Data & Analytics

hkuds Skill

Read, create, or edit Microsoft Word .docx files — extract/summarize text and tables, generate reports/letters/memos with headings, tables, images, TOC and page numbers, do find-and-replace, or apply tracked changes (redlines) and comments. Use whenever the user has a .docx or wants a Word deliverable. Not for PDF, .xlsx, .pptx, or Google Docs.

hkuds Skill

Read, create, or edit Excel spreadsheets (.xlsx/.xlsm) — sheet data, formulas, styles, charts, multi-sheet workbooks — and bulk .csv/.tsv tables; use whenever a spreadsheet is the input or the deliverable (extract/analyze data, add columns/formulas/formatting/charts, clean messy tables, build from scratch), but not for Google Sheets API or Word/PDF/script outputs.

sizzlecar Skill

Query MySQL databases, summarize results, and export to CSV/Excel. Use when the user asks to check data, run SQL queries, export tables, or generate data reports from a database.

smvlx Bundle

Use when working with Yandex Metrika (Yandex Metrica) analytics - retrieving traffic stats, managing counters and goals via API, setting up tracking code in web projects, building reports, analyzing conversions, or debugging counter issues. Triggers on mentions of Yandex Metrika, Metrica, web analytics counters, pageviews metrics, site traffic reports, conversion goals, or counter IDs. Always use this skill when the user mentions Yandex Metrika or wants analytics data from their site, even if they don't say "API" explicitly.

jsonbored Bundle

Add PostHog MCP analytics to a TypeScript, JavaScript, or Python MCP server. Instruments the server so every tool call, agent intent, and failure is captured as a $mcp_* event — the @posthog/mcp Node SDK for TS/JS, or posthog.mcp (shipped inside the posthog package) for Python. Detects the server style (official MCP SDK Server/McpServer/FastMCP, mcp-handler, @rekog/mcp-nest, jlowin fastmcp, or a custom HTTP/edge dispatcher) and wires in the matching instrumentation, credentials, and graceful shutdown.

marchenko-sales Bundle

Segment prospecting for B2B sales: finds candidate companies in a given niche or hypothesis (e.g. 'medical tourism', 'online English schools', 'car rental services'), verifies each against two strict criteria (segment fit + your ICP signal) and saves a prioritized xlsx (priority signal × company scale). Use when the input is a segment description, NOT a specific company. Output feeds company-context. Skill body is in Russian. Triggers (EN): 'find 30 companies in niche X', 'list candidates in segment Y'. Triggers (RU): «накидай компаний в сфере X», «найди 30 компаний ниши Y», «список площадок в сегменте Z».

patterai Skill

Inspect Patter call data — mount the live dashboard, read CallMetrics (duration, cost, latency, transcript), export call history to CSV/JSON, and track per-call provider costs. Use when the user wants to debug a call, see which calls cost the most, audit transcripts, monitor a live agent, find a recording URL, check latency p99, export call history for reporting, or watch the dashboard during a demo. Covers Patter 0.7.0's in-memory MetricsStore + 500-call ring buffer, the FastAPI/Express dashboard mount, the REST API and SSE stream — in both Python and TypeScript.

themattberman Bundle

Ingests the operator's raw market voice (a CSV or a folder of .md/.txt files), normalizes it to the canonical input contract, indexes every source, and computes corpus sufficiency. Captures speaker_type and source_type at import so they are never guessed later. Triggers on: source intake, ingest my reviews, normalize sources, index my market voice, import my CSV of comments, build the source index, check if my corpus is thin.

timeplus-io Bundle

Write and execute Timeplus streaming SQL for real-time analytics. Use this skill when the user wants to create streams, run streaming queries, build materialized views, ingest data, send data to sinks, write UDFs, or simulate data with random streams. Executes SQL via the ClickHouse-compatible HTTP interface on port 8123 using environment variables TIMEPLUS_HOST, TIMEPLUS_USER, and TIMEPLUS_PASSWORD. Covers full Timeplus SQL syntax including window functions, JOINs, CTEs, UDFs, data types, aggregations, and all DDL/DML statements.

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, building dashboard JSON, or debugging install failures.

no-today Skill

Use when an AI agent needs to read (or, with explicit intent, write) a database — running SQL, listing databases/tables/columns, diagnosing locks, or checking connectivity — across configured targets (mysql / postgres / kingbase / redis / sqlite / mongo; plus dataease, a last-resort read-only HTTP bypass). Covers the read/write guard, the JSON envelope, the namespace model, and target inference.

open-edge-platform Skill

Benchmarks a trained Physical AI Studio policy in a simulation gym and reports success metrics. Use when running physicalai benchmark, editing configs under library/configs/benchmark, adding or changing a Benchmark class in physicalai.benchmark, tuning rollout/episode/env settings, recording rollout videos, or interpreting results.json / results.csv.

