Data & Analytics

hachiwar Bundle

Diagnose and fix UnicodeDecodeError, UnicodeEncodeError, mojibake, and corrupted Chinese text in Codex coding tasks. Use when Python or another tool cannot decode a file or subprocess stream; Chinese text displays as replacement characters or strings such as "中文" or "涓枃"; file, terminal, CSV, JSON, HTTP, Git, or Windows encoding behavior is unclear; or a repository needs a safe migration to UTF-8.

hachiwar Bundle

Diagnose and fix UnicodeDecodeError, UnicodeEncodeError, mojibake, and corrupted Chinese text in Claude Code tasks. Use this skill whenever a file, command, test, CSV, JSON, HTTP response, Git diff, or Windows terminal shows broken Chinese, replacement characters, strings such as "中文" or "涓枃", an unknown codec, or any decode/encode exception. Use it even when the user only says Chinese text is garbled or a file cannot be read.

haiyuan-eng-google Bundle

BigQuery router skill — authentication, global flags, SQL queries, schema inspection, and connections. Entry point for all BigQuery-specific dcx usage.

hansohn Bundle

Generate a complete marketplace listing file (pricing analysis + listing copy for each enabled platform + photo order) for a secondhand item, and optionally create an eBay draft. Use whenever the user wants to sell, list, post, cross-list, or flip a used item on Facebook Marketplace or eBay. Trigger on phrases like "list this for sale", "make a marketplace listing", "sell this item", "post this on FB or eBay", "cross-list this", "create a listing for X", or when the user references a CSV of items to sell. Orchestrates /marketplace:comps (pricing) and /marketplace:photos (photos), iterates enabled platforms from the plugin's platforms/ directory, writes a single .md file with one listing-copy section per enabled platform, and (if /marketplace:ebay-draft is available and the user opts in) creates an eBay draft via the eBay MCP.

jacksonrpp Bundle

Triagem e diagnóstico de performance de nível especialista em Power BI — localizar onde um relatório ou consulta lenta de fato gasta seu tempo (modelo de dados, DAX/motor de fórmula, visuais de relatório, atualização, capacidade, ou uma fonte DirectQuery) e encaminhar a correção, operando o MCP de modelagem do Power BI para capturar traces de servidor e métricas de execução. Use esta skill sempre que o usuário relatar algo LENTO e ainda não estiver claro por quê: um relatório ou página lenta, um timeout de consulta, uma atualização longa, uso alto de capacidade/memória, lentidão de DirectQuery, ou "por que meu Power BI está lento". Ela mede e diagnostica, e então passa adiante: reescrever uma medida é power-bi-dax, mudanças de modelo/armazenamento são power-bi-data-modeling, e layout de página/visual é power-bi-report-design. Para capacidade, gateway e monitoramento de tenant, ela orienta e ajuda a escrever consultas do Log Analytics (KQL).

jezweb Skill

Install the OfficeCLI binary (create/read/edit .docx/.xlsx/.pptx with no Microsoft Office) and register it as a Goose MCP server. Use when the user wants Office-document capabilities, asks to 'install officecli' / 'add Word/Excel/PowerPoint support', or a skill/app needs to generate Office files.

kklimuk Bundle

Read, edit, redline, comment on, and create Microsoft Word .docx files. Use to fill out or edit a Word doc, redline a contract with tracked changes, add/resolve comments, replace text keeping its formatting, restyle headings/fonts, edit tables, or read/extract a .docx as Markdown or text. Also BUILD a new .docx — from Markdown or programmatically (code that outputs a Word report with headings, tables, images). Not for PDF, Google Docs, Excel, PowerPoint, or .doc.

