Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Author, validate, and test Power Query M expressions in semantic model partitions. Automatically invoke when the user mentions "Power Query", "M code", "M expression", "partition expression", "query folding", or asks to "write Power Query", "fix Power Query", "test a partition", "preview partition data", "debug Power Query step", "optimize Power Query".
Intelligent stock analysis skill. Enter a stock ticker (A-shares/Hong Kong/U.S. stocks) to automatically: 1. Fetch real-time quotes and historical K-line data 2. Calculate technical indicators (MA/MACD/RSI/volume/deviation rate) 3. Provide an overall score (out of 100) and buy/sell signals 4. Search the latest news 5. Perform AI analysis and output a decision dashboard. Trigger when the user provides a ticker for analysis, asks how a stock is doing, requests market analysis, etc. Example inputs: “Analyze TSLA PLTR,” “How is 600519 doing?” “Take a look at HK00700”
Use when authoring or modifying a Datex Studio storage component (configurationTypeId=17, *-storage.json suffix) on a branch — cloud-persisted Mongo storage accessed via $db at function-tier. Owns the storage-vs-Footprint entity decision, column descriptor shape, the `required: true` read-then-patch trap (additive-only-after-shipping), additive evolution rules, and impact analysis before schema changes. Triggers: "create a storage", "add a column to xxx_storage", "options/config table", "rule table", "daily snapshot capture", "$db.update validation error after adding a required column", deciding between storage and Footprint entity.
Dense vector embeddings, semantic search, RAG pipelines, and reranking via Together AI. Generate embeddings with open-source models and rerank results behind dedicated endpoints. Reach for it whenever the user needs vector representations or retrieval quality improvements rather than direct text generation.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like “the xlsx in my downloads”) — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Use when the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions “A/B test,” “split test,” “experiment,” “test this change,” “variant copy,” “multivariate test,” “hypothesis,” “should I test this,” “which version is better,” “test two versions,” “statistical significance,” “how long should I run this test,” “growth experiments,” “experiment velocity,” “experiment backlog,” “ICE score,” “experimentation program,” or “experiment playbook.” Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.
Creates a new venue-profile YAML for venues/conferences/ from a conference CFP URL, validates it against venues/schema.yml, and preps the contribution PR. Use when the user wants to add a venue, contribute or refresh a venue profile, encode a conference's submission requirements (deadlines, page limits, blind level, template invocation, rebuttal format, submission system) as machine-readable YAML, copy a profile forward to a new year, or validate a profile before opening a pull request. Covers scaffolding the file, extracting facts from the live CFP, the DBLP/Semantic Scholar/Crossref alias table, the mandatory verified provenance block, schema validation, and PR-readiness checks.
This skill helps users extract structured product listings from Amazon, including titles, ASINs, prices, ratings, and specifications. Use this skill when users want to search for products on Amazon, find the best selling brand products, track price changes for items, get a list of categories with high ratings, compare different brand products on Amazon, extract Amazon product data for market research, look for products in a specific language or marketplace, analyze competitor pricing for keywords, find featured products for search terms, get technical specifications like material or color for product lists.
DCF valuation model for A-share stocks using Chinese financial data. Uses AkShare MCP for financial statements, WACC inputs (risk-free rate from China government bond yields), and growth projections. Use instead of the original dcf-model skill for Chinese equities.
Write, review, and migrate Supabase logs queries against the ClickHouse-backed `logs` table (the `logs.all.otel` analytics endpoint). Use this whenever a task involves Logs Explorer SQL, the `log_attributes` map, querying a log `source` (edge_logs, postgres_logs, auth_logs, etc.), translating an old BigQuery `cross join unnest(metadata)` logs query to ClickHouse, or wiring analytics log SQL in `apps/studio/data/logs` and `apps/studio/components/interfaces/Settings/Logs`. Reach for it even when the user just says "logs query", "Logs Explorer", or pastes a BigQuery logs query to convert, not only when they name ClickHouse.
