Directiva DI-003-01-MINEDU V03 (RSG 023-2026-MINEDU) y los Oficios Multiples 00010 y 00016-2026-MINEDU/SG-OGA. Usar cuando el usuario mencione expediente de viaticos, rendicion de viaticos, planilla de viaticos, control previo, Anexo 3, declaracion jurada, comprobantes de comision de servicios, o adjunte PDFs de rendicion SIGA-VIATICOS. Es dominio y salida a la vez: no usa el formato de dos hojas de informe-control-previo-minedu ni el Protocolo v1.1 de siete hojas de informe-control-previo-os-oc, que son de otros tipos de expediente.

hanns111 Bundle

Formato de salida ÚNICO del informe Excel de control previo de expedientes de pago de Órdenes de Servicio y Órdenes de Compra del MINEDU: siete hojas del Protocolo v1.1 — dictamen, proveído, expediente, firmas, validaciones del TDR, tabla tributaria y protocolo versionado — con enlaces a los PDF y páginas en columna aparte. La norma y el criterio de OS y OC los aporta la skill control-previo-ordenes; esta skill define cómo se presenta el resultado. NO se usa en viáticos, encargos ni caja chica.

hanns111 Skill

Genera el informe Excel de control previo del MINEDU en formato de dos hojas, Dictamen y Expediente, para encargos a personal, caja chica, convenios, servicios básicos, tasas, sentencias judiciales y demás expedientes de pago. NO aplica a Órdenes de Servicio ni Órdenes de Compra, que usan el Protocolo v1.1 de siete hojas de informe-control-previo-os-oc, ni a viáticos, que tienen su propio formato oficial de tres hojas.

pineapplesour Bundle

Summarize a CSV file with pandas and print per-column statistics.

brandbai7 Bundle

Download public Tmall or Taobao item-page data through a visible signed-in Chrome session. Use for 商品资料包、主图与详情图、可见视频、规格参数、SKU 与价格销量库存快照，以及独立下载全部评价或问大家问题和回答，生成普通版 Excel、ZIP 和可回溯原始数据。商品资料、评价和问大家是三项独立能力；默认只做下载与质量说明，不自动生成商品价值、卖点、用户语义或商业结论。

brandbai7 Bundle

Collect public Weibo accounts, individual posts with current-page creator snapshots, profile posts, keyword or hashtag search results, supertopic posts, hot-search ranking snapshots, source-visible comments, comment replies, repost propagation records, images, video and interaction snapshots through a visible signed-in Chrome session. Use for 微博明星主页采集、品牌或明星账号全部当前可见置顶加最近 N 条微博、单条微博下载与当前页达人快照、明星代言与品牌事件关键词搜索、普通话题与明星超话留证、热搜主榜或文娱榜快照、评论与转发扩散采集、DataTool 类普通版 Excel 与 ZIP 交付，以及为后续明星营销、舆情传播或账号分析保留可回溯原始数据。默认只完成下载、结构化与完整性说明，不自动进入账号主页、不下载头像、不生成明星口碑、粉丝质量、代言效果、情感标签或商业归因。

brandbai7 Bundle

Download public TikTok videos, photo posts, published captions, media, single-work creator snapshots, creator-profile selections, keyword-search snapshots, BrandBAI plugin work-list selections and visible first-level comments through a visible signed-in Chrome session. Use for TikTok 单作品完整资料包与当前页达人快照、账号主页全部当前可见置顶加最近 N 条非置顶作品、搜索结果前 N 条、插件作品清单续跑、视频或图集素材、封面、可用独立原声、发布文案、基础互动数据、一级评论、Excel 与 ZIP，以及品牌海外市场扫描、达人候选池、竞品内容、官宣接收和 TikTok Shop 联盟内容的原始证据准备；默认只做采集、双语整理和质量说明，不自动进入达人主页、不下载头像、不做语音转写、语义分析、经营指标推算或商业结论。

brandbai7 Bundle

Download public Xiaohongshu notes through a visible signed-in Chrome session. Use for 单篇笔记完整资料包、当前笔记页达人快照与可见评论、账号主页当前可见置顶加最近 N 条列表卡片、关键词搜索前 N 条列表卡片、封面与基础互动数据、普通版 Excel、ZIP，以及为后续账号研究和内容分析保留稳定笔记 ID 与完整性状态。账号主页和搜索批量模式只采当前列表页可见数据，不逐篇进入详情；默认只做下载与质量核验，不自动进入作者主页、不下载头像、不生成语义标签或商业结论。

wjjjjjjjjjjj Bundle

将用户明确指定的本地文件或目录批量规范化为 Markdown，并核验输出，适合知识库入库、检索和后续分析。仅在用户要转换成 Markdown、生成 md 文件或批量归一化时使用；如果只是阅读、总结、编辑或高保真还原 PDF、Word、PPT、Excel，使用相应文档 Skill，不触发本 Skill。

wjjjjjjjjjjj Bundle

为档案信息化项目建立功能级报价口径、预算分配和金额对账。用于用户明确要求功能报价、分项报价、预算分配或审查档案项目报价清单；不因普通功能清单、方案预算文字或 Excel 美化自动触发。负责金额契约、叶子功能识别、权重分配、尾差回补和范围边界；Excel 导入、公式、样式、渲染与导出由当前 Spreadsheets Skill 主控。

ruslankhis Bundle

Design, implement, adapt or audit memory and retrieval in Python Google ADK agents. Select and combine conversation sessions/state, governed RAG, Agent Platform Memory Bank and scoped BigQuery history; enforce identity, consent, retention, replay and erasure boundaries. Use for agent memory, knowledge retrieval or cross-session continuity work. Do not activate for general database administration, arbitrary SQL generation, deployment alone, prompt-only editing or non-agent caching.