openbkn-ai Skill

操作 BKN（Business Knowledge Network）平台的统一 CLI `openbkn` —— 知识网络 构建/查询（Schema：对象/关系/行动类型、指标、概念组；实例与语义搜索； push/pull/validate；从 Vega Catalog 或 CSV 建网）、资源、Vega Catalog 与 索引构建任务、Context Loader（MCP 检索）、模型工厂（大模型/小模型 CRUD、OpenAI 兼容对话/embedding/ rerank）、Skill 注册（zip 注册/下载/安装 + 生命周期）、Toolbox/Tool（上传、 导入导出、调用）、BKN Trace（第三方 Agent 受管 Conversation / Interaction / Operation、拉取 spans、用符号 规则 + LLM rubric 判定诊断一条 trace、scan、eval-set 构建、schema 校验）、 以及运营面（`openbkn admin`：组织/用户/角色 CRUD、审计、模型管理）与认证 （token + OAuth 密码/浏览器）。 当用户提到：知识网络 / 知识图谱 / 对象类 / 关系 / 行动 / 指标 metric / 语义搜索 / 建索引 / create-from-catalog / 大模型 / 小模型 / embedding / rerank / Skill / 技能包 / toolbox / 工具箱 / tool / 沙箱函数 / function / trace / 证据链 / diagnose / eval-set / Vega / Catalog / 数据源 / 组织 / 用户 / 角色 / 审计 audit / AppKey / api-key / bak_ 凭据 / 签发 key / 撤销 key 等意图时使用。

nullpond Bundle

name: xlsx

nullpond Bundle

MiniMax professional Excel processing capability. REQUIRED loading for ANY spreadsheet-related operations. Compatible with XLSX/XLSM/CSV file types, featuring formula recalculation (recalc.py via LibreOffice), comprehensive verification toolchain (recheck, reference-check, validate, chart-verify) plus pivot table generation (pivot). Technology foundation: Python + openpyxl/pandas + MiniMaxXlsx CLI (C#/.NET) + LibreOffice (headless).

konecty Bundle

Helps developer-agents WRITE CODE to integrate with the Konecty platform — preferring the official SDKs (Python konecty_sdk_python, Node/TS @konecty/sdk), with the full REST API documented for other languages. Covers authenticating server-side code (service-account token), find/query, create, update, delete, cross-module and SQL queries, file upload/download, and writing data hooks (scriptBeforeValidation, validationScript, scriptAfterSave). Use when: escrever código, criar integração, integrar meu app/serviço com Konecty, usar o SDK Python/Node, exemplo de código, gerar um cliente, autenticar código, escrever um hook; write code, build an integration, use the Konecty SDK, code example, generate a client, authenticate server-side, call the Konecty API, write a hook. Do NOT use to run one-off data ops now (find/create/update/delete) — use konecty-data; or to manage schema/metadata — use konecty-meta.

jjyaoao Bundle

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When GLM needs to work 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

janbrus Bundle

Svensk offentlig statistik från SCB via PxWebApi v2. Använd ALLTID när någon frågar om svenska siffror, statistik, befolkning, KPI, inflation, arbetslöshet, löner, priser, BNP, ekonomi, handel, export, import, utbildning, hälsa, bostäder, kommun- eller länsdata, eller nämner SCB, Statistiska centralbyrån eller Statistikdatabasen. Trigger på "hitta siffror på", "hur många bor i", "KPI senaste året", "befolkningsökning", "prisindex", "bostadspriser" och liknande. Also trigger on "Swedish statistics", "population of Sweden", "Statistics Sweden", "SCB data", "Sweden GDP", "inflation in Sweden", "housing prices Sweden" or similar. Använd denna framför websökning när svaret finns i svensk offentlig statistik. Täcker kodlistor, sparade frågor och outputformat (json-stat2, csv, xlsx).

janbrus Bundle

Norsk offisiell statistikk fra SSB via PxWebApi v2. Bruk ALLTID når noen spør om norske tall, statistikk, befolkning, KPI, inflasjon, arbeidsledighet, lønn, priser, BNP, økonomi, handel, eksport, import, utdanning, helse, bolig, kostra, kommune- eller fylkesdata, eller nevner SSB, Statistisk sentralbyrå eller Statistikkbanken. Trigger på "finn tall på", "hvor mange bor i", "KPI siste år", "befolkningsvekst", "prisindeks", "boligpriser" og lignende. Also trigger on "Norwegian statistics", "population of Norway", "Statistics Norway", "SSB data", "Norway GDP", "inflation in Norway", "housing prices Norway" or similar. Bruk denne fremfor websøk når svaret finnes i norsk offentlig statistikk. Dekker kodelister, lagrede spørringer og outputformater (json-stat2, csv, xlsx).

yaniv-golan Bundle

Deterministic library-first regression — fit a CSV against the calculator-primitive witness library (unary, affine `a·w(x)+b` with constant snapping, depth-2 composite `w(v(x))`, binary `w(x,y)`) and emit a machine-checkable JSON verdict ranked by max |residual| and R². Use when you need a reproducible, audit-able answer to "which elementary law generated this data?" — the JSON output is downstream-consumable (no LLM in the loop), exit codes encode the verdict, complex-plane evaluation via cmath catches branch-cut hazards. Snaps to π, e, 1/ln(10), Catalan G, ζ(3), Khinchin K, log₂(e), e^π, γ, etc. Optional `--noise-sigma σ` for measured data; reports SE(a)/SE(b).