kunpengcompute Bundle

为Spark表达式生成测试SQL用例。读取包含Spark函数信息的CSV文件，为每个函数生成19种数据类型的测试SQL并输出到新CSV。使用场景：用户需要为Spark函数生成测试SQL、处理CSV中的表达式列表、批量生成SQL测试用例、或涉及OmniOperator/gluten-velox表达式兼容性测试。触发关键词包括但不限于：生成测试SQL、表达式测试、SQL测试用例、Spark函数测试、批量生成SQL、数据类型测试、Spark表达式CSV、OmniOperator测试、gluten-velox测试。即使用户没有明确提到"skill"或"脚本"，只要涉及从CSV中的函数列表生成SQL测试，就应使用此skill。

kunpengcompute Bundle

Use for OmniOperator expression development. Trigger when implementing new vectorized expressions, functions, or operators in OmniOperator framework. This includes scalar functions, aggregate functions, window functions, variadic functions, bitwise operations, math functions, string functions (like concat, split, substring), or any SQL function implementation. Also trigger when asked to "implement function", "add expression", "create vectorized function", "实现函数", "添加表达式", "编写函数", when working with Register*.cpp registration files, or when user mentions "OmniOperator" with "function/expression/implementation" or "函数/表达式/实现" and specifies function signature, arguments, return type, NULL handling, or vector encoding support.

leiverkus Bundle

Create, read, edit, convert, repair, inspect, analyze, or format OpenDocument Spreadsheet files (.ods) — including bidirectional conversion to XLSX/XLS via headless LibreOffice. Supports named ranges, data validation (dropdowns and range constraints), embedded charts (bar, line, pie, scatter), conditional formatting, and pivot tables.

oceanbase Bundle

seekdb database documentation lookup. Use when users ask about seekdb features, SQL syntax, vector search, hybrid search, integrations, deployment, or any seekdb-related topics. Automatically locates relevant docs via catalog-based semantic search.

oceanbase Bundle

Use seekdb-cli to interact with seekdb/OceanBase databases via shell commands. Use when: (1) querying databases with SQL, (2) exploring table schemas and structure, (3) profiling table data distributions, (4) inferring table relationships, (5) managing vector collections and semantic search, (6) adding/exporting collection data, (7) managing AI models , (8) checking database connection status, or (9) performing any database operation via command line.

oceanbase Bundle

Import CSV or Excel files into seekdb vector database and manage collections. Supports automatic vectorization of specified columns using embedding functions. When users need to: (1) Read and preview Excel files, (2) Import CSV/Excel data into seekdb, (3) Create vector collections from tabular data, (4) Vectorize specific text columns for semantic search, (5) Batch insert product/document data with embeddings, (6) Delete collections, or (7) Access sample data files (sample_products.csv/xlsx) for testing - IMPORTANT: sample files are located in this skill's example-data/ directory, you MUST read this skill file first to get the correct path.

oceanbase Bundle

Query and export data from seekdb vector database. Supports two search modes: (1) Scalar search - metadata filtering only, (2) Hybrid search - fulltext + semantic search combined. The --query-text parameter is used for BOTH fulltext ($contains) and semantic (query_texts) search simultaneously. Can export results to CSV/Excel.

oneclaw Bundle

Use this skill any time a .xlsx file is involved -- as input, output, or both. This includes: creating spreadsheets, financial models, dashboards, or trackers; reading, parsing, or extracting data from any .xlsx file; editing, modifying, or updating existing workbooks; working with formulas, charts, pivot tables, or templates; importing CSV/TSV data into Excel format. Trigger whenever the user mentions 'spreadsheet', 'workbook', 'Excel', 'financial model', 'tracker', 'dashboard', or references a .xlsx/.csv filename. Drive bulk edits through JSON batch files passed to officecli batch --input; never write Python / Node / Ruby (or other interpreted-language) helper scripts to generate the JSON or wrap CLI calls.

owid Skill

Access Our World In Data from Python with the owid-catalog library: load chart data, catalog tables or individual indicators as pandas DataFrames that carry their own units, descriptions, sources and citations. Use this skill whenever the work happens in Python or a notebook (pandas, a uv script, matplotlib, parquet); whenever you need an indicator's metadata, units or codebook; whenever you need dimensions that published charts flatten away, such as sex, age group or projection variant; or whenever you need to search OWID's full catalog of indicators and tables, including semantic search by meaning, rather than only its published charts. Prefer it over the HTTP-based search-charts and fetch-chart-data skills for any Python-based analysis.