ehteshambuildagents Skill

Post-mortem on what the user has already published - which posts worked, why, and what to stop doing. Use when the user pastes their LinkedIn analytics or past posts and asks "what's working", "why did this flop", "read my analytics", "audit my content", or wants to know what to double down on.

mypropper Bundle

Produce a finished document from a reusable template and a set of values — fill a contract, offer letter, invoice, statement of work or report, check the merged wording before it is committed, and turn a list of rows into one document each. Use when someone wants a document built from a template plus data, asks to fill in, populate or merge a template, has a spreadsheet or list of values that should become documents, or wants the same paperwork produced for many customers.

ivelten Skill

Model PostgreSQL databases from Haskell types using Rel8. Covers the type-mapping decision tree (composite types vs jsonb vs enums vs primitives), indexed JSONB queries, composite-type indexing caveats, Rel8 table definitions with HKD, and pure-SQL migrations via hasql-migrations. Use when designing the database layer, choosing PostgreSQL column types for Haskell ADTs, writing Rel8 queries, or setting up migrations.

ftrout Bundle

Investigate an incident from logs: pick the Windows Security/System/PowerShell/Sysmon event IDs, Linux auth/audit/systemd/cron/shell-history artifacts, and web server or proxy logs that answer the question, normalize time zones, merge everything into one UTC super-timeline, pivot user to host to process to network, and preserve evidence properly. Use it whenever someone pastes or points at exported logs (CSV, JSON, EVTX exports, auth.log, access.log), asks "what happened on this host", "when did they get in", "what did this account do", "build a timeline", "which event IDs should I pull", or needs a forensic narrative for an incident report, even if they never say forensics.

ftrout Bundle

Plan, run, and write up hypothesis-driven threat hunts (PEAK / TaHiTI style): turn a threat report, an ATT&CK technique, a coverage gap, an anomaly, or "something feels off" into a testable hypothesis with data sources, queries, expected benign volume, an analysis technique (stacking, prevalence, baselining, clustering, sequencing, outliers), success criteria, and hand-offs. Use it whenever someone says "hunt for", "go look for", "is anyone doing X in our environment", "what should we hunt this week", "build a hunt from this report", "stack these values", "what is rare here", "baseline this data source", or hands over a CSV/JSONL export and asks what stands out. Also use it when a report or a purple-team result implies behaviour that no alert covers, even if nobody says the word hunt.

ftrout Bundle

Turn an investigative question, a hunt hypothesis, or an indicator list into a correct, efficient query for the team's SIEM: Microsoft Sentinel / Defender XDR (KQL), Splunk (SPL with CIM), Elastic (KQL, EQL, ES|QL over ECS), Google SecOps / Chronicle (UDM search, YARA-L), or Athena / BigQuery SQL over CloudTrail, VPC flow and audit logs. Use it whenever someone asks to "write a query", "search the SIEM for", "check if any host talked to", "find logons from", "translate this SPL to KQL", "why does my query return nothing / time out", or hands over an IOC list (typically the CSV from `ioc-extraction`) that needs to become a retro-hunt. Also use it when another skill needs a query run: backtests for `detection-engineering`, hunt queries for `threat-hunting`, scoping for `incident-triage`.

hiyabh Bundle

Extract structured data from Hebrew handwritten/scanned PDF reports (especially Ministry of Education grant reports — דוחות ביצוע מענקי שכר לימוד), payslips, BDO accountant approvals, and merge into RTL Excel summaries. Triggers — "דוחות ביצוע", "מענק שכר לימוד", "תלוש שכר עברי", "סריקה בכתב יד", "אקסל מענקים", "OCR עברי", "geulah", "גאולה". Use when user has a folder of mixed Hebrew PDFs (signed/unsigned reports, scanned tables with handwritten teacher rows, payslip PDFs with digital text) and needs a single tabular summary.

mannyrodriguez-wk Bundle

Anchor/router skill for live-demoing the Workiva internal MCP (Model Context Protocol) connector to a prospect on a real call. Enforces a hard pre-flight safety gate (memory state, tenant/workspace confirmation, GRC entitlement probing, live wrong-data correction protocol) before any MCP tool touches live data, then routes the SC to the correct domain sub-skill (/grc, /reporting, /analytics, /sustainability) based on what the prospect wants to see. Trigger phrases: '/demo', 'let's demo the MCP', 'I have a live Workiva MCP demo', 'demo the connector for [prospect]', 'walk the prospect through GRC/reporting/analytics/sustainability live', 'start the live MCP session'. Distinct from presales/demo-framework-adapter, which plans the demo narrative/script offline before the call — this skill is about safely executing a live, MCP-powered demo during the call itself.