cookjohn Bundle

Export WoS records to Zotero, RIS, BibTeX, or Excel.

ysm-dev Skill

Query and analyze data using the DuckDB CLI. Use when the user needs to run SQL queries, analyze CSV/Parquet/JSON files, create or query databases, export data, or perform any ad-hoc data analysis from the command line. Triggers include requests to "query a file", "analyze data", "run SQL", "read a CSV/Parquet/JSON", "create a database", "export to CSV/Parquet", or any data analysis task that benefits from SQL.

ysm-dev Bundle

Use when the user wants to scrape, crawl, or extract data from a website or URL. Triggers on: 'scrape this site', 'get data from this URL', 'crawl this page', 'extract data from the web', 'pull data from this link', 'download data from this website', 'I need data from [URL]', or any request involving collecting structured data from a web page. Also triggers when the user provides a URL and asks for its data in CSV, JSON, or other tabular formats. Always load the agent-browser skill alongside this one.

ysm-dev Bundle

Analyze and process large CSV files (1M+ rows) using DuckDB and Polars. Use when the user asks to analyze, query, filter, aggregate, join, or transform CSV data. Triggers on requests like "analyze this CSV", "query CSV file", "filter large dataset", "aggregate CSV data", "join CSV files", "CSV statistics", or any data analysis task involving CSV/TSV/Parquet files.

zxc7563598 Bundle

账单分析工具。通过 /analyze-bill 手动调用，解析微信/支付宝账单文件（CSV/Excel），支持按时间、商户、分类、支付方式等多维度交互式分析和消费报告生成。仅在用户明确输入 /analyze-bill 时触发。

lionad-morotar Skill

将数据可视化报告（如 Visual Capitalist、Our World in Data、行业研究报告）归档到 analytics.md。当用户分享数据报告、调查报告、行业研究链接时使用，自动提取关键数据点并按主题整理。

liuning0820 Bundle

面向本地知识库目录的检索和问答助手。核心流程：(1)分层索引导航 (2)遇到PDF/Excel时必须先读取references学习处理方法 (3)处理文件后再检索。按文件类型组合使用 grep、Read、pdfplumber、pandas 进行渐进式检索，避免整文件加载。用户问题涉及"从知识库目录回答问题/检索信息/查资料"时使用。

markbain Skill

Elicit completed project data and append a new row to context/portfolio/project-database.csv. Use when a project is finished or to backfill a missing project. Ask one section at a time, then write the CSV row and offer to run cv_updater.py.

pgplex Skill

Consult PostgreSQL's parser and grammar (gram.y) to understand SQL syntax, DDL statement structure, and parsing rules when implementing pgschema features. Use this skill when generating DDL in internal/diff/*.go, validating SQL syntax, understanding keyword precedence, or learning how PostgreSQL handles specific constructs like triggers, indexes, generated columns, or constraint triggers.

kesslernity Bundle

PURPOSE

justrach Skill

Scaffold Zig-native database routes using pg.zig + TurboPG. Use when adding database-backed CRUD endpoints, custom SQL queries (pgvector, JSONB, full-text search, JOINs, CTEs), or standalone TurboPG usage.

kasimmj Skill

Generate safe, reversible SQL migrations with proper up/down statements, transactional wrappers, and rollback safety checks. Supports Postgres, MySQL, SQLite.

0xelitesystem Bundle

Diagnose and clean messy CSV, TSV, or spreadsheet files. Use whenever the user uploads a CSV or TSV that has data quality issues, asks to "clean", "normalize", "fix", or "deduplicate" tabular data, or hands over a file with encoding problems, broken headers, type inconsistencies, duplicate rows, or missing values. Triggers on "clean this CSV", "fix this data", "this spreadsheet is messy", "deduplicate these rows", or any data-quality request on a tabular file. Always run scripts/diagnose.py before making changes so the cleanup is informed by what is actually broken.

faizee-asad Skill

Create, update, clean, and summarize CSV job application trackers with statuses, next actions, contacts, follow-up dates, and notes.

guerthcastro Skill

Opinionated C# and .NET 10 coding conventions built around Clean Architecture and plain Dapper: one type per file, file-scoped namespaces, primary constructors, camelCase locals and fields with no underscore prefix, POCO entities with hand written SQL, versioned migration scripts, soft deletes, and a single LookUp catalog table. Use this skill whenever writing, reviewing, refactoring, or scaffolding C# code, solution structures, entities, repositories, services, handlers, DTOs, mappers, or validators for a .NET 10 project that follows these conventions. Also use when creating a new project from scratch, migrating an existing one, or adding a new layer to an existing solution. Apply these conventions without exception unless the user explicitly overrides a rule for a specific case.

scalefreecom Bundle

Installs and configures the datavault4dbt package in a dbt project — packages.yml, copying the global vars into dbt_project.yml, hash and naming settings, and per-adapter setup. Use when setting up datavault4dbt, installing the package, changing hash/naming global variables, or adapting configuration for a specific warehouse (Snowflake, BigQuery, Redshift, etc.).