Converts Excel (.xlsx) workbooks into Markdown so their contents can be accurately analyzed, summarized, searched, or extracted from. Use this skill whenever the user shares, references, or asks about a .xlsx file — even if they don't say "convert" or "markdown" explicitly. This includes requests to "read", "summarize", "review", "extract data from", "compare", "chart", or "analyze" a spreadsheet, workbook, budget, data export, or tracker. Always run the bundled conversion script to produce Markdown first; do not attempt to parse .xlsx content directly or write ad-hoc extraction code. Also use this skill for batch requests involving a whole folder of Excel workbooks. IMPORTANT: When the user references a folder or set of documents containing multiple file types (.pdf, .docx, .xlsx), invoke ALL three sibling skills — convert-pdf-to-md, convert-word-to-md, and convert-excel-to-md — so no file type is silently skipped.
Point Cowork at your invoices and payments records -- builds an AR aging report, drafts escalating follow-up emails matched to each invoice's age and the client relationship, and runs as a weekly scheduled task so nothing slips past 30 days unnoticed.
Drop a folder of vendor quotes, proposals, and SOWs on Cowork -- normalizes them into one comparison matrix, computes true total cost of ownership, surfaces the terms each vendor buried, and arms you with negotiation leverage points and reference-check questions.
The judgment layer SSOT for data visualization — load it before drawing any chart, dashboard, or board, not after. It governs "whether it should be drawn this way": what conclusion the chart wants the reader to reach, mean or median, whether aggregation is allowed, stacked or line, whether a dual axis is acceptable, color scheme and number of colors, whether the same entity keeps the same color and position across charts, and how many columns a table should keep. Medium-agnostic: it applies to HTML report pages, React/Vue dashboards, native PPT charts, matplotlib/plotly/ECharts/D3, and charts rendered to PNG alike. Use before drawing charts, or when reviewing existing charts ("what's wrong with these charts", "why are the legends inconsistent"). Not for report page layout/components/interaction (use report-with-html:report-with-html) or the implementation and rendering pitfalls of native PPT charts (use deck-creator:deck-creator).
Power BI deployment, CI/CD, governance, and administration. PROACTIVELY activate for: (1) Power BI deployment pipelines (Service deployment pipelines, fabric-cicd, custom workflows), (2) CI/CD for Power BI via GitHub Actions or Azure DevOps, (3) workspace management and roles, (4) row-level security (RLS) and object-level security (OLS), (5) capacity management (Premium, PPU, Fabric SKUs F2-F2048), (6) tenant settings and governance, (7) Power BI Report Server deployments, (8) service principal setup for automation, (9) data-gateway management. Provides: deployment-pipeline templates, GitHub Actions and Azure DevOps YAML, RLS/OLS implementation patterns, capacity sizing guidance, and service-principal auth recipes.
Product selection data query and analysis for Mercado Libre, calling 24 tools for products, official links, keywords, categories, trends, stores, reviews, exchange rates and plan usage through the LinkFox gateway, covering the Mexico, Brazil, Argentina, Chile and Colombia sites. This skill triggers when the user mentions Mercado Libre, product selection on Mercado Libre, product search, category trends, trending keyword searches, reverse traffic keyword lookup, store lookup, review lookup, exchange rates or plan usage.
Use to pull many structured records from ONE known listing page — team directories, product/pricing catalogs, job listings, conference speakers, paginated lists. ALSO read this when writing code that integrates the /v1/extract endpoint (schema, async polling, NDJSON results). Uses Linkup's async /v1/extract REST endpoint and returns NDJSON rows. Requires LINKUP_API_KEY. For a single page's prose use linkup-fetch; for web discovery use linkup-search.
Pipeline analysis composite. Pulls deal/meeting data from any CRM or tracking system, analyzes the pipeline over a user-defined period (weekly, fortnightly, monthly, quarterly), and produces both an executive summary and a detailed diagnostic report. Covers volume, qualification rates, source effectiveness, stage velocity, stuck deals, and actionable recommendations. Tool-agnostic — works with any CRM (Salesforce, HubSpot, Pipedrive, Close, Supabase, CSV).
Design or critique an A/B test or controlled product experiment with statistical rigor — pre-registered falsifiable hypothesis, sample-size/power up front, a full business cycle, one primary metric plus guardrails, segment + long-term reads, and a pre-set iterate/pivot/persevere decision. Catches the defaults Claude misses: peeking/early stopping, tiny samples, no guardrails, vanity metrics, \"it won\" with no learning loop. Trigger when asked to set up or review an A/B test, design an experiment, pick experiment metrics, decide sample size/significance/duration, or interpret/act on test results.