owid Skill

Search Our World In Data's published charts by keyword to find the chart you need, across topics like population, energy and electricity, CO2 and climate, poverty and GDP, health and causes of death, education, democracy, violence and war. Use this whenever someone wants to find, browse, link or embed an OWID chart and does not already have its URL, or asks what OWID publishes on a topic. Returns each chart's title, subtitle and URL, plus which visualisations it supports so you can build a ?tab= link. Not for: fetching the data behind a URL you already have (use fetch-chart-data); Python or pandas work, indicator and column metadata, or searching the full catalog of indicators and tables beyond published charts (use owid-catalog); combining OWID data with your own (use joining-data).

pass-with-high-score Bundle

CSV Translator Workflow

rodydavis Bundle

Guide and examples for using OpenXML Xlsx features in the open_xml package.

sameergdogg Bundle

**Network & Referral Finder**: Searches the user's LinkedIn connections and a referral spreadsheet to find potential contacts at a target company. Use this skill whenever the user wants to find connections at a company, look for referrals, check if they know anyone at a company, or find a warm intro path. Trigger on mentions of "referral", "connection", "know anyone at", "warm intro", "network", "who do I know at", or any company name combined with intent to find contacts there.

the-focus-ai Bundle

This skill should be used when the user asks to "read spreadsheet", "write to sheet", "create spreadsheet", "list spreadsheets", "google sheets", "read cells", "write cells", "append rows", "sheet data", or mentions Google Sheets operations. Provides Google Sheets API integration for reading, writing, and managing spreadsheets.

topunix Bundle

Use when reviewing or writing a database schema change for Bugzilla 5.0+/Harmony - anything touching Bugzilla/Install/DB.pm, Bugzilla/DB/Schema.pm, or code calling bz_add_column/bz_column_info/bz_alter_column/bz_add_index. Covers idempotent upgrade-script patterns, the abstract-schema type system, and the specific DB-specific SQL functions Harmony's own test suite forbids for MySQL/PostgreSQL/SQLite portability. Trigger for "will this migration run safely twice", "is this portable across databases", or schema/DDL patch review.

ludo-technologies Bundle

NumPy and pandas best practices for data science and ML code covering vectorization, DataFrame indexing and mutation under Copy-on-Write, dtypes, schema validation with pandera, reproducible randomness, transformation style, array typing, and numeric testing. Use when writing, reviewing, or refactoring code that uses numpy, pandas, DataFrames, ndarrays, Jupyter notebooks, or data pipelines, or when the user asks about pandas/numpy performance or idioms.

oracle Bundle

Oracle Database Navigator (DBN) language parser guide. Use when changing, reviewing, explaining, validating, or generating SQL/PSQL parser element XML files, language-parser-elements.dtd, grammar element definitions, parser branches, wrappers, semantic object/alias/variable identifiers, and dialect parser definitions under com/dbn/language.

parallel-web Skill

Bulk data enrichment. Adds web-sourced fields (CEO names, funding, contact info) to lists of companies, people, or products. Use for enriching CSV files or inline data. Supports multi-turn: pass --previous-interaction-id from a prior research task to carry context forward.

pol-cc Bundle

Add a new dbt model (staging, intermediate, or marts) to an existing MDS deployment. Invoke when the user wants to transform raw data, build an analytics table, or expose a new metric in BigQuery.

pol-cc Bundle

Add a new BigQuery-backed skill to the MCP server: a tool exposed to AI agents plus the .md context files that describe the underlying data. Invoke when the user wants AI agents (claude.ai, Claude Code, Cursor) to query a new domain of the warehouse.

pruthivim Bundle

Turns raw user research into a structured insight matrix mapping user statements to problem statements. Reads interview transcripts, call recording transcripts, written call notes, or survey verbatims and distills them into themes, problem statements, verbatim quotes, severity, and frequency — instead of manual tagging in a spreadsheet. Use whenever the user uploads or references interview transcripts, call notes, user interviews, customer feedback, or qualitative research, or asks to "synthesize," "find themes in," "pull insights from," "tag," "code," or "make sense of" research data — even without saying "insight matrix." Also use for casual phrasings like "what are customers complaining about" or "what's coming up across these calls," or requests to find pain points, recurring complaints, or unexpected/workaround user behaviors. Handles a single transcript or a batch from the same project, offering a combined cross-interview matrix once each is processed.

quanhua92 Skill

Fetch raw OHLCV price data using the aipa CLI. Use this skill whenever the user asks for price data, candle data, OHLCV data, historical prices, stock quotes, crypto prices, moving averages, volume data, or any raw market data without AI analysis. Also use for: top performers, worst performers, best stocks, top gainers, biggest losers, market movers, ranking tickers by price change / volume / value / MA scores / money flow (`aipa performers`); volume profile, POC, point of control, value area, support/resistance by volume, volume-by-price histogram (`aipa volume-profile`). Also use for fundamental data: company info, financial ratios, PE, PB, ROE, NPL, CAR, fundamental ranking and screening (`aipa fundamentals info/ratios/rank/screen`). Also use when the user wants to inspect what data is available, build charts, perform their own calculations, or get numbers for a spreadsheet. Even if the user doesn't mention "aipa", trigger this skill for any raw financial data, fundamental data, or market ranking request.

autumnsgrove Bundle

Comprehensive Excel spreadsheet creation, editing, and analysis with support for formulas, formatting, charts, data analysis, and visualization. Use when working with .xlsx, .xlsm, .csv files for: (1) Creating spreadsheets with formulas and formatting, (2) Reading/analyzing data, (3) Modifying existing spreadsheets while preserving formulas, (4) Creating charts and visualizations, (5) Data transformation and analysis, (6) Multi-worksheet operations

autumnsgrove Bundle

Expert SQL query writing, optimization, and database schema design with support for PostgreSQL, MySQL, SQLite, and SQL Server. Use when working with databases for: (1) Writing complex SQL queries with joins, subqueries, and window functions, (2) Optimizing slow queries and analyzing execution plans, (3) Designing database schemas with proper normalization, (4) Creating indexes and improving query performance, (5) Writing migrations and handling schema changes, (6) Debugging SQL errors and query issues

harperaa Skill

Understand how AI generates SQL injection, command injection, and XSS vulnerabilities. Use this skill when you need to learn about injection attack patterns in AI code, see real-world examples of injection vulnerabilities, understand why AI generates insecure database queries, or recognize vulnerable code patterns. Triggers include "SQL injection AI", "command injection", "XSS vulnerabilities", "injection attacks", "AI database queries", "shell injection", "cross-site scripting AI code".

91zgaoge Skill

Analyze uploaded documents (PDF, Word, Excel, PPT) using local RAG system at http://localhost:9000. Use when user uploads a file and asks to analyze, summarize, or extract information from it.

shopify Skill

Development workflow guide for Shopify's Hydrogen framework. Covers testing, upgrading, recipes, PR conventions, analytics architecture, CLI tooling, and project scaffolding. Use when developing the Hydrogen framework. Also activates when someone mentions "recipes", "patch files", "customer account testing", "hydrogen upgrade", "skeleton template", "hydrogen CLI", "create-hydrogen", "hydrogen init", or "shopify-cli-update" in the headless context.

shrek-abaper Bundle

Read and write ABAP source code and metadata from SAP systems via the ADT REST API. Use when the user asks to read, view, analyze, modify, write, or activate ABAP programs, classes, function modules, function groups, interfaces, includes, CDS views, DDIC tables, structures, data elements, domains, type groups, transactions, or packages. Also handles: syntax checking, where-used analysis, Open SQL data preview, transport request management (list, create, release), and searching for ABAP objects by name. Write and transport operations require explicit capability flags enabled in config, AND require user confirmation for every individual operation — confirmation is one-time and never reused across operations in the same session. On first use, guides the user through SAP credential setup interactively.

skill-commons Skill

Synthetic input whose frontmatter name disagrees with its directory identity.