Programmatic Power BI development with PBIR, PBIP, TMDL, TOM, and fabric-cicd. PROACTIVELY activate for: (1) creating Power BI reports programmatically (PBIR enhanced report format), (2) PBIR vs PBIR-Legacy selection (2026 default), (3) PBIP developer mode and Power BI project files, (4) Tabular Object Model (TOM) / .NET SDK scripting, (5) Tabular Editor scripting (C# scripts, advanced scripting), (6) pbi-tools workflows, (7) fabric-cicd Python deployments (FabricWorkspace, publish_all_items), (8) Fabric CLI (fab deploy), (9) Semantic Link / sempy / semantic-link-labs, (10) generating PBIX programmatically, (11) parameter.yml for environment-specific deployments, (12) ALM Toolkit. Provides: PBIR/PBIP project templates, fabric-cicd deploy.py, Tabular Editor scripting recipes, parameter.yml patterns, and end-to-end programmatic workflows.
Generate publication-ready scientific figures in Python/matplotlib with a consistent figures4papers house style. Use when creating or refining academic bar/trend/heatmap/scatter/multi-panel figures, enforcing visual consistency, or exporting paper-ready PNG/PDF/SVG outputs.
Follow-up Signals scout for recently merged pull requests. Works out whether each one has deployed, then checks the project's telemetry for whether it did what it claimed, had the impact it expected, or caused a side effect that needs a look.
Turso edge-hosted SQLite platform built on libSQL (open-source SQLite fork). Covers @libsql/client SDK, embedded replicas with local sync, multi-database per-tenant architecture, platform API for database provisioning, schema migrations, vector search with F32_BLOB, batch operations, interactive transactions, and encryption at rest. Use when connecting to Turso databases, configuring embedded replicas, provisioning databases via the platform API, implementing per-tenant database isolation, performing vector similarity search, or integrating libSQL with Drizzle ORM.
Expert ML engineer specializing in machine learning model lifecycle, production deployment, and ML system optimization. Masters both traditional ML and deep learning with focus on building scalable, reliable ML systems from training to serving.
Track reviews, ratings, sentiment, and brand mentions across Google Maps, Booking.com, TripAdvisor, Facebook, Instagram, YouTube, and TikTok. Use when user asks to monitor brand reputation, analyze reviews, track mentions, or gather customer feedback.
Store and query custom business data using CustomObjectMgr, OCAPI Data API, and Shopper Custom Objects API. Use this skill whenever the user needs to create, read, update, or search custom object instances, build processing queues with status fields, choose between site-scoped and organization-scoped storage, or query custom objects with bool/term filters. Also use when persisting non-standard data -- even if they just say 'store config per site' or 'query my custom data'.
Create financial plans for Chinese wealth management clients covering retirement, education, estate, and cash-flow planning. Adapted from the original financial-plan skill for Chinese tax rules, social security, and local financial products. Triggers on "A股财务规划", "理财规划", "financial plan China", "retirement plan China", "财务规划客户", "退休规划", "教育金规划", or "comprehensive financial plan".
Comprehensive A-share sector and industry landscape reports — market size, competitive positioning, policy environment, key A-share players, trading multiples, and thematic trends. Adapted from the original sector-overview skill for Chinese market structure and terminology. Triggers on "A股行业分析", "行业研究", "板块分析", "sector overview China", "A-share sector deep dive", "白酒/半导体/新能源 行业分析", or "[industry] landscape China".
Validate data quality in market analysis documents and blog articles before publication. Use when checking for price scale inconsistencies (ETF vs futures), instrument notation errors, date/day-of-week mismatches, allocation total errors, and unit mismatches. Supports English and Japanese content. Advisory mode -- flags issues as warnings for human review, not as blockers.
When the user wants to forecast demand, build forecasting models, or improve forecast accuracy. Also use when the user mentions "demand planning," "sales forecasting," "time series," "forecast accuracy," "demand sensing," "statistical forecasting," or "predictive analytics." For capacity planning based on forecasts, see capacity-planning. For S&OP integration, see sales-operations-planning.
Use this skill to find high-quality dividend growth stocks (12%+ annual dividend growth, 1.5%+ yield) that are experiencing temporary pullbacks, identified by RSI oversold conditions (RSI ≤40). This skill combines fundamental dividend analysis with technical timing indicators to identify buying opportunities in strong dividend growers during short-term weakness